{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/parameter-efficient-fine-tuning","name":"parameter-efficient fine-tuning","slug":"parameter-efficient-fine-tuning","description_markdown":"Parameter-Efficient Fine-Tuning (PEFT) is a technique used to adapt pre-trained models to new tasks with minimal changes to the model's parameters. This approach is particularly useful in scenarios where computational resources are limited or when it is desirable to maintain the original model's performance on the initial task.","categories":[{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":935,"papers_with_code":441,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/parameter-efficient-fine-tuning-on-boolq","slug":"parameter-efficient-fine-tuning-on-boolq","dataset":"BoolQ","dataset_url":"/dataset/boolq","rows_in_archive":4,"metrics":["Accuracy (% )"],"first_row_in_archive_order":{"model":"LLaMA2-7b","paper_title":"QLoRA: Efficient Finetuning of Quantized LLMs","paper_url":"/paper/qlora-efficient-finetuning-of-quantized-llms","paper_date":"2023-05-23","arxiv_id":"2305.14314","code_links":[{"title":"qwenlm/qwen","url":"https://github.com/qwenlm/qwen"},{"title":"QwenLM/Qwen-7B","url":"https://github.com/QwenLM/Qwen-7B"},{"title":"artidoro/qlora","url":"https://github.com/artidoro/qlora"},{"title":"huggingface/text-generation-inference","url":"https://github.com/huggingface/text-generation-inference"},{"title":"timdettmers/bitsandbytes","url":"https://github.com/timdettmers/bitsandbytes"},{"title":"qwenlm/qwen-vl","url":"https://github.com/qwenlm/qwen-vl"},{"title":"internlm/xtuner","url":"https://github.com/internlm/xtuner"},{"title":"openmedlab/pulse","url":"https://github.com/openmedlab/pulse"},{"title":"flagai-open/aquila2","url":"https://github.com/flagai-open/aquila2"},{"title":"pilancilab/caldera","url":"https://github.com/pilancilab/caldera"},{"title":"daniel-furman/sft-demos","url":"https://github.com/daniel-furman/sft-demos"},{"title":"ist-daslab/rosa","url":"https://github.com/ist-daslab/rosa"},{"title":"cornell-zhang/llm-datatypes","url":"https://github.com/cornell-zhang/llm-datatypes"},{"title":"brandon3964/multimodal-task-vector","url":"https://github.com/brandon3964/multimodal-task-vector"},{"title":"BatsResearch/LexC-Gen","url":"https://github.com/BatsResearch/LexC-Gen"},{"title":"jerrywu-code/susgen","url":"https://github.com/jerrywu-code/susgen"},{"title":"12kimih/hicupid","url":"https://github.com/12kimih/hicupid"},{"title":"Luohh5/Chain-of-Exemplar","url":"https://github.com/Luohh5/Chain-of-Exemplar"},{"title":"erikaawang/probing-multilingual-dynamics","url":"https://github.com/erikaawang/probing-multilingual-dynamics"},{"title":"Rain9876/ShareLoRA","url":"https://github.com/Rain9876/ShareLoRA"}],"syntology":{"n":26,"n_ran":18,"n_constructed":1,"n_ran_checked":6,"n_instrument":12,"n_unverified":8,"n_honours":2,"n_violates":2,"n_no_contract":2,"n_pointer_only":17,"phrase":"18 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 12 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/qlora-efficient-finetuning-of-quantized-llms#ran","syntology_url":"https://syntology.ai/paper/2305.14314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14314"}},"official":{"repos":["artidoro/qlora","timdettmers/bitsandbytes"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["community","listed","official","unlocated"]}}}},{"leaderboard":"/sota/parameter-efficient-fine-tuning-on-hellaswag","slug":"parameter-efficient-fine-tuning-on-hellaswag","dataset":"HellaSwag","dataset_url":"/dataset/hellaswag","rows_in_archive":3,"metrics":["Accuracy (% )"],"first_row_in_archive_order":{"model":"LLaMA2-7b","paper_title":"GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs","paper_url":"/paper/gift-sw-gaussian-noise-injected-fine-tuning","paper_date":"2024-08-27","arxiv_id":"2408.15300","code_links":[{"title":"On-Point-RND/GIFT_SW","url":"https://github.com/On-Point-RND/GIFT_SW"}],"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gift-sw-gaussian-noise-injected-fine-tuning#ran","syntology_url":"https://syntology.ai/paper/2408.15300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.15300"}},"official":{"repos":["On-Point-RND/GIFT_SW"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}}},{"leaderboard":"/sota/parameter-efficient-fine-tuning-on-winogrande","slug":"parameter-efficient-fine-tuning-on-winogrande","dataset":"WinoGrande","dataset_url":"/dataset/winogrande","rows_in_archive":3,"metrics":["Accuracy (% )"],"first_row_in_archive_order":{"model":"LLaMA2-7b","paper_title":"GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs","paper_url":"/paper/gift-sw-gaussian-noise-injected-fine-tuning","paper_date":"2024-08-27","arxiv_id":"2408.15300","code_links":[{"title":"On-Point-RND/GIFT_SW","url":"https://github.com/On-Point-RND/GIFT_SW"}],"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gift-sw-gaussian-noise-injected-fine-tuning#ran","syntology_url":"https://syntology.ai/paper/2408.15300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.15300"}},"official":{"repos":["On-Point-RND/GIFT_SW"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}}}],"datasets":[{"url":"/dataset/hellaswag","name":"HellaSwag","full_name":"","num_papers_in_archive":994},{"url":"/dataset/winogrande","name":"WinoGrande","full_name":"","num_papers_in_archive":703},{"url":"/dataset/boolq","name":"BoolQ","full_name":"Boolean Questions","num_papers_in_archive":701}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":10,"rows_per_page":100,"shown":100,"of":935,"of_with_code":441,"tagged_in_all":935,"counts":{"archive_papers_tagged":935,"with_a_code_link":441,"where_syntology_ran_a_sample":198,"not_listed_spam_title":0,"listed":935,"listed_where_code_ran":198,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":165,"every_run_a_failure_of_syntologys_instrument":33,"listed_with_a_run_with_no_instrument_failure":165,"listed_every_run_a_failure_of_syntologys_instrument":33,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/lora-low-rank-adaptation-of-large-language","slug":"lora-low-rank-adaptation-of-large-language","title":"LoRA: Low-Rank Adaptation of Large Language Models","date":"2021-06-17","arxiv_id":"2106.09685","repositories_listed":74,"syntology":{"n":84,"n_ran":51,"n_constructed":19,"n_ran_checked":43,"n_instrument":8,"n_unverified":33,"n_honours":1,"n_violates":0,"n_no_contract":42,"n_pointer_only":30,"phrase":"51 ran (of which 19 constructed an object rather than computing a result; 43 with no instrument failure: 1 honoured, 0 violated, 42 with no contract checked; 8 where Syntology's instrument failed) · 33 unverified","sample_list":"/paper/lora-low-rank-adaptation-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2106.09685","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09685"}},"official":{"repos":["microsoft/LoRA"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/qlora-efficient-finetuning-of-quantized-llms","slug":"qlora-efficient-finetuning-of-quantized-llms","title":"QLoRA: Efficient Finetuning of Quantized LLMs","date":"2023-05-23","arxiv_id":"2305.14314","repositories_listed":20,"syntology":{"n":26,"n_ran":18,"n_constructed":1,"n_ran_checked":6,"n_instrument":12,"n_unverified":8,"n_honours":2,"n_violates":2,"n_no_contract":2,"n_pointer_only":17,"phrase":"18 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 12 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/qlora-efficient-finetuning-of-quantized-llms#ran","syntology_url":"https://syntology.ai/paper/2305.14314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14314"}},"official":{"repos":["artidoro/qlora","timdettmers/bitsandbytes"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["community","listed","official","unlocated"]}}},{"url":"/paper/any2point-empowering-any-modality-large","slug":"any2point-empowering-any-modality-large","title":"Any2Point: Empowering Any-modality Large Models for Efficient 3D Understanding","date":"2024-04-11","arxiv_id":"2404.07989","repositories_listed":7,"syntology":{"n":24,"n_ran":17,"n_constructed":0,"n_ran_checked":7,"n_instrument":10,"n_unverified":7,"n_honours":1,"n_violates":2,"n_no_contract":4,"n_pointer_only":24,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 2 violated, 4 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/any2point-empowering-any-modality-large#ran","syntology_url":"https://syntology.ai/paper/2404.07989","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07989"}},"official":{"repos":["ivan-tang-3d/any2point"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/point-peft-parameter-efficient-fine-tuning","slug":"point-peft-parameter-efficient-fine-tuning","title":"Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models","date":"2023-10-04","arxiv_id":"2310.03059","repositories_listed":7,"syntology":null},{"url":"/paper/bitfit-simple-parameter-efficient-fine-tuning","slug":"bitfit-simple-parameter-efficient-fine-tuning","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","date":"2021-06-18","arxiv_id":"2106.10199","repositories_listed":6,"syntology":{"n":13,"n_ran":4,"n_constructed":1,"n_ran_checked":3,"n_instrument":1,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/bitfit-simple-parameter-efficient-fine-tuning#ran","syntology_url":"https://syntology.ai/paper/2106.10199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.10199"}},"official":{"repos":["benzakenelad/BitFit"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/dora-weight-decomposed-low-rank-adaptation","slug":"dora-weight-decomposed-low-rank-adaptation","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","date":"2024-02-14","arxiv_id":"2402.09353","repositories_listed":5,"syntology":{"n":15,"n_ran":8,"n_constructed":0,"n_ran_checked":0,"n_instrument":8,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":14,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/dora-weight-decomposed-low-rank-adaptation#ran","syntology_url":"https://syntology.ai/paper/2402.09353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09353"}},"official":{"repos":["NVlabs/DoRA","nbasyl/DoRA"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":7,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/point-bind-point-llm-aligning-point-cloud","slug":"point-bind-point-llm-aligning-point-cloud","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","date":"2023-09-01","arxiv_id":"2309.00615","repositories_listed":5,"syntology":{"n":20,"n_ran":15,"n_constructed":0,"n_ran_checked":9,"n_instrument":6,"n_unverified":5,"n_honours":3,"n_violates":1,"n_no_contract":5,"n_pointer_only":15,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 1 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/point-bind-point-llm-aligning-point-cloud#ran","syntology_url":"https://syntology.ai/paper/2309.00615","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.00615"}},"official":{"repos":["ziyuguo99/point-bind_point-llm"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/dora-enhancing-parameter-efficient-fine","slug":"dora-enhancing-parameter-efficient-fine","title":"DoRA: Enhancing Parameter-Efficient Fine-Tuning with Dynamic Rank Distribution","date":"2024-05-27","arxiv_id":"2405.17357","repositories_listed":4,"syntology":null},{"url":"/paper/s-lora-serving-thousands-of-concurrent-lora","slug":"s-lora-serving-thousands-of-concurrent-lora","title":"S-LoRA: Serving Thousands of Concurrent LoRA Adapters","date":"2023-11-06","arxiv_id":"2311.03285","repositories_listed":4,"syntology":null},{"url":"/paper/longlora-efficient-fine-tuning-of-long","slug":"longlora-efficient-fine-tuning-of-long","title":"LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models","date":"2023-09-21","arxiv_id":"2309.12307","repositories_listed":4,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/longlora-efficient-fine-tuning-of-long#ran","syntology_url":"https://syntology.ai/paper/2309.12307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12307"}},"official":{"repos":["dvlab-research/longlora"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/bone-block-affine-transformation-as-parameter","slug":"bone-block-affine-transformation-as-parameter","title":"Balancing LoRA Performance and Efficiency with Simple Shard Sharing","date":"2024-09-19","arxiv_id":"2409.15371","repositories_listed":3,"syntology":null},{"url":"/paper/segment-any-text-a-universal-approach-for","slug":"segment-any-text-a-universal-approach-for","title":"Segment Any Text: A Universal Approach for Robust, Efficient and Adaptable Sentence Segmentation","date":"2024-06-24","arxiv_id":"2406.16678","repositories_listed":3,"syntology":null},{"url":"/paper/analyzing-the-impact-of-data-selection-and","slug":"analyzing-the-impact-of-data-selection-and","title":"PoliTune: Analyzing the Impact of Data Selection and Fine-Tuning on Economic and Political Biases in Large Language Models","date":"2024-04-10","arxiv_id":"2404.08699","repositories_listed":3,"syntology":null},{"url":"/paper/an-embarrassingly-simple-approach-for-llm","slug":"an-embarrassingly-simple-approach-for-llm","title":"An Embarrassingly Simple Approach for LLM with Strong ASR Capacity","date":"2024-02-13","arxiv_id":"2402.08846","repositories_listed":3,"syntology":null},{"url":"/paper/learning-to-route-among-specialized-experts","slug":"learning-to-route-among-specialized-experts","title":"Learning to Route Among Specialized Experts for Zero-Shot Generalization","date":"2024-02-08","arxiv_id":"2402.05859","repositories_listed":3,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-to-route-among-specialized-experts#ran","syntology_url":"https://syntology.ai/paper/2402.05859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05859"}},"official":{"repos":["r-three/phatgoose"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/moelora-an-moe-based-parameter-efficient-fine","slug":"moelora-an-moe-based-parameter-efficient-fine","title":"When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications","date":"2023-10-21","arxiv_id":"2310.18339","repositories_listed":3,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/moelora-an-moe-based-parameter-efficient-fine#ran","syntology_url":"https://syntology.ai/paper/2310.18339","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.18339"}},"official":{"repos":["applied-machine-learning-lab/moelora-peft","liuqidong07/moelora-peft"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/owq-lessons-learned-from-activation-outliers","slug":"owq-lessons-learned-from-activation-outliers","title":"OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models","date":"2023-06-04","arxiv_id":"2306.02272","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/owq-lessons-learned-from-activation-outliers#ran","syntology_url":"https://syntology.ai/paper/2306.02272","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02272"}},"official":{"repos":["ecolab-postech/owq","xvyaward/owq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/glyphdraw-learning-to-draw-chinese-characters","slug":"glyphdraw-learning-to-draw-chinese-characters","title":"GlyphDraw: Seamlessly Rendering Text with Intricate Spatial Structures in Text-to-Image Generation","date":"2023-03-31","arxiv_id":"2303.17870","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/glyphdraw-learning-to-draw-chinese-characters#ran","syntology_url":"https://syntology.ai/paper/2303.17870","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17870"}},"official":{"repos":["OPPO-Mente-Lab/GlyphDraw"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/taste-text-aligned-speech-tokenization-and","slug":"taste-text-aligned-speech-tokenization-and","title":"TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling","date":"2025-04-09","arxiv_id":"2504.07053","repositories_listed":2,"syntology":{"n":20,"n_ran":14,"n_constructed":0,"n_ran_checked":12,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":20,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/taste-text-aligned-speech-tokenization-and#ran","syntology_url":"https://syntology.ai/paper/2504.07053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.07053"}},"official":{"repos":["mtkresearch/taste-spokenlm"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/farexstance-explainable-stance-detection-for","slug":"farexstance-explainable-stance-detection-for","title":"FarExStance: Explainable Stance Detection for Farsi","date":"2024-12-18","arxiv_id":"2412.14008","repositories_listed":2,"syntology":null},{"url":"/paper/prompt-compression-for-large-language-models","slug":"prompt-compression-for-large-language-models","title":"Prompt Compression for Large Language Models: A Survey","date":"2024-10-16","arxiv_id":"2410.12388","repositories_listed":2,"syntology":null},{"url":"/paper/one-initialization-to-rule-them-all-fine","slug":"one-initialization-to-rule-them-all-fine","title":"Parameter Efficient Fine-tuning via Explained Variance Adaptation","date":"2024-10-09","arxiv_id":"2410.07170","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/one-initialization-to-rule-them-all-fine#ran","syntology_url":"https://syntology.ai/paper/2410.07170","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07170"}},"official":{"repos":["BenediktAlkin/vtab1k-pytorch","ml-jku/EVA"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/lessons-learned-from-a-unifying-empirical","slug":"lessons-learned-from-a-unifying-empirical","title":"Lessons and Insights from a Unifying Study of Parameter-Efficient Fine-Tuning (PEFT) in Visual Recognition","date":"2024-09-24","arxiv_id":"2409.16434","repositories_listed":2,"syntology":null},{"url":"/paper/sam2rad-a-segmentation-model-for-medical","slug":"sam2rad-a-segmentation-model-for-medical","title":"Sam2Rad: A Segmentation Model for Medical Images with Learnable Prompts","date":"2024-09-10","arxiv_id":"2409.06821","repositories_listed":2,"syntology":null},{"url":"/paper/soft-language-prompts-for-language-transfer","slug":"soft-language-prompts-for-language-transfer","title":"Soft Language Prompts for Language Transfer","date":"2024-07-02","arxiv_id":"2407.02317","repositories_listed":2,"syntology":null},{"url":"/paper/low-rank-few-shot-adaptation-of-vision","slug":"low-rank-few-shot-adaptation-of-vision","title":"Low-Rank Few-Shot Adaptation of Vision-Language Models","date":"2024-05-28","arxiv_id":"2405.18541","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/low-rank-few-shot-adaptation-of-vision#ran","syntology_url":"https://syntology.ai/paper/2405.18541","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.18541"}},"official":null}},{"url":"/paper/iisan-efficiently-adapting-multimodal","slug":"iisan-efficiently-adapting-multimodal","title":"IISAN: Efficiently Adapting Multimodal Representation for Sequential Recommendation with Decoupled PEFT","date":"2024-04-02","arxiv_id":"2404.02059","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/iisan-efficiently-adapting-multimodal#ran","syntology_url":"https://syntology.ai/paper/2404.02059","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.02059"}},"official":{"repos":["gair-lab/iisan","jjgenailab/iisan"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/advancing-parameter-efficiency-in-fine-tuning","slug":"advancing-parameter-efficiency-in-fine-tuning","title":"Advancing Parameter Efficiency in Fine-tuning via Representation Editing","date":"2024-02-23","arxiv_id":"2402.15179","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/advancing-parameter-efficiency-in-fine-tuning#ran","syntology_url":"https://syntology.ai/paper/2402.15179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15179"}},"official":{"repos":["mlwu22/red"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/kinit-at-semeval-2024-task-8-fine-tuned-llms","slug":"kinit-at-semeval-2024-task-8-fine-tuned-llms","title":"KInIT at SemEval-2024 Task 8: Fine-tuned LLMs for Multilingual Machine-Generated Text Detection","date":"2024-02-21","arxiv_id":"2402.13671","repositories_listed":2,"syntology":null},{"url":"/paper/tunetables-context-optimization-for-scalable","slug":"tunetables-context-optimization-for-scalable","title":"TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks","date":"2024-02-17","arxiv_id":"2402.11137","repositories_listed":2,"syntology":{"n":17,"n_ran":12,"n_constructed":0,"n_ran_checked":5,"n_instrument":7,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/tunetables-context-optimization-for-scalable#ran","syntology_url":"https://syntology.ai/paper/2402.11137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11137"}},"official":{"repos":["penfever/tabpfn-pt","penfever/tunetables"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/democratizing-large-language-models-via","slug":"democratizing-large-language-models-via","title":"Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuning","date":"2024-02-06","arxiv_id":"2402.04401","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/democratizing-large-language-models-via#ran","syntology_url":"https://syntology.ai/paper/2402.04401","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04401"}},"official":{"repos":["tamsiuhin/oppu"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-sparse-fine-tuning-to-large-language","slug":"scaling-sparse-fine-tuning-to-large-language","title":"Scaling Sparse Fine-Tuning to Large Language Models","date":"2024-01-29","arxiv_id":"2401.16405","repositories_listed":2,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":4,"n_instrument":9,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/scaling-sparse-fine-tuning-to-large-language#ran","syntology_url":"https://syntology.ai/paper/2401.16405","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.16405"}},"official":{"repos":["alanansell/peft","ducdauge/sft-llm"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/gaussian-adaptive-attention-is-all-you-need","slug":"gaussian-adaptive-attention-is-all-you-need","title":"Density Adaptive Attention is All You Need: Robust Parameter-Efficient Fine-Tuning Across Multiple Modalities","date":"2024-01-20","arxiv_id":"2401.11143","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gaussian-adaptive-attention-is-all-you-need#ran","syntology_url":"https://syntology.ai/paper/2401.11143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.11143"}},"official":{"repos":["gioannides/gaussian-adaptive-attention"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/rosa-accurate-parameter-efficient-fine-tuning","slug":"rosa-accurate-parameter-efficient-fine-tuning","title":"RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation","date":"2024-01-09","arxiv_id":"2401.04679","repositories_listed":2,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/rosa-accurate-parameter-efficient-fine-tuning#ran","syntology_url":"https://syntology.ai/paper/2401.04679","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.04679"}},"official":{"repos":["ist-daslab/rosa"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/astraios-parameter-efficient-instruction","slug":"astraios-parameter-efficient-instruction","title":"Astraios: Parameter-Efficient Instruction Tuning Code Large Language Models","date":"2024-01-01","arxiv_id":"2401.00788","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/astraios-parameter-efficient-instruction#ran","syntology_url":"https://syntology.ai/paper/2401.00788","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.00788"}},"official":{"repos":["bigcode-project/astraios","agi-edgerunners/llm-adapters"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/federated-full-parameter-tuning-of-billion","slug":"federated-full-parameter-tuning-of-billion","title":"Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes","date":"2023-12-11","arxiv_id":"2312.06353","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/federated-full-parameter-tuning-of-billion#ran","syntology_url":"https://syntology.ai/paper/2312.06353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06353"}},"official":{"repos":["alibaba/federatedscope"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["named_in_paper"]}}},{"url":"/paper/aspen-high-throughput-lora-fine-tuning-of","slug":"aspen-high-throughput-lora-fine-tuning-of","title":"mLoRA: Fine-Tuning LoRA Adapters via Highly-Efficient Pipeline Parallelism in Multiple GPUs","date":"2023-12-05","arxiv_id":"2312.02515","repositories_listed":2,"syntology":null},{"url":"/paper/towards-general-purpose-vision-foundation","slug":"towards-general-purpose-vision-foundation","title":"Evaluating General Purpose Vision Foundation Models for Medical Image Analysis: An Experimental Study of DINOv2 on Radiology Benchmarks","date":"2023-12-04","arxiv_id":"2312.02366","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-general-purpose-vision-foundation#ran","syntology_url":"https://syntology.ai/paper/2312.02366","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02366"}},"official":{"repos":["mohammedsb/dinov2formedical","mohammedsb/dinov2forradiology"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/aggregate-decompose-and-fine-tune-a-simple","slug":"aggregate-decompose-and-fine-tune-a-simple","title":"Aggregate, Decompose, and Fine-Tune: A Simple Yet Effective Factor-Tuning Method for Vision Transformer","date":"2023-11-12","arxiv_id":"2311.06749","repositories_listed":2,"syntology":null},{"url":"/paper/empirical-study-of-peft-techniques-for-winter","slug":"empirical-study-of-peft-techniques-for-winter","title":"Empirical Study of PEFT techniques for Winter Wheat Segmentation","date":"2023-10-03","arxiv_id":"2310.01825","repositories_listed":2,"syntology":null},{"url":"/paper/fedjudge-federated-legal-large-language-model","slug":"fedjudge-federated-legal-large-language-model","title":"FedJudge: Federated Legal Large Language Model","date":"2023-09-15","arxiv_id":"2309.08173","repositories_listed":2,"syntology":null},{"url":"/paper/sct-a-simple-baseline-for-parameter-efficient","slug":"sct-a-simple-baseline-for-parameter-efficient","title":"SCT: A Simple Baseline for Parameter-Efficient Fine-Tuning via Salient Channels","date":"2023-09-15","arxiv_id":"2309.08513","repositories_listed":2,"syntology":null},{"url":"/paper/dept-decomposed-prompt-tuning-for-parameter","slug":"dept-decomposed-prompt-tuning-for-parameter","title":"DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning","date":"2023-09-11","arxiv_id":"2309.05173","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dept-decomposed-prompt-tuning-for-parameter#ran","syntology_url":"https://syntology.ai/paper/2309.05173","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.05173"}},"official":{"repos":["zhengxiangshi/dept"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/simteg-a-frustratingly-simple-approach","slug":"simteg-a-frustratingly-simple-approach","title":"SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning","date":"2023-08-03","arxiv_id":"2308.02565","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/simteg-a-frustratingly-simple-approach#ran","syntology_url":"https://syntology.ai/paper/2308.02565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.02565"}},"official":{"repos":["vermouthdky/simteg"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/explicit-visual-prompting-for-universal","slug":"explicit-visual-prompting-for-universal","title":"Explicit Visual Prompting for Universal Foreground Segmentations","date":"2023-05-29","arxiv_id":"2305.18476","repositories_listed":2,"syntology":null},{"url":"/paper/a-comprehensive-analysis-of-adapter","slug":"a-comprehensive-analysis-of-adapter","title":"A Comprehensive Analysis of Adapter Efficiency","date":"2023-05-12","arxiv_id":"2305.07491","repositories_listed":2,"syntology":null},{"url":"/paper/radadapt-radiology-report-summarization-via","slug":"radadapt-radiology-report-summarization-via","title":"RadAdapt: Radiology Report Summarization via Lightweight Domain Adaptation of Large Language Models","date":"2023-05-02","arxiv_id":"2305.01146","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/radadapt-radiology-report-summarization-via#ran","syntology_url":"https://syntology.ai/paper/2305.01146","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.01146"}},"official":{"repos":["davevanveen/radadapt"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/scaling-down-to-scale-up-a-guide-to-parameter","slug":"scaling-down-to-scale-up-a-guide-to-parameter","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","date":"2023-03-28","arxiv_id":"2303.15647","repositories_listed":2,"syntology":{"n":6,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/scaling-down-to-scale-up-a-guide-to-parameter#ran","syntology_url":"https://syntology.ai/paper/2303.15647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.15647"}},"official":{"repos":["guitaricet/peft_comparison"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/adaptive-budget-allocation-for-parameter","slug":"adaptive-budget-allocation-for-parameter","title":"AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning","date":"2023-03-18","arxiv_id":"2303.10512","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adaptive-budget-allocation-for-parameter#ran","syntology_url":"https://syntology.ai/paper/2303.10512","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.10512"}},"official":{"repos":["qingruzhang/adalora"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/visual-query-tuning-towards-effective-usage","slug":"visual-query-tuning-towards-effective-usage","title":"Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learning","date":"2022-12-06","arxiv_id":"2212.03220","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/visual-query-tuning-towards-effective-usage#ran","syntology_url":"https://syntology.ai/paper/2212.03220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03220"}},"official":{"repos":["andytu28/VQT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/few-shot-parameter-efficient-fine-tuning-is","slug":"few-shot-parameter-efficient-fine-tuning-is","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","date":"2022-05-11","arxiv_id":"2205.05638","repositories_listed":2,"syntology":null},{"url":"/paper/compacter-efficient-low-rank-hypercomplex","slug":"compacter-efficient-low-rank-hypercomplex","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","date":"2021-06-08","arxiv_id":"2106.04647","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/compacter-efficient-low-rank-hypercomplex#ran","syntology_url":"https://syntology.ai/paper/2106.04647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.04647"}},"official":{"repos":["rabeehk/compacter"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/losia-efficient-high-rank-fine-tuning-via","slug":"losia-efficient-high-rank-fine-tuning-via","title":"LoSiA: Efficient High-Rank Fine-Tuning via Subnet Localization and Optimization","date":"2025-07-06","arxiv_id":"2507.04487","repositories_listed":1,"syntology":null},{"url":"/paper/detecting-referring-expressions-in-visually","slug":"detecting-referring-expressions-in-visually","title":"Detecting Referring Expressions in Visually Grounded Dialogue with Autoregressive Language Models","date":"2025-06-26","arxiv_id":"2506.21294","repositories_listed":1,"syntology":null},{"url":"/paper/guilomo-allocating-expert-number-and-rank-for","slug":"guilomo-allocating-expert-number-and-rank-for","title":"GuiLoMo: Allocating Expert Number and Rank for LoRA-MoE via Bilevel Optimization with GuidedSelection Vectors","date":"2025-06-17","arxiv_id":"2506.14646","repositories_listed":1,"syntology":null},{"url":"/paper/ar-rag-autoregressive-retrieval-augmentation","slug":"ar-rag-autoregressive-retrieval-augmentation","title":"AR-RAG: Autoregressive Retrieval Augmentation for Image Generation","date":"2025-06-08","arxiv_id":"2506.06962","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-mixture-of-progressive-parameter","slug":"dynamic-mixture-of-progressive-parameter","title":"Dynamic Mixture of Progressive Parameter-Efficient Expert Library for Lifelong Robot Learning","date":"2025-06-06","arxiv_id":"2506.05985","repositories_listed":1,"syntology":null},{"url":"/paper/2506-04430","slug":"2506-04430","title":"Leveraging Coordinate Momentum in SignSGD and Muon: Memory-Optimized Zero-Order","date":"2025-06-04","arxiv_id":"2506.04430","repositories_listed":1,"syntology":null},{"url":"/paper/gradient-inversion-attacks-on-parameter","slug":"gradient-inversion-attacks-on-parameter","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","date":"2025-06-04","arxiv_id":"2506.04453","repositories_listed":1,"syntology":null},{"url":"/paper/parameter-efficient-fine-tuning-llama-3-1-for","slug":"parameter-efficient-fine-tuning-llama-3-1-for","title":"Parameter Efficient Fine Tuning Llama 3.1 for Answering Arabic Legal Questions: A Case Study on Jordanian Laws","date":"2025-06-02","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cl-lora-continual-low-rank-adaptation-for","slug":"cl-lora-continual-low-rank-adaptation-for","title":"CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental Learning","date":"2025-05-30","arxiv_id":"2505.24816","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-zero-initialization-investigating-the","slug":"beyond-zero-initialization-investigating-the","title":"Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics","date":"2025-05-29","arxiv_id":"2505.23194","repositories_listed":1,"syntology":null},{"url":"/paper/da-vpt-semantic-guided-visual-prompt-tuning","slug":"da-vpt-semantic-guided-visual-prompt-tuning","title":"DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers","date":"2025-05-29","arxiv_id":"2505.23694","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/da-vpt-semantic-guided-visual-prompt-tuning#ran","syntology_url":"https://syntology.ai/paper/2505.23694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23694"}},"official":{"repos":["noahsark/da-vpt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/loki-low-damage-knowledge-implanting-of-large","slug":"loki-low-damage-knowledge-implanting-of-large","title":"LoKI: Low-damage Knowledge Implanting of Large Language Models","date":"2025-05-28","arxiv_id":"2505.22120","repositories_listed":1,"syntology":null},{"url":"/paper/more-a-mixture-of-low-rank-experts-for","slug":"more-a-mixture-of-low-rank-experts-for","title":"MoRE: A Mixture of Low-Rank Experts for Adaptive Multi-Task Learning","date":"2025-05-28","arxiv_id":"2505.22694","repositories_listed":1,"syntology":null},{"url":"/paper/dlp-dynamic-layerwise-pruning-in-large","slug":"dlp-dynamic-layerwise-pruning-in-large","title":"DLP: Dynamic Layerwise Pruning in Large Language Models","date":"2025-05-27","arxiv_id":"2505.23807","repositories_listed":1,"syntology":{"n":10,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 10 unverified","sample_list":"/paper/dlp-dynamic-layerwise-pruning-in-large#ran","syntology_url":"https://syntology.ai/paper/2505.23807","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23807"}},"official":{"repos":["ironartisan/dlp"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":10,"ran_from_kinds":[]}}},{"url":"/paper/universal-reasoner-a-single-composable-plug","slug":"universal-reasoner-a-single-composable-plug","title":"Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs","date":"2025-05-25","arxiv_id":"2505.19075","repositories_listed":1,"syntology":null},{"url":"/paper/15500-seconds-lean-uav-classification","slug":"15500-seconds-lean-uav-classification","title":"15,500 Seconds: Lean UAV Classification Leveraging PEFT and Pre-Trained Networks","date":"2025-05-21","arxiv_id":"2506.11049","repositories_listed":1,"syntology":null},{"url":"/paper/4500-seconds-small-data-training-approaches","slug":"4500-seconds-small-data-training-approaches","title":"4,500 Seconds: Small Data Training Approaches for Deep UAV Audio Classification","date":"2025-05-21","arxiv_id":"2505.23782","repositories_listed":1,"syntology":null},{"url":"/paper/cola-collaborative-low-rank-adaptation","slug":"cola-collaborative-low-rank-adaptation","title":"CoLA: Collaborative Low-Rank Adaptation","date":"2025-05-21","arxiv_id":"2505.15471","repositories_listed":1,"syntology":null},{"url":"/paper/gated-integration-of-low-rank-adaptation-for","slug":"gated-integration-of-low-rank-adaptation-for","title":"Gated Integration of Low-Rank Adaptation for Continual Learning of Language Models","date":"2025-05-21","arxiv_id":"2505.15424","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gated-integration-of-low-rank-adaptation-for#ran","syntology_url":"https://syntology.ai/paper/2505.15424","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.15424"}},"official":{"repos":["liangyanshuo/gainlora"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/abba-highly-expressive-hadamard-product","slug":"abba-highly-expressive-hadamard-product","title":"ABBA: Highly Expressive Hadamard Product Adaptation for Large Language Models","date":"2025-05-20","arxiv_id":"2505.14238","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/abba-highly-expressive-hadamard-product#ran","syntology_url":"https://syntology.ai/paper/2505.14238","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.14238"}},"official":{"repos":["cert-lab/abba"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/quaff-quantized-parameter-efficient-fine","slug":"quaff-quantized-parameter-efficient-fine","title":"Quaff: Quantized Parameter-Efficient Fine-Tuning under Outlier Spatial Stability Hypothesis","date":"2025-05-20","arxiv_id":"2505.14742","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-sparsity-for-parameter-efficient","slug":"exploring-sparsity-for-parameter-efficient","title":"Exploring Sparsity for Parameter Efficient Fine Tuning Using Wavelets","date":"2025-05-18","arxiv_id":"2505.12532","repositories_listed":1,"syntology":null},{"url":"/paper/reasoning-on-a-budget-miniaturizing-deepseek","slug":"reasoning-on-a-budget-miniaturizing-deepseek","title":"Reasoning on a Budget: Miniaturizing DeepSeek R1 with SFT-GRPO Alignment for Instruction-Tuned LLMs","date":"2025-05-16","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/multi-token-prediction-needs-registers","slug":"multi-token-prediction-needs-registers","title":"Multi-Token Prediction Needs Registers","date":"2025-05-15","arxiv_id":"2505.10518","repositories_listed":1,"syntology":{"n":20,"n_ran":18,"n_constructed":0,"n_ran_checked":9,"n_instrument":9,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/multi-token-prediction-needs-registers#ran","syntology_url":"https://syntology.ai/paper/2505.10518","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.10518"}},"official":{"repos":["nasosger/mutor"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/pt-moe-an-efficient-finetuning-framework-for","slug":"pt-moe-an-efficient-finetuning-framework-for","title":"PT-MoE: An Efficient Finetuning Framework for Integrating Mixture-of-Experts into Prompt Tuning","date":"2025-05-14","arxiv_id":"2505.09519","repositories_listed":1,"syntology":null},{"url":"/paper/parameter-efficient-fine-tuning-of-vision","slug":"parameter-efficient-fine-tuning-of-vision","title":"Parameter-Efficient Fine-Tuning of Vision Foundation Model for Forest Floor Segmentation from UAV Imagery","date":"2025-05-13","arxiv_id":"2505.08932","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-large-language-models-for-28","slug":"leveraging-large-language-models-for-28","title":"Leveraging Large Language Models for enzymatic reaction prediction and characterization","date":"2025-05-08","arxiv_id":"2505.05616","repositories_listed":1,"syntology":null},{"url":"/paper/gaprompt-geometry-aware-point-cloud-prompt","slug":"gaprompt-geometry-aware-point-cloud-prompt","title":"GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model","date":"2025-05-07","arxiv_id":"2505.04119","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/gaprompt-geometry-aware-point-cloud-prompt#ran","syntology_url":"https://syntology.ai/paper/2505.04119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.04119"}},"official":{"repos":["zhoujiahuan1991/icml2025-gaprompt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/on-device-llm-for-context-aware-wi-fi-roaming","slug":"on-device-llm-for-context-aware-wi-fi-roaming","title":"On-Device LLM for Context-Aware Wi-Fi Roaming","date":"2025-05-07","arxiv_id":"2505.04174","repositories_listed":1,"syntology":null},{"url":"/paper/vision-graph-prompting-via-semantic-low-rank","slug":"vision-graph-prompting-via-semantic-low-rank","title":"Vision Graph Prompting via Semantic Low-Rank Decomposition","date":"2025-05-07","arxiv_id":"2505.04121","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/vision-graph-prompting-via-semantic-low-rank#ran","syntology_url":"https://syntology.ai/paper/2505.04121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.04121"}},"official":{"repos":["zhoujiahuan1991/icml2025-vgp"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/deepfakes-on-demand-the-rise-of-accessible","slug":"deepfakes-on-demand-the-rise-of-accessible","title":"Deepfakes on Demand: the rise of accessible non-consensual deepfake image generators","date":"2025-05-06","arxiv_id":"2505.03859","repositories_listed":1,"syntology":null},{"url":"/paper/spectrumfm-a-foundation-model-for-intelligent","slug":"spectrumfm-a-foundation-model-for-intelligent","title":"SpectrumFM: A Foundation Model for Intelligent Spectrum Management","date":"2025-05-02","arxiv_id":"2505.06256","repositories_listed":1,"syntology":null},{"url":"/paper/adcare-vlm-leveraging-large-vision-language","slug":"adcare-vlm-leveraging-large-vision-language","title":"AdCare-VLM: Leveraging Large Vision Language Model (LVLM) to Monitor Long-Term Medication Adherence and Care","date":"2025-05-01","arxiv_id":"2505.00275","repositories_listed":1,"syntology":{"n":10,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/adcare-vlm-leveraging-large-vision-language#ran","syntology_url":"https://syntology.ai/paper/2505.00275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.00275"}},"official":{"repos":["asad14053/AdCare-VLM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/deeclip-a-robust-and-generalizable","slug":"deeclip-a-robust-and-generalizable","title":"DeeCLIP: A Robust and Generalizable Transformer-Based Framework for Detecting AI-Generated Images","date":"2025-04-28","arxiv_id":"2504.19876","repositories_listed":1,"syntology":null},{"url":"/paper/clip-it-clip-based-pairing-for-histology","slug":"clip-it-clip-based-pairing-for-histology","title":"CLIP-IT: CLIP-based Pairing for Histology Images Classification","date":"2025-04-22","arxiv_id":"2504.16181","repositories_listed":1,"syntology":null},{"url":"/paper/pointlora-low-rank-adaptation-with-token-1","slug":"pointlora-low-rank-adaptation-with-token-1","title":"PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning","date":"2025-04-22","arxiv_id":"2504.16023","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pointlora-low-rank-adaptation-with-token-1#ran","syntology_url":"https://syntology.ai/paper/2504.16023","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.16023"}},"official":{"repos":["songw-zju/pointlora"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/reasoningv-efficient-verilog-code-generation","slug":"reasoningv-efficient-verilog-code-generation","title":"ReasoningV: Efficient Verilog Code Generation with Adaptive Hybrid Reasoning Model","date":"2025-04-20","arxiv_id":"2504.14560","repositories_listed":1,"syntology":null},{"url":"/paper/integrating-structural-and-semantic-signals","slug":"integrating-structural-and-semantic-signals","title":"Integrating Structural and Semantic Signals in Text-Attributed Graphs with BiGTex","date":"2025-04-16","arxiv_id":"2504.12474","repositories_listed":1,"syntology":null},{"url":"/paper/crossan-towards-efficient-and-effective","slug":"crossan-towards-efficient-and-effective","title":"CROSSAN: Towards Efficient and Effective Adaptation of Multiple Multimodal Foundation Models for Sequential Recommendation","date":"2025-04-14","arxiv_id":"2504.10307","repositories_listed":1,"syntology":null},{"url":"/paper/lori-reducing-cross-task-interference-in","slug":"lori-reducing-cross-task-interference-in","title":"LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation","date":"2025-04-10","arxiv_id":"2504.07448","repositories_listed":1,"syntology":null},{"url":"/paper/earth-adapter-bridge-the-geospatial-domain","slug":"earth-adapter-bridge-the-geospatial-domain","title":"Earth-Adapter: Bridge the Geospatial Domain Gaps with Mixture of Frequency Adaptation","date":"2025-04-08","arxiv_id":"2504.06220","repositories_listed":1,"syntology":null},{"url":"/paper/aroma-autonomous-rank-one-matrix-adaptation","slug":"aroma-autonomous-rank-one-matrix-adaptation","title":"AROMA: Autonomous Rank-one Matrix Adaptation","date":"2025-04-06","arxiv_id":"2504.05343","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/aroma-autonomous-rank-one-matrix-adaptation#ran","syntology_url":"https://syntology.ai/paper/2504.05343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.05343"}},"official":{"repos":["shudun23/aroma"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/clip-sla-parameter-efficient-clip-adaptation","slug":"clip-sla-parameter-efficient-clip-adaptation","title":"CLIP-SLA: Parameter-Efficient CLIP Adaptation for Continuous Sign Language Recognition","date":"2025-04-02","arxiv_id":"2504.01666","repositories_listed":1,"syntology":null},{"url":"/paper/dynmole-boosting-mixture-of-lora-experts-fine","slug":"dynmole-boosting-mixture-of-lora-experts-fine","title":"DynMoLE: Boosting Mixture of LoRA Experts Fine-Tuning with a Hybrid Routing Mechanism","date":"2025-04-01","arxiv_id":"2504.00661","repositories_listed":1,"syntology":null},{"url":"/paper/msplora-a-multi-scale-pyramid-low-rank","slug":"msplora-a-multi-scale-pyramid-low-rank","title":"MSPLoRA: A Multi-Scale Pyramid Low-Rank Adaptation for Efficient Model Fine-Tuning","date":"2025-03-27","arxiv_id":"2503.21838","repositories_listed":1,"syntology":null},{"url":"/paper/iap-improving-continual-learning-of-vision","slug":"iap-improving-continual-learning-of-vision","title":"IAP: Improving Continual Learning of Vision-Language Models via Instance-Aware Prompting","date":"2025-03-26","arxiv_id":"2503.20612","repositories_listed":1,"syntology":null},{"url":"/paper/quad-quantization-and-parameter-efficient","slug":"quad-quantization-and-parameter-efficient","title":"QUAD: Quantization and Parameter-Efficient Tuning of LLM with Activation Decomposition","date":"2025-03-25","arxiv_id":"2503.19353","repositories_listed":1,"syntology":null},{"url":"/paper/unlocking-the-hidden-potential-of-clip-in","slug":"unlocking-the-hidden-potential-of-clip-in","title":"Unlocking the Hidden Potential of CLIP in Generalizable Deepfake Detection","date":"2025-03-25","arxiv_id":"2503.19683","repositories_listed":1,"syntology":null}],"syntology_records":41,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":22,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/parameter-efficient-fine-tuning-on-boolq","since_archive":"/sota/parameter-efficient-fine-tuning-on-boolq#since-judged","papers_judged":16,"placed":0},{"leaderboard":"/sota/parameter-efficient-fine-tuning-on-hellaswag","since_archive":"/sota/parameter-efficient-fine-tuning-on-hellaswag#since-judged","papers_judged":10,"placed":0},{"leaderboard":"/sota/parameter-efficient-fine-tuning-on-winogrande","since_archive":"/sota/parameter-efficient-fine-tuning-on-winogrande#since-judged","papers_judged":8,"placed":0}]},"papers_where_code_ran":198,"papers_where_code_ran_first_page":"/task/parameter-efficient-fine-tuning/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":10,"url":"/task/parameter-efficient-fine-tuning/papers/2","json":"/task/parameter-efficient-fine-tuning/papers/2.json","rows":100},{"order":"archive","page":3,"of":10,"url":"/task/parameter-efficient-fine-tuning/papers/3","json":"/task/parameter-efficient-fine-tuning/papers/3.json","rows":100},{"order":"archive","page":4,"of":10,"url":"/task/parameter-efficient-fine-tuning/papers/4","json":"/task/parameter-efficient-fine-tuning/papers/4.json","rows":100},{"order":"archive","page":5,"of":10,"url":"/task/parameter-efficient-fine-tuning/papers/5","json":"/task/parameter-efficient-fine-tuning/papers/5.json","rows":100},{"order":"archive","page":6,"of":10,"url":"/task/parameter-efficient-fine-tuning/papers/6","json":"/task/parameter-efficient-fine-tuning/papers/6.json","rows":100},{"order":"archive","page":7,"of":10,"url":"/task/parameter-efficient-fine-tuning/papers/7","json":"/task/parameter-efficient-fine-tuning/papers/7.json","rows":100},{"order":"archive","page":8,"of":10,"url":"/task/parameter-efficient-fine-tuning/papers/8","json":"/task/parameter-efficient-fine-tuning/papers/8.json","rows":100},{"order":"archive","page":9,"of":10,"url":"/task/parameter-efficient-fine-tuning/papers/9","json":"/task/parameter-efficient-fine-tuning/papers/9.json","rows":100},{"order":"archive","page":10,"of":10,"url":"/task/parameter-efficient-fine-tuning/papers/10","json":"/task/parameter-efficient-fine-tuning/papers/10.json","rows":35},{"order":"ran","page":1,"of":2,"url":"/task/parameter-efficient-fine-tuning/papers/ran/1","json":"/task/parameter-efficient-fine-tuning/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/task/parameter-efficient-fine-tuning/papers/ran/2","json":"/task/parameter-efficient-fine-tuning/papers/ran/2.json","rows":98}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"ac6c1aeedd66a259452c768a7a9c2f966ef93a46988da4721af400291bebc313","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}