{"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":"/method/adafactor","slug":"adafactor","name":"Adafactor","full_name":"Adafactor","full_name_withheld":false,"description_markdown":"**Adafactor** is a stochastic optimization method based on [Adam](https://paperswithcode.com/method/adam) that reduces memory usage while retaining the empirical benefits of adaptivity. This is achieved through maintaining a factored representation of the squared gradient accumulator across training steps. Specifically, by tracking moving averages of the row and column sums of the squared gradients for matrix-valued variables, we are able to reconstruct a low-rank approximation of the exponentially smoothed accumulator at each training step that is optimal with respect to the generalized Kullback-Leibler divergence. For an $n \\times m$ matrix, this reduces the memory requirements from $O(n m)$ to $O(n + m)$. \r\n\r\nInstead of defining the optimization algorithm in terms of absolute step sizes {$\\alpha_t$}$\\_{t=1}^T$, the authors define the optimization algorithm in terms of relative step sizes {$\\rho_t$}$\\_{t=1}^T$, which get multiplied by the scale of the parameters. The scale of a parameter vector or matrix is defined as the root-mean-square of its components, lower-bounded by a small constant $\\epsilon_2$.  The reason for this lower bound is to allow zero-initialized parameters to escape 0. \r\n\r\nProposed hyperparameters are: $\\epsilon\\_{1} = 10^{-30}$, $\\epsilon\\_{2} = 10^{-3}$, $d=1$, $p\\_{t} = \\min\\left(10^{-2}, \\frac{1}{\\sqrt{t}}\\right)$, $\\hat{\\beta}\\_{2\\_{t}} = 1 - t^{-0.8}$.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","paper":"/paper/adafactor-adaptive-learning-rates-with","first_author":"Noam Shazeer","n_authors":2,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/adafactor-adaptive-learning-rates-with"},"source":{"url":"http://arxiv.org/abs/1804.04235v1","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/DeadAt0m/adafactor-pytorch/blob/561e627239c29c0be11256171a795b49e0404098/adafactor.py#L7","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Large Batch Optimization","url":"/methods/category/large-batch-optimization","pwc_aliases":[]},{"area":"General","area_id":"general","collection":"Stochastic Optimization","url":"/methods/category/stochastic-optimization","pwc_aliases":[]}],"n_papers_tagged":733,"archive_num_papers":733,"papers_newest_first":[{"paper":null,"slug":"chat-ghosting-a-comparative-study-of-methods","title":"Chat-Ghosting: A Comparative Study of Methods for Auto-Completion in Dialog Systems","date":"2025-07-08","arxiv_id":"2507.05940","n_code_links":0,"syntology":null},{"paper":null,"slug":"i-know-which-llm-wrote-your-code-last-summer","title":"I Know Which LLM Wrote Your Code Last Summer: LLM generated Code Stylometry for Authorship Attribution","date":"2025-06-18","arxiv_id":"2506.17323","n_code_links":0,"syntology":null},{"paper":null,"slug":"fretting-transformer-encoder-decoder-model","title":"Fretting-Transformer: Encoder-Decoder Model for MIDI to Tablature Transcription","date":"2025-06-17","arxiv_id":"2506.14223","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comprehensive-study-of-decoder-only-llms-1","title":"A Comprehensive Study of Decoder-Only LLMs for Text-to-Image Generation","date":"2025-06-09","arxiv_id":"2506.08210","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multi-dataset-evaluation-of-models-for","title":"A Multi-Dataset Evaluation of Models for Automated Vulnerability Repair","date":"2025-06-05","arxiv_id":"2506.04987","n_code_links":0,"syntology":null},{"paper":null,"slug":"decom-renorm-merge-model-merging-on-the-right","title":"Decom-Renorm-Merge: Model Merging on the Right Space Improves Multitasking","date":"2025-05-29","arxiv_id":"2505.23117","n_code_links":0,"syntology":null},{"paper":"/paper/shioenv-a-cli-behavior-capturing-environment","slug":"shioenv-a-cli-behavior-capturing-environment","title":"ShIOEnv: A CLI Behavior-Capturing Environment Enabling Grammar-Guided Command Synthesis for Dataset Curation","date":"2025-05-23","arxiv_id":"2505.18374","n_code_links":1,"syntology":null},{"paper":"/paper/logicase-effective-test-case-generation-from","slug":"logicase-effective-test-case-generation-from","title":"LogiCase: Effective Test Case Generation from Logical Description in Competitive Programming","date":"2025-05-21","arxiv_id":"2505.15039","n_code_links":0,"syntology":{"ran":11,"of":19,"n_ran_checked":5,"n_instrument":6,"unverified":8,"pointer_only":19,"phrase":"11 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 8 unverified","official":null}},{"paper":"/paper/eeg-to-text-translation-a-model-for","slug":"eeg-to-text-translation-a-model-for","title":"EEG-to-Text Translation: A Model for Deciphering Human Brain Activity","date":"2025-05-20","arxiv_id":"2505.13936","n_code_links":1,"syntology":null},{"paper":"/paper/masking-in-multi-hop-qa-an-analysis-of-how","slug":"masking-in-multi-hop-qa-an-analysis-of-how","title":"Masking in Multi-hop QA: An Analysis of How Language Models Perform with Context Permutation","date":"2025-05-16","arxiv_id":"2505.11754","n_code_links":1,"syntology":null},{"paper":null,"slug":"multilingual-machine-translation-with-quantum","title":"Multilingual Machine Translation with Quantum Encoder Decoder Attention-based Convolutional Variational Circuits","date":"2025-05-14","arxiv_id":"2505.09407","n_code_links":0,"syntology":null},{"paper":"/paper/cardioformer-advancing-ai-in-ecg-analysis","slug":"cardioformer-advancing-ai-in-ecg-analysis","title":"Cardioformer: Advancing AI in ECG Analysis with Multi-Granularity Patching and ResNet","date":"2025-05-08","arxiv_id":"2505.05538","n_code_links":1,"syntology":null},{"paper":null,"slug":"performance-evaluation-of-large-language-1","title":"Performance Evaluation of Large Language Models in Bangla Consumer Health Query Summarization","date":"2025-05-08","arxiv_id":"2505.05070","n_code_links":0,"syntology":null},{"paper":"/paper/gascade-grouped-summarization-of-adverse-drug","slug":"gascade-grouped-summarization-of-adverse-drug","title":"GASCADE: Grouped Summarization of Adverse Drug Event for Enhanced Cancer Pharmacovigilance","date":"2025-05-07","arxiv_id":"2505.04284","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-review-of-dna-restriction-free-overlapping","title":"A review of DNA restriction-free overlapping sequence cloning techniques for synthetic biology","date":"2025-05-06","arxiv_id":"2505.03681","n_code_links":0,"syntology":null},{"paper":null,"slug":"jaccdiv-a-metric-and-benchmark-for","title":"JaccDiv: A Metric and Benchmark for Quantifying Diversity of Generated Marketing Text in the Music Industry","date":"2025-04-29","arxiv_id":"2504.20849","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-are-qualified-benchmark","title":"Large Language Models are Qualified Benchmark Builders: Rebuilding Pre-Training Datasets for Advancing Code Intelligence Tasks","date":"2025-04-28","arxiv_id":"2504.19444","n_code_links":0,"syntology":null},{"paper":null,"slug":"fast-powerformer-a-memory-efficient","title":"Fast-Powerformer: A Memory-Efficient Transformer for Accurate Mid-Term Wind Power Forecasting","date":"2025-04-15","arxiv_id":"2504.10923","n_code_links":0,"syntology":null},{"paper":"/paper/sigma-a-dataset-for-text-to-code-semantic","slug":"sigma-a-dataset-for-text-to-code-semantic","title":"Sigma: A dataset for text-to-code semantic parsing with statistical analysis","date":"2025-04-05","arxiv_id":"2504.04301","n_code_links":1,"syntology":null},{"paper":null,"slug":"advancing-sentiment-analysis-in-tamil-english","title":"Advancing Sentiment Analysis in Tamil-English Code-Mixed Texts: Challenges and Transformer-Based Solutions","date":"2025-03-30","arxiv_id":"2503.23295","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-knowledge-graph-completion-with","title":"Enhancing Knowledge Graph Completion with Entity Neighborhood and Relation Context","date":"2025-03-29","arxiv_id":"2503.23205","n_code_links":0,"syntology":null},{"paper":"/paper/scaling-down-text-encoders-of-text-to-image","slug":"scaling-down-text-encoders-of-text-to-image","title":"Scaling Down Text Encoders of Text-to-Image Diffusion Models","date":"2025-03-25","arxiv_id":"2503.19897","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-training-and-inference-scaling-laws","slug":"exploring-training-and-inference-scaling-laws","title":"Exploring Training and Inference Scaling Laws in Generative Retrieval","date":"2025-03-24","arxiv_id":"2503.18941","n_code_links":1,"syntology":null},{"paper":null,"slug":"predicting-the-road-ahead-a-knowledge-graph","title":"Predicting the Road Ahead: A Knowledge Graph based Foundation Model for Scene Understanding in Autonomous Driving","date":"2025-03-24","arxiv_id":"2503.18730","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-code-llm-training-with-programmer","title":"Enhancing Code LLM Training with Programmer Attention","date":"2025-03-19","arxiv_id":"2503.14936","n_code_links":0,"syntology":null},{"paper":null,"slug":"dreamrenderer-taming-multi-instance-attribute","title":"DreamRenderer: Taming Multi-Instance Attribute Control in Large-Scale Text-to-Image Models","date":"2025-03-17","arxiv_id":"2503.12885","n_code_links":0,"syntology":null},{"paper":null,"slug":"arled-leveraging-led-based-arman-model-for","title":"ARLED: Leveraging LED-based ARMAN Model for Abstractive Summarization of Persian Long Documents","date":"2025-03-13","arxiv_id":"2503.10233","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-longformer-based-framework-for-accurate-and","title":"A LongFormer-Based Framework for Accurate and Efficient Medical Text Summarization","date":"2025-03-10","arxiv_id":"2503.06888","n_code_links":0,"syntology":null},{"paper":"/paper/roamify-designing-and-evaluating-an-llm-based","slug":"roamify-designing-and-evaluating-an-llm-based","title":"Roamify: Designing and Evaluating an LLM Based Google Chrome Extension for Personalised Itinerary Planning","date":"2025-03-10","arxiv_id":"2504.10489","n_code_links":1,"syntology":null},{"paper":null,"slug":"seeing-delta-parameters-as-jpeg-images-data","title":"Seeing Delta Parameters as JPEG Images: Data-Free Delta Compression with Discrete Cosine Transform","date":"2025-03-09","arxiv_id":"2503.06676","n_code_links":0,"syntology":null},{"paper":null,"slug":"moemoe-question-guided-dense-and-scalable","title":"MoEMoE: Question Guided Dense and Scalable Sparse Mixture-of-Expert for Multi-source Multi-modal Answering","date":"2025-03-08","arxiv_id":"2503.06296","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-transformer-model-for-predicting-chemical","title":"A Transformer Model for Predicting Chemical Reaction Products from Generic Templates","date":"2025-03-04","arxiv_id":"2503.05810","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-representation-alignment-for-image","slug":"multimodal-representation-alignment-for-image","title":"Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think","date":"2025-02-27","arxiv_id":"2502.20172","n_code_links":1,"syntology":null},{"paper":null,"slug":"ldgen-enhancing-text-to-image-synthesis-via","title":"LDGen: Enhancing Text-to-Image Synthesis via Large Language Model-Driven Language Representation","date":"2025-02-25","arxiv_id":"2502.18302","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-fine-tuning-approach-for-t5-using-knowledge","title":"A Fine-Tuning Approach for T5 Using Knowledge Graphs to Address Complex Tasks","date":"2025-02-23","arxiv_id":"2502.16484","n_code_links":0,"syntology":null},{"paper":null,"slug":"corrections-meet-explanations-a-unified","title":"Corrections Meet Explanations: A Unified Framework for Explainable Grammatical Error Correction","date":"2025-02-21","arxiv_id":"2502.15261","n_code_links":0,"syntology":null},{"paper":null,"slug":"empowering-llms-with-logical-reasoning-a","title":"Empowering LLMs with Logical Reasoning: A Comprehensive Survey","date":"2025-02-21","arxiv_id":"2502.15652","n_code_links":0,"syntology":null},{"paper":"/paper/bridging-text-and-vision-a-multi-view-text","slug":"bridging-text-and-vision-a-multi-view-text","title":"Bridging Text and Vision: A Multi-View Text-Vision Registration Approach for Cross-Modal Place Recognition","date":"2025-02-20","arxiv_id":"2502.14195","n_code_links":1,"syntology":null},{"paper":null,"slug":"order-agnostic-identifier-for-large-language","title":"Order-agnostic Identifier for Large Language Model-based Generative Recommendation","date":"2025-02-15","arxiv_id":"2502.10833","n_code_links":0,"syntology":null},{"paper":"/paper/a-large-scale-benchmark-for-vietnamese","slug":"a-large-scale-benchmark-for-vietnamese","title":"A Large-Scale Benchmark for Vietnamese Sentence Paraphrases","date":"2025-02-11","arxiv_id":"2502.07188","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-adaptive-moment-optimization-via","title":"Improving Adaptive Moment Optimization via Preconditioner Diagonalization","date":"2025-02-11","arxiv_id":"2502.07488","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-and-secure-code-watermarking-for-large","title":"Robust and Secure Code Watermarking for Large Language Models via ML/Crypto Codesign","date":"2025-02-04","arxiv_id":"2502.02068","n_code_links":0,"syntology":null},{"paper":null,"slug":"general-embedding-vs-task-specific-embedding","title":"General Embedding vs. Task-Specific Embedding: A Comparative Approach to Enhancing NLP Performance","date":"2025-01-30","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/visualizing-uncertainty-in-translation-tasks","slug":"visualizing-uncertainty-in-translation-tasks","title":"Visualizing Uncertainty in Translation Tasks: An Evaluation of LLM Performance and Confidence Metrics","date":"2025-01-26","arxiv_id":"2501.17187","n_code_links":1,"syntology":null},{"paper":null,"slug":"diffusion-based-text-to-music-generation-with","title":"Diffusion based Text-to-Music Generation with Global and Local Text based Conditioning","date":"2025-01-24","arxiv_id":"2501.14680","n_code_links":0,"syntology":null},{"paper":"/paper/confidence-estimation-for-error-detection-in","slug":"confidence-estimation-for-error-detection-in","title":"Confidence Estimation for Error Detection in Text-to-SQL Systems","date":"2025-01-16","arxiv_id":"2501.09527","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-robustness-of-multilingual-llms-on","slug":"exploring-robustness-of-multilingual-llms-on","title":"Exploring Robustness of Multilingual LLMs on Real-World Noisy Data","date":"2025-01-14","arxiv_id":"2501.08322","n_code_links":1,"syntology":null},{"paper":"/paper/mathreader-text-to-speech-for-mathematical","slug":"mathreader-text-to-speech-for-mathematical","title":"MathReader : Text-to-Speech for Mathematical Documents","date":"2025-01-13","arxiv_id":"2501.07088","n_code_links":1,"syntology":null},{"paper":null,"slug":"bridging-dialects-translating-standard-bangla","title":"Bridging Dialects: Translating Standard Bangla to Regional Variants Using Neural Models","date":"2025-01-10","arxiv_id":"2501.05749","n_code_links":0,"syntology":null},{"paper":null,"slug":"integrating-llms-with-its-recent-advances","title":"Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directions","date":"2025-01-08","arxiv_id":"2501.04437","n_code_links":0,"syntology":null},{"paper":"/paper/how-to-select-pre-trained-code-models-for","slug":"how-to-select-pre-trained-code-models-for","title":"How to Select Pre-Trained Code Models for Reuse? A Learning Perspective","date":"2025-01-07","arxiv_id":"2501.03783","n_code_links":1,"syntology":null},{"paper":null,"slug":"empowering-bengali-education-with-ai-solving","title":"Empowering Bengali Education with AI: Solving Bengali Math Word Problems through Transformer Models","date":"2025-01-05","arxiv_id":"2501.02599","n_code_links":0,"syntology":null},{"paper":"/paper/belin-a-novel-corpus-for-bengali-religious","slug":"belin-a-novel-corpus-for-bengali-religious","title":"BeliN: A Novel Corpus for Bengali Religious News Headline Generation using Contextual Feature Fusion","date":"2025-01-02","arxiv_id":"2501.01069","n_code_links":1,"syntology":null},{"paper":null,"slug":"reformer-generating-radio-fakes-for-data","title":"ReFormer: Generating Radio Fakes for Data Augmentation","date":"2024-12-31","arxiv_id":"2501.00282","n_code_links":0,"syntology":null},{"paper":"/paper/yad-leveraging-t5-for-improved-automatic","slug":"yad-leveraging-t5-for-improved-automatic","title":"YAD: Leveraging T5 for Improved Automatic Diacritization of Yorùbá Text","date":"2024-12-28","arxiv_id":"2412.20218","n_code_links":1,"syntology":null},{"paper":null,"slug":"hand-hierarchical-attention-network-for-multi","title":"HAND: Hierarchical Attention Network for Multi-Scale Handwritten Document Recognition and Layout Analysis","date":"2024-12-25","arxiv_id":"2412.18981","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-large-language-models-with-an","title":"Optimizing Large Language Models with an Enhanced LoRA Fine-Tuning Algorithm for Efficiency and Robustness in NLP Tasks","date":"2024-12-25","arxiv_id":"2412.18729","n_code_links":0,"syntology":null},{"paper":null,"slug":"advancing-explainability-in-neural-machine","title":"Advancing Explainability in Neural Machine Translation: Analytical Metrics for Attention and Alignment Consistency","date":"2024-12-24","arxiv_id":"2412.18669","n_code_links":0,"syntology":null},{"paper":null,"slug":"htr-jand-handwritten-text-recognition-with","title":"HTR-JAND: Handwritten Text Recognition with Joint Attention Network and Knowledge Distillation","date":"2024-12-24","arxiv_id":"2412.18524","n_code_links":0,"syntology":null},{"paper":null,"slug":"identifying-cyberbullying-roles-in-social","title":"Identifying Cyberbullying Roles in Social Media","date":"2024-12-21","arxiv_id":"2412.16417","n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarial-robustness-through-dynamic","title":"Adversarial Robustness through Dynamic Ensemble Learning","date":"2024-12-20","arxiv_id":"2412.16254","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-llms-obfuscate-code-a-systematic-analysis","title":"Can LLMs Obfuscate Code? A Systematic Analysis of Large Language Models into Assembly Code Obfuscation","date":"2024-12-20","arxiv_id":"2412.16135","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-first-multilingual-model-for-the","title":"The First Multilingual Model For The Detection of Suicide Texts","date":"2024-12-20","arxiv_id":"2412.15498","n_code_links":0,"syntology":null},{"paper":null,"slug":"llmcl-gec-advancing-grammatical-error","title":"LLMCL-GEC: Advancing Grammatical Error Correction with LLM-Driven Curriculum Learning","date":"2024-12-17","arxiv_id":"2412.12541","n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-guided-textual-explanation-generation","title":"Graph-Guided Textual Explanation Generation Framework","date":"2024-12-16","arxiv_id":"2412.12318","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-text-normalization-for-luxembourgish","title":"Neural Text Normalization for Luxembourgish using Real-Life Variation Data","date":"2024-12-12","arxiv_id":"2412.09383","n_code_links":0,"syntology":null},{"paper":"/paper/smmf-square-matricized-momentum-factorization","slug":"smmf-square-matricized-momentum-factorization","title":"SMMF: Square-Matricized Momentum Factorization for Memory-Efficient Optimization","date":"2024-12-12","arxiv_id":"2412.08894","n_code_links":1,"syntology":null},{"paper":null,"slug":"text-generation-models-for-luxembourgish-with","title":"Text Generation Models for Luxembourgish with Limited Data: A Balanced Multilingual Strategy","date":"2024-12-12","arxiv_id":"2412.09415","n_code_links":0,"syntology":null},{"paper":"/paper/are-clinical-t5-models-better-for-clinical","slug":"are-clinical-t5-models-better-for-clinical","title":"Are Clinical T5 Models Better for Clinical Text?","date":"2024-12-08","arxiv_id":"2412.05845","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-large-language-models-for-20","title":"Leveraging Large Language Models for Comparative Literature Summarization with Reflective Incremental Mechanisms","date":"2024-12-03","arxiv_id":"2412.02149","n_code_links":0,"syntology":null},{"paper":"/paper/sitse-sinhala-text-simplification-dataset-and","slug":"sitse-sinhala-text-simplification-dataset-and","title":"SiTSE: Sinhala Text Simplification Dataset and Evaluation","date":"2024-12-02","arxiv_id":"2412.01293","n_code_links":1,"syntology":null},{"paper":"/paper/a-comprehensive-guide-to-explainable-ai-from","slug":"a-comprehensive-guide-to-explainable-ai-from","title":"A Comprehensive Guide to Explainable AI: From Classical Models to LLMs","date":"2024-12-01","arxiv_id":"2412.00800","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-santali-linguistic-inclusion-building","title":"Towards Santali Linguistic Inclusion: Building the First Santali-to-English Translation Model using mT5 Transformer and Data Augmentation","date":"2024-11-29","arxiv_id":"2411.19726","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-extensive-evaluation-of-factual","title":"An Extensive Evaluation of Factual Consistency in Large Language Models for Data-to-Text Generation","date":"2024-11-28","arxiv_id":"2411.19203","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-on-cutting-edge-relation-extraction","title":"A survey on cutting-edge relation extraction techniques based on language models","date":"2024-11-27","arxiv_id":"2411.18157","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-fuzzy-system-for-sequence","title":"Generative Fuzzy System for Sequence Generation","date":"2024-11-21","arxiv_id":"2411.13867","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-combined-encoder-and-transformer-approach","title":"A Combined Encoder and Transformer Approach for Coherent and High-Quality Text Generation","date":"2024-11-19","arxiv_id":"2411.12157","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-multimodal-models-for-enhanced","title":"Leveraging Multimodal Models for Enhanced Neuroimaging Diagnostics in Alzheimer's Disease","date":"2024-11-12","arxiv_id":"2411.07871","n_code_links":0,"syntology":null},{"paper":"/paper/regress-don-t-guess-a-regression-like-loss-on","slug":"regress-don-t-guess-a-regression-like-loss-on","title":"Regress, Don't Guess -- A Regression-like Loss on Number Tokens for Language Models","date":"2024-11-04","arxiv_id":"2411.02083","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["tum-ai/number-token-loss"],"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":["official"]}}},{"paper":"/paper/training-free-regional-prompting-for","slug":"training-free-regional-prompting-for","title":"Training-free Regional Prompting for Diffusion Transformers","date":"2024-11-04","arxiv_id":"2411.02395","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["instantX-research/Regional-Prompting-FLUX"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/protransformer-robustify-transformers-via","slug":"protransformer-robustify-transformers-via","title":"ProTransformer: Robustify Transformers via Plug-and-Play Paradigm","date":"2024-10-30","arxiv_id":"2410.23182","n_code_links":1,"syntology":null},{"paper":"/paper/building-a-coding-assistant-via-the-retrieval","slug":"building-a-coding-assistant-via-the-retrieval","title":"Building A Coding Assistant via the Retrieval-Augmented Language Model","date":"2024-10-21","arxiv_id":"2410.16229","n_code_links":1,"syntology":null},{"paper":null,"slug":"unlocking-legal-knowledge-a-multilingual","title":"Unlocking Legal Knowledge: A Multilingual Dataset for Judicial Summarization in Switzerland","date":"2024-10-17","arxiv_id":"2410.13456","n_code_links":0,"syntology":null},{"paper":null,"slug":"tokenization-and-morphology-in-multilingual","title":"Tokenization and Morphology in Multilingual Language Models: A Comparative Analysis of mT5 and ByT5","date":"2024-10-15","arxiv_id":"2410.11627","n_code_links":0,"syntology":null},{"paper":"/paper/sana-efficient-high-resolution-image","slug":"sana-efficient-high-resolution-image","title":"SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers","date":"2024-10-14","arxiv_id":"2410.10629","n_code_links":2,"syntology":null},{"paper":null,"slug":"single-ground-truth-is-not-enough-add","title":"Single Ground Truth Is Not Enough: Add Linguistic Variability to Aspect-based Sentiment Analysis Evaluation","date":"2024-10-13","arxiv_id":"2410.09807","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-sparql-generation-by-triplet-order","slug":"enhancing-sparql-generation-by-triplet-order","title":"Enhancing SPARQL Generation by Triplet-order-sensitive Pre-training","date":"2024-10-08","arxiv_id":"2410.05731","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-free-energy-in-pretraining-model","title":"Leveraging free energy in pretraining model selection for improved fine-tuning","date":"2024-10-08","arxiv_id":"2410.05612","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-transfer-learning-based-peer-review","title":"Deep Transfer Learning Based Peer Review Aggregation and Meta-review Generation for Scientific Articles","date":"2024-10-05","arxiv_id":"2410.04202","n_code_links":0,"syntology":null},{"paper":"/paper/sieve-general-purpose-data-filtering-system","slug":"sieve-general-purpose-data-filtering-system","title":"GPT-4o as the Gold Standard: A Scalable and General Purpose Approach to Filter Language Model Pretraining Data","date":"2024-10-03","arxiv_id":"2410.02755","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-llm-fine-tuning-for-text-to-sqls-by","title":"Enhancing LLM Fine-tuning for Text-to-SQLs by SQL Quality Measurement","date":"2024-10-02","arxiv_id":"2410.01869","n_code_links":0,"syntology":null},{"paper":null,"slug":"glmha-a-guided-low-rank-multi-head-self","title":"GLMHA A Guided Low-rank Multi-Head Self-Attention for Efficient Image Restoration and Spectral Reconstruction","date":"2024-10-01","arxiv_id":"2410.00380","n_code_links":0,"syntology":null},{"paper":null,"slug":"abstractive-summarization-of-low-resourced","title":"Abstractive Summarization of Low resourced Nepali language using Multilingual Transformers","date":"2024-09-29","arxiv_id":"2409.19566","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-automatic-keyphrase-labelling-with","title":"Enhancing Automatic Keyphrase Labelling with Text-to-Text Transfer Transformer (T5) Architecture: A Framework for Keyphrase Generation and Filtering","date":"2024-09-25","arxiv_id":"2409.16760","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-omissions-and-distortions-in","title":"Probing Omissions and Distortions in Transformer-based RDF-to-Text Models","date":"2024-09-25","arxiv_id":"2409.16707","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-the-right-thing-just-debias-multi-category","title":"Do the Right Thing, Just Debias! Multi-Category Bias Mitigation Using LLMs","date":"2024-09-24","arxiv_id":"2409.16371","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-academic-skills-assessment-with-nlp","title":"Improving Academic Skills Assessment with NLP and Ensemble Learning","date":"2024-09-23","arxiv_id":"2409.19013","n_code_links":0,"syntology":null},{"paper":null,"slug":"emmett-efficient-multimodal-machine","title":"EMMeTT: Efficient Multimodal Machine Translation Training","date":"2024-09-20","arxiv_id":"2409.13523","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-large-language-models-for-product","title":"Exploring Large Language Models for Product Attribute Value Identification","date":"2024-09-19","arxiv_id":"2409.12695","n_code_links":0,"syntology":null},{"paper":"/paper/muri-high-quality-instruction-tuning-datasets","slug":"muri-high-quality-instruction-tuning-datasets","title":"MURI: High-Quality Instruction Tuning Datasets for Low-Resource Languages via Reverse Instructions","date":"2024-09-19","arxiv_id":"2409.12958","n_code_links":1,"syntology":null}],"papers_shown":100,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":733,"with_a_code_link":363,"where_syntology_ran_a_sample":103,"not_listed_spam_title":0,"listed":733,"listed_where_code_ran":103,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":89,"every_run_a_failure_of_syntologys_instrument":14,"listed_with_a_run_with_no_instrument_failure":89,"listed_every_run_a_failure_of_syntologys_instrument":14,"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"},"papers_where_code_ran":103,"papers_where_code_ran_first_page":"/method/adafactor/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"archive","page":2,"of":8,"url":"/method/adafactor/papers/2","json":"/method/adafactor/papers/2.json","rows":100},{"order":"archive","page":3,"of":8,"url":"/method/adafactor/papers/3","json":"/method/adafactor/papers/3.json","rows":100},{"order":"archive","page":4,"of":8,"url":"/method/adafactor/papers/4","json":"/method/adafactor/papers/4.json","rows":100},{"order":"archive","page":5,"of":8,"url":"/method/adafactor/papers/5","json":"/method/adafactor/papers/5.json","rows":100},{"order":"archive","page":6,"of":8,"url":"/method/adafactor/papers/6","json":"/method/adafactor/papers/6.json","rows":100},{"order":"archive","page":7,"of":8,"url":"/method/adafactor/papers/7","json":"/method/adafactor/papers/7.json","rows":100},{"order":"archive","page":8,"of":8,"url":"/method/adafactor/papers/8","json":"/method/adafactor/papers/8.json","rows":33},{"order":"ran","page":1,"of":2,"url":"/method/adafactor/papers/ran/1","json":"/method/adafactor/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/method/adafactor/papers/ran/2","json":"/method/adafactor/papers/ran/2.json","rows":3}],"tasks":[{"task":"/task/language-modelling","name":"Language Modelling","papers":128},{"task":"/task/language-modeling","name":"Language Modeling","papers":100},{"task":"/task/question-answering","name":"Question Answering","papers":86},{"task":"/task/decoder","name":"Decoder","papers":79},{"task":"/task/text-generation","name":"Text Generation","papers":65},{"task":"/task/sentence","name":"Sentence","papers":58},{"task":"/task/translation","name":"Translation","papers":47},{"task":"/task/machine-translation","name":"Machine Translation","papers":41},{"task":"/task/retrieval","name":"Retrieval","papers":40},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":40},{"task":"/task/natural-language-understanding","name":"Natural Language Understanding","papers":29},{"task":"/task/abstractive-text-summarization","name":"Abstractive Text Summarization","papers":23},{"task":"/task/semantic-parsing","name":"Semantic Parsing","papers":23},{"task":"/task/sentiment-analysis","name":"Sentiment Analysis","papers":22},{"task":"/task/natural-language-inference","name":"Natural Language Inference","papers":21},{"task":"/task/code-generation","name":"Code Generation","papers":20},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":20},{"task":"/task/text-summarization","name":"Text Summarization","papers":19},{"task":"/task/diversity","name":"Diversity","papers":18},{"task":"/task/knowledge-graphs","name":"Knowledge Graphs","papers":17}],"tasks_shown":20,"n_tasks":492,"usage_by_year":[{"year":"2018","papers":1},{"year":"2019","papers":2},{"year":"2020","papers":37},{"year":"2021","papers":112},{"year":"2022","papers":168},{"year":"2023","papers":202},{"year":"2024","papers":158},{"year":"2025","papers":53}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/adafactor"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Adafactor","read_at":"2026-10-05T00:51:26+00:00","query":"Adafactor","kind":"paper","have":"unverified_code","tier":"harvested","verified_implementation":false,"level":1,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"arxiv_id":"1804.04235"},"resolution":"paper","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"same_paper","archive_paper_arxiv_id":"1804.04235","repositories":{"listed":5,"in_graph":5,"list_truncated":false,"strongest_link":"mentioned_in_github"},"retrieve_with":"get_harvested_code_for_paper(arxiv_id='1804.04235')","name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"1804.04235","citations":1347},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'Adafactor'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"1804.04235","page":"/paper/adafactor-adaptive-learning-rates-with","syntology_url":"https://syntology.ai/paper/1804.04235","in_graph_layer":true,"samples":4,"ran":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"phrase":"4 ran (of which 0 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) · 0 unverified","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"harvested code stored, below machine verification (unverified_code; harvested), served level V1. Repositories: 5 listed of 5 in the graph, strongest link: mentioned on GitHub. The lookup matched a paper by its title, arXiv:1804.04235, not a method entry. This answer is about arXiv:1804.04235, the paper the archive credits with this method.","level_legend":{"state":"quoted","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","card_sha256":"479785a84658dd682a11b10237b3620d651d7f87799f5dc7add970aaa83f6d39","note":"Syntology's served verification levels, quoted verbatim from its MCP server card; a row is split where the card separates clauses with a double hyphen, and the separator is not reproduced","levels":[{"level":"V0","quoted":["imports"]},{"level":"V1","quoted":["executes against a synthesized fixture and returns a value of the recorded type"]},{"level":"V2","quoted":["two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs","neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)"]},{"level":"V3","quoted":["paper-derived property tests pass on both of those same two generations."]}],"no_rung":"No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results."}},"syntology_have_state":"loaded","record_sha256":"5ef5c95268a3cb609bffd8afa1da1f2d4b03f3e76ff9ebb28d13d71e0d0ddd49","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}