{"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/reasoning-segmentation","name":"Reasoning Segmentation","slug":"reasoning-segmentation","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":52,"papers_with_code":25,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"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":1,"rows_per_page":100,"shown":52,"of":52,"of_with_code":25,"tagged_in_all":52,"counts":{"archive_papers_tagged":52,"with_a_code_link":25,"where_syntology_ran_a_sample":12,"not_listed_spam_title":0,"listed":52,"listed_where_code_ran":12,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":10,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":10,"listed_every_run_a_failure_of_syntologys_instrument":2,"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/visionreasoner-unified-visual-perception-and","slug":"visionreasoner-unified-visual-perception-and","title":"VisionReasoner: Unified Visual Perception and Reasoning via Reinforcement Learning","date":"2025-05-17","arxiv_id":"2505.12081","repositories_listed":3,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":13,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/visionreasoner-unified-visual-perception-and#ran","syntology_url":"https://syntology.ai/paper/2505.12081","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.12081"}},"official":{"repos":["dvlab-research/VisionReasoner","hiyouga/easyr1","dvlab-research/Seg-Zero"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/seg-zero-reasoning-chain-guided-segmentation","slug":"seg-zero-reasoning-chain-guided-segmentation","title":"Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement","date":"2025-03-09","arxiv_id":"2503.06520","repositories_listed":3,"syntology":null},{"url":"/paper/seg-r1-segmentation-can-be-surprisingly","slug":"seg-r1-segmentation-can-be-surprisingly","title":"Seg-R1: Segmentation Can Be Surprisingly Simple with Reinforcement Learning","date":"2025-06-27","arxiv_id":"2506.22624","repositories_listed":2,"syntology":{"n":23,"n_ran":22,"n_constructed":0,"n_ran_checked":7,"n_instrument":15,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":4,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 15 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/seg-r1-segmentation-can-be-surprisingly#ran","syntology_url":"https://syntology.ai/paper/2506.22624","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.22624"}},"official":{"repos":["geshang777/Seg-R1"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/visa-reasoning-video-object-segmentation-via","slug":"visa-reasoning-video-object-segmentation-via","title":"VISA: Reasoning Video Object Segmentation via Large Language Models","date":"2024-07-16","arxiv_id":"2407.11325","repositories_listed":2,"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":2,"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/visa-reasoning-video-object-segmentation-via#ran","syntology_url":"https://syntology.ai/paper/2407.11325","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.11325"}},"official":{"repos":["cilinyan/VISA","cilinyan/revos-api"],"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"]}}},{"url":"/paper/lisa-reasoning-segmentation-via-large","slug":"lisa-reasoning-segmentation-via-large","title":"LISA: Reasoning Segmentation via Large Language Model","date":"2023-08-01","arxiv_id":"2308.00692","repositories_listed":2,"syntology":null},{"url":"/paper/openmaskdino3d-reasoning-3d-segmentation-via","slug":"openmaskdino3d-reasoning-3d-segmentation-via","title":"OpenMaskDINO3D : Reasoning 3D Segmentation via Large Language Model","date":"2025-06-05","arxiv_id":"2506.04837","repositories_listed":1,"syntology":null},{"url":"/paper/rvtbench-a-benchmark-for-visual-reasoning","slug":"rvtbench-a-benchmark-for-visual-reasoning","title":"RVTBench: A Benchmark for Visual Reasoning Tasks","date":"2025-05-17","arxiv_id":"2505.11838","repositories_listed":1,"syntology":null},{"url":"/paper/smartfreeedit-mask-free-spatial-aware-image","slug":"smartfreeedit-mask-free-spatial-aware-image","title":"SmartFreeEdit: Mask-Free Spatial-Aware Image Editing with Complex Instruction Understanding","date":"2025-04-17","arxiv_id":"2504.12704","repositories_listed":1,"syntology":null},{"url":"/paper/mmr-a-large-scale-benchmark-dataset-for-multi","slug":"mmr-a-large-scale-benchmark-dataset-for-multi","title":"MMR: A Large-scale Benchmark Dataset for Multi-target and Multi-granularity Reasoning Segmentation","date":"2025-03-18","arxiv_id":"2503.13881","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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/mmr-a-large-scale-benchmark-dataset-for-multi#ran","syntology_url":"https://syntology.ai/paper/2503.13881","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.13881"}},"official":{"repos":["jdg900/mmr"],"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/ufo-a-unified-approach-to-fine-grained-visual","slug":"ufo-a-unified-approach-to-fine-grained-visual","title":"UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface","date":"2025-03-03","arxiv_id":"2503.01342","repositories_listed":1,"syntology":null},{"url":"/paper/pixel-level-reasoning-segmentation-via-multi","slug":"pixel-level-reasoning-segmentation-via-multi","title":"Pixel-Level Reasoning Segmentation via Multi-turn Conversations","date":"2025-02-13","arxiv_id":"2502.09447","repositories_listed":1,"syntology":null},{"url":"/paper/the-devil-is-in-temporal-token-high-quality","slug":"the-devil-is-in-temporal-token-high-quality","title":"The Devil is in Temporal Token: High Quality Video Reasoning Segmentation","date":"2025-01-15","arxiv_id":"2501.08549","repositories_listed":1,"syntology":null},{"url":"/paper/hyperseg-hybrid-segmentation-assistant-with","slug":"hyperseg-hybrid-segmentation-assistant-with","title":"HyperSeg: Hybrid Segmentation Assistant with Fine-grained Visual Perceiver","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/instructseg-unifying-instructed-visual","slug":"instructseg-unifying-instructed-visual","title":"InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models","date":"2024-12-18","arxiv_id":"2412.14006","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":8,"n_instrument":4,"n_unverified":2,"n_honours":2,"n_violates":1,"n_no_contract":5,"n_pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 1 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/instructseg-unifying-instructed-visual#ran","syntology_url":"https://syntology.ai/paper/2412.14006","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.14006"}},"official":{"repos":["congvvc/instructseg"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/hyperseg-towards-universal-visual","slug":"hyperseg-towards-universal-visual","title":"HyperSeg: Towards Universal Visual Segmentation with Large Language Model","date":"2024-11-26","arxiv_id":"2411.17606","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":8,"n_instrument":5,"n_unverified":4,"n_honours":4,"n_violates":2,"n_no_contract":2,"n_pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 2 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/hyperseg-towards-universal-visual#ran","syntology_url":"https://syntology.ai/paper/2411.17606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17606"}},"official":{"repos":["congvvc/HyperSeg"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/one-token-to-seg-them-all-language-instructed","slug":"one-token-to-seg-them-all-language-instructed","title":"One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos","date":"2024-09-29","arxiv_id":"2409.19603","repositories_listed":1,"syntology":{"n":16,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":8,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/one-token-to-seg-them-all-language-instructed#ran","syntology_url":"https://syntology.ai/paper/2409.19603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19603"}},"official":{"repos":["showlab/videolisa"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/2409-13407","slug":"2409-13407","title":"Instruction-guided Multi-Granularity Segmentation and Captioning with Large Multimodal Model","date":"2024-09-20","arxiv_id":"2409.13407","repositories_listed":1,"syntology":null},{"url":"/paper/visual-agents-as-fast-and-slow-thinkers","slug":"visual-agents-as-fast-and-slow-thinkers","title":"Visual Agents as Fast and Slow Thinkers","date":"2024-08-16","arxiv_id":"2408.08862","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visual-agents-as-fast-and-slow-thinkers#ran","syntology_url":"https://syntology.ai/paper/2408.08862","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.08862"}},"official":{"repos":["guangyans/sys2-llava"],"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/2408-01120","slug":"2408-01120","title":"An Efficient and Effective Transformer Decoder-Based Framework for Multi-Task Visual Grounding","date":"2024-08-02","arxiv_id":"2408.01120","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":5,"n_instrument":7,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":15,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/2408-01120#ran","syntology_url":"https://syntology.ai/paper/2408.01120","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.01120"}},"official":{"repos":["chenwei746/eevg"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/villa-video-reasoning-segmentation-with-large","slug":"villa-video-reasoning-segmentation-with-large","title":"ViLLa: Video Reasoning Segmentation with Large Language Model","date":"2024-07-18","arxiv_id":"2407.14500","repositories_listed":1,"syntology":null},{"url":"/paper/reason3d-searching-and-reasoning-3d","slug":"reason3d-searching-and-reasoning-3d","title":"Reason3D: Searching and Reasoning 3D Segmentation via Large Language Model","date":"2024-05-27","arxiv_id":"2405.17427","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":7,"phrase":"5 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/reason3d-searching-and-reasoning-3d#ran","syntology_url":"https://syntology.ai/paper/2405.17427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17427"}},"official":{"repos":["kuanchihhuang/reason3d"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-seg-bridging-image-segmentation-and-large","slug":"llm-seg-bridging-image-segmentation-and-large","title":"LLM-Seg: Bridging Image Segmentation and Large Language Model Reasoning","date":"2024-04-12","arxiv_id":"2404.08767","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/llm-seg-bridging-image-segmentation-and-large#ran","syntology_url":"https://syntology.ai/paper/2404.08767","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.08767"}},"official":{"repos":["wangjunchi/llmseg"],"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/cores-orchestrating-the-dance-of-reasoning","slug":"cores-orchestrating-the-dance-of-reasoning","title":"CoReS: Orchestrating the Dance of Reasoning and Segmentation","date":"2024-04-08","arxiv_id":"2404.05673","repositories_listed":1,"syntology":{"n":13,"n_ran":5,"n_constructed":1,"n_ran_checked":2,"n_instrument":3,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":13,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/cores-orchestrating-the-dance-of-reasoning#ran","syntology_url":"https://syntology.ai/paper/2404.05673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05673"}},"official":{"repos":["baoxiaoyi/cores"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":8,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/an-improved-baseline-for-reasoning","slug":"an-improved-baseline-for-reasoning","title":"LISA++: An Improved Baseline for Reasoning Segmentation with Large Language Model","date":"2023-12-28","arxiv_id":"2312.17240","repositories_listed":1,"syntology":{"n":14,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":8,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/an-improved-baseline-for-reasoning#ran","syntology_url":"https://syntology.ai/paper/2312.17240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.17240"}},"official":null}},{"url":"/paper/pixellm-pixel-reasoning-with-large-multimodal","slug":"pixellm-pixel-reasoning-with-large-multimodal","title":"PixelLM: Pixel Reasoning with Large Multimodal Model","date":"2023-12-04","arxiv_id":"2312.02228","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 1 unverified","sample_list":"/paper/pixellm-pixel-reasoning-with-large-multimodal#ran","syntology_url":"https://syntology.ai/paper/2312.02228","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02228"}},"official":null}},{"url":null,"slug":"hrseg-high-resolution-visual-perception-and","title":"HRSeg: High-Resolution Visual Perception and Enhancement for Reasoning Segmentation","date":"2025-07-17","arxiv_id":"2507.12883","repositories_listed":0,"syntology":null},{"url":null,"slug":"medseg-r-reasoning-segmentation-in-medical","title":"MedSeg-R: Reasoning Segmentation in Medical Images with Multimodal Large Language Models","date":"2025-06-12","arxiv_id":"2506.10465","repositories_listed":0,"syntology":null},{"url":null,"slug":"decoupling-the-image-perception-and","title":"Decoupling the Image Perception and Multimodal Reasoning for Reasoning Segmentation with Digital Twin Representations","date":"2025-06-09","arxiv_id":"2506.07943","repositories_listed":0,"syntology":null},{"url":null,"slug":"rsvp-reasoning-segmentation-via-visual","title":"RSVP: Reasoning Segmentation via Visual Prompting and Multi-modal Chain-of-Thought","date":"2025-06-04","arxiv_id":"2506.04277","repositories_listed":0,"syntology":null},{"url":null,"slug":"pixelthink-towards-efficient-chain-of-pixel","title":"PixelThink: Towards Efficient Chain-of-Pixel Reasoning","date":"2025-05-29","arxiv_id":"2505.23727","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-segmentation-for-images-and-videos","title":"Reasoning Segmentation for Images and Videos: A Survey","date":"2025-05-24","arxiv_id":"2505.18816","repositories_listed":0,"syntology":null},{"url":null,"slug":"prs-med-position-reasoning-segmentation-with","title":"PRS-Med: Position Reasoning Segmentation with Vision-Language Model in Medical Imaging","date":"2025-05-17","arxiv_id":"2505.11872","repositories_listed":0,"syntology":null},{"url":null,"slug":"lisat-language-instructed-segmentation","title":"LISAT: Language-Instructed Segmentation Assistant for Satellite Imagery","date":"2025-05-05","arxiv_id":"2505.02829","repositories_listed":0,"syntology":null},{"url":null,"slug":"lvlm-csp-accelerating-large-vision-language","title":"LVLM_CSP: Accelerating Large Vision Language Models via Clustering, Scattering, and Pruning for Reasoning Segmentation","date":"2025-04-15","arxiv_id":"2504.10854","repositories_listed":0,"syntology":null},{"url":null,"slug":"medisee-reasoning-based-pixel-level","title":"MediSee: Reasoning-based Pixel-level Perception in Medical Images","date":"2025-04-15","arxiv_id":"2504.11008","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-reasoning-video-segmentation-with-just","title":"Online Reasoning Video Segmentation with Just-in-Time Digital Twins","date":"2025-03-27","arxiv_id":"2503.21056","repositories_listed":0,"syntology":null},{"url":null,"slug":"operating-room-workflow-analysis-via","title":"Operating Room Workflow Analysis via Reasoning Segmentation over Digital Twins","date":"2025-03-26","arxiv_id":"2503.21054","repositories_listed":0,"syntology":null},{"url":null,"slug":"mllm-for3d-adapting-multimodal-large-language","title":"MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation","date":"2025-03-23","arxiv_id":"2503.18135","repositories_listed":0,"syntology":null},{"url":null,"slug":"veggie-instructional-editing-and-reasoning","title":"VEGGIE: Instructional Editing and Reasoning Video Concepts with Grounded Generation","date":"2025-03-18","arxiv_id":"2503.14350","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-the-invisible-reasoning-complex-1","title":"Unveiling the Invisible: Reasoning Complex Occlusions Amodally with AURA","date":"2025-03-13","arxiv_id":"2503.10225","repositories_listed":0,"syntology":null},{"url":null,"slug":"think-before-you-segment-high-quality","title":"Think Before You Segment: High-Quality Reasoning Segmentation with GPT Chain of Thoughts","date":"2025-03-10","arxiv_id":"2503.07503","repositories_listed":0,"syntology":null},{"url":null,"slug":"popen-preference-based-optimization-and","title":"POPEN: Preference-Based Optimization and Ensemble for LVLM-Based Reasoning Segmentation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"prima-multi-image-vision-language-models-for","title":"PRIMA: Multi-Image Vision-Language Models for Reasoning Segmentation","date":"2024-12-19","arxiv_id":"2412.15209","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-3d-reasoning-segmentation-with","title":"Multimodal 3D Reasoning Segmentation with Complex Scenes","date":"2024-11-21","arxiv_id":"2411.13927","repositories_listed":0,"syntology":null},{"url":null,"slug":"motion-grounded-video-reasoning-understanding","title":"Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level","date":"2024-11-15","arxiv_id":"2411.09921","repositories_listed":0,"syntology":null},{"url":null,"slug":"segllm-multi-round-reasoning-segmentation","title":"SegLLM: Multi-round Reasoning Segmentation","date":"2024-10-24","arxiv_id":"2410.18923","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-03001","title":"One Framework to Rule Them All: Unifying Multimodal Tasks with LLM Neural-Tuning","date":"2024-08-06","arxiv_id":"2408.03001","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning3d-grounding-and-reasoning-in-3d","title":"Reasoning3D -- Grounding and Reasoning in 3D: Fine-Grained Zero-Shot Open-Vocabulary 3D Reasoning Part Segmentation via Large Vision-Language Models","date":"2024-05-29","arxiv_id":"2405.19326","repositories_listed":0,"syntology":null},{"url":null,"slug":"empowering-segmentation-ability-to-multi","title":"Empowering Segmentation Ability to Multi-modal Large Language Models","date":"2024-03-21","arxiv_id":"2403.14141","repositories_listed":0,"syntology":null},{"url":null,"slug":"foodlmm-a-versatile-food-assistant-using","title":"FoodLMM: A Versatile Food Assistant using Large Multi-modal Model","date":"2023-12-22","arxiv_id":"2312.14991","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-segmentation-road-network-generation","title":"Beyond Segmentation: Road Network Generation with Multi-Modal LLMs","date":"2023-10-15","arxiv_id":"2310.09755","repositories_listed":0,"syntology":null},{"url":null,"slug":"pave-the-way-to-grasp-anything-transferring","title":"Transferring Foundation Models for Generalizable Robotic Manipulation","date":"2023-06-09","arxiv_id":"2306.05716","repositories_listed":0,"syntology":null}],"syntology_records":14,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_where_code_ran":12,"papers_where_code_ran_first_page":"/task/reasoning-segmentation/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":"ran","page":1,"of":1,"url":"/task/reasoning-segmentation/papers/ran/1","json":"/task/reasoning-segmentation/papers/ran/1.json","rows":12}],"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":"8d912ae7d4894253cab7a66390e69000a235b2a8a47bf206bfd807bd3b4aed85","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}