{"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 (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":25,"of":25,"tagged_in_all":52,"items":[{"url":"/paper/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":1,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/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","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":15,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/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_unverified":0,"n_pointer_only":2}},{"url":"/paper/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","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","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","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","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_unverified":1,"n_pointer_only":0}},{"url":"/paper/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","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","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","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","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":6,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/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":7,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/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":7,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/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","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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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":11,"n_unverified":4,"n_pointer_only":15}},{"url":"/paper/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","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_unverified":2,"n_pointer_only":7}},{"url":"/paper/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_unverified":1,"n_pointer_only":1}},{"url":"/paper/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_unverified":8,"n_pointer_only":13}},{"url":"/paper/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":4,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/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_unverified":1,"n_pointer_only":0}}],"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}