{"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/visual-reasoning/papers/2","list_of":"/task/visual-reasoning","task":"Visual Reasoning","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":7,"rows_per_page":100,"rows":[101,200],"of":698,"counts":{"archive_papers_tagged":698,"with_a_code_link":356,"where_syntology_ran_a_sample":165,"not_listed_spam_title":0,"listed":698,"listed_where_code_ran":165,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":130,"every_run_a_failure_of_syntologys_instrument":35,"listed_with_a_run_with_no_instrument_failure":130,"listed_every_run_a_failure_of_syntologys_instrument":35,"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"},"first_page":"/task/visual-reasoning","prev":"/task/visual-reasoning","next":"/task/visual-reasoning/papers/3","papers":[{"url":"/paper/deepeyes-incentivizing-thinking-with-images","slug":"deepeyes-incentivizing-thinking-with-images","title":"DeepEyes: Incentivizing \"Thinking with Images\" via Reinforcement Learning","date":"2025-05-20","arxiv_id":"2505.14362","repositories_listed":1,"syntology":{"n":17,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":4,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/deepeyes-incentivizing-thinking-with-images#ran","syntology_url":"https://syntology.ai/paper/2505.14362","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.14362"}},"official":{"repos":["visual-agent/deepeyes"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/visualquality-r1-reasoning-induced-image","slug":"visualquality-r1-reasoning-induced-image","title":"VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank","date":"2025-05-20","arxiv_id":"2505.14460","repositories_listed":1,"syntology":{"n":14,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/visualquality-r1-reasoning-induced-image#ran","syntology_url":"https://syntology.ai/paper/2505.14460","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.14460"}},"official":{"repos":["tianhewu/visualquality-r1"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/neurosymbolic-diffusion-models","slug":"neurosymbolic-diffusion-models","title":"Neurosymbolic Diffusion Models","date":"2025-05-19","arxiv_id":"2505.13138","repositories_listed":1,"syntology":null},{"url":"/paper/viplan-a-benchmark-for-visual-planning-with","slug":"viplan-a-benchmark-for-visual-planning-with","title":"ViPlan: A Benchmark for Visual Planning with Symbolic Predicates and Vision-Language Models","date":"2025-05-19","arxiv_id":"2505.13180","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/openthinkimg-learning-to-think-with-images","slug":"openthinkimg-learning-to-think-with-images","title":"OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning","date":"2025-05-13","arxiv_id":"2505.08617","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-vision-language-models-for-visual","slug":"leveraging-vision-language-models-for-visual","title":"Leveraging Vision-Language Models for Visual Grounding and Analysis of Automotive UI","date":"2025-05-09","arxiv_id":"2505.05895","repositories_listed":1,"syntology":null},{"url":"/paper/echoink-r1-exploring-audio-visual-reasoning","slug":"echoink-r1-exploring-audio-visual-reasoning","title":"EchoInk-R1: Exploring Audio-Visual Reasoning in Multimodal LLMs via Reinforcement Learning","date":"2025-05-07","arxiv_id":"2505.04623","repositories_listed":1,"syntology":null},{"url":"/paper/noisyrollout-reinforcing-visual-reasoning","slug":"noisyrollout-reinforcing-visual-reasoning","title":"NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation","date":"2025-04-17","arxiv_id":"2504.13055","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":5,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 5 samples that ran constructed an object rather than computing a result","sample_list":"/paper/noisyrollout-reinforcing-visual-reasoning#ran","syntology_url":"https://syntology.ai/paper/2504.13055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.13055"}},"official":null}},{"url":"/paper/colorbench-can-vlms-see-and-understand-the","slug":"colorbench-can-vlms-see-and-understand-the","title":"ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness","date":"2025-04-10","arxiv_id":"2504.10514","repositories_listed":1,"syntology":null},{"url":"/paper/sft-or-rl-an-early-investigation-into","slug":"sft-or-rl-an-early-investigation-into","title":"SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models","date":"2025-04-10","arxiv_id":"2504.11468","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/sft-or-rl-an-early-investigation-into#ran","syntology_url":"https://syntology.ai/paper/2504.11468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.11468"}},"official":null}},{"url":"/paper/vlm-r1-a-stable-and-generalizable-r1-style","slug":"vlm-r1-a-stable-and-generalizable-r1-style","title":"VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model","date":"2025-04-10","arxiv_id":"2504.07615","repositories_listed":1,"syntology":null},{"url":"/paper/omnicaptioner-one-captioner-to-rule-them-all","slug":"omnicaptioner-one-captioner-to-rule-them-all","title":"OmniCaptioner: One Captioner to Rule Them All","date":"2025-04-09","arxiv_id":"2504.07089","repositories_listed":1,"syntology":null},{"url":"/paper/v-mage-a-game-evaluation-framework-for","slug":"v-mage-a-game-evaluation-framework-for","title":"V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models","date":"2025-04-08","arxiv_id":"2504.06148","repositories_listed":1,"syntology":null},{"url":"/paper/tgraphx-tensor-aware-graph-neural-network-for","slug":"tgraphx-tensor-aware-graph-neural-network-for","title":"TGraphX: Tensor-Aware Graph Neural Network for Multi-Dimensional Feature Learning","date":"2025-04-04","arxiv_id":"2504.03953","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-rl-scaling-for-vision-language","slug":"rethinking-rl-scaling-for-vision-language","title":"Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme","date":"2025-04-03","arxiv_id":"2504.02587","repositories_listed":1,"syntology":null},{"url":"/paper/tdbench-benchmarking-vision-language-models","slug":"tdbench-benchmarking-vision-language-models","title":"TDBench: Benchmarking Vision-Language Models in Understanding Top-Down Images","date":"2025-04-01","arxiv_id":"2504.03748","repositories_listed":1,"syntology":null},{"url":"/paper/q-insight-understanding-image-quality-via","slug":"q-insight-understanding-image-quality-via","title":"Q-Insight: Understanding Image Quality via Visual Reinforcement Learning","date":"2025-03-28","arxiv_id":"2503.22679","repositories_listed":1,"syntology":null},{"url":"/paper/embodied-reasoner-synergizing-visual-search","slug":"embodied-reasoner-synergizing-visual-search","title":"Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks","date":"2025-03-27","arxiv_id":"2503.21696","repositories_listed":1,"syntology":null},{"url":"/paper/reason-rft-reinforcement-fine-tuning-for","slug":"reason-rft-reinforcement-fine-tuning-for","title":"Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning","date":"2025-03-26","arxiv_id":"2503.20752","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":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) · 4 unverified","sample_list":"/paper/reason-rft-reinforcement-fine-tuning-for#ran","syntology_url":"https://syntology.ai/paper/2503.20752","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.20752"}},"official":null}},{"url":"/paper/agentic-keyframe-search-for-video-question","slug":"agentic-keyframe-search-for-video-question","title":"Agentic Keyframe Search for Video Question Answering","date":"2025-03-20","arxiv_id":"2503.16032","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/agentic-keyframe-search-for-video-question#ran","syntology_url":"https://syntology.ai/paper/2503.16032","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.16032"}},"official":{"repos":["fansunqi/akeys"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/drivelmm-o1-a-step-by-step-reasoning-dataset","slug":"drivelmm-o1-a-step-by-step-reasoning-dataset","title":"DriveLMM-o1: A Step-by-Step Reasoning Dataset and Large Multimodal Model for Driving Scenario Understanding","date":"2025-03-13","arxiv_id":"2503.10621","repositories_listed":1,"syntology":null},{"url":"/paper/how-do-multimodal-large-language-models","slug":"how-do-multimodal-large-language-models","title":"How Do Multimodal Large Language Models Handle Complex Multimodal Reasoning? Placing Them in An Extensible Escape Game","date":"2025-03-13","arxiv_id":"2503.10042","repositories_listed":1,"syntology":null},{"url":"/paper/interpretable-image-classification-via-non","slug":"interpretable-image-classification-via-non","title":"Interpretable Image Classification via Non-parametric Part Prototype Learning","date":"2025-03-13","arxiv_id":"2503.10247","repositories_listed":1,"syntology":null},{"url":"/paper/physvlm-enabling-visual-language-models-to","slug":"physvlm-enabling-visual-language-models-to","title":"PhysVLM: Enabling Visual Language Models to Understand Robotic Physical Reachability","date":"2025-03-11","arxiv_id":"2503.08481","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/physvlm-enabling-visual-language-models-to#ran","syntology_url":"https://syntology.ai/paper/2503.08481","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.08481"}},"official":{"repos":["unira-zwj/PhysVLM"],"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/segagent-exploring-pixel-understanding","slug":"segagent-exploring-pixel-understanding","title":"SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories","date":"2025-03-11","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/segagent-exploring-pixel-understanding-1","slug":"segagent-exploring-pixel-understanding-1","title":"SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories","date":"2025-03-11","arxiv_id":"2503.08625","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 1 unverified","sample_list":"/paper/segagent-exploring-pixel-understanding-1#ran","syntology_url":"https://syntology.ai/paper/2503.08625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.08625"}},"official":{"repos":["aim-uofa/SegAgent"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/visrl-intention-driven-visual-perception-via","slug":"visrl-intention-driven-visual-perception-via","title":"VisRL: Intention-Driven Visual Perception via Reinforced Reasoning","date":"2025-03-10","arxiv_id":"2503.07523","repositories_listed":1,"syntology":null},{"url":"/paper/r1-zero-s-aha-moment-in-visual-reasoning-on-a","slug":"r1-zero-s-aha-moment-in-visual-reasoning-on-a","title":"R1-Zero's \"Aha Moment\" in Visual Reasoning on a 2B Non-SFT Model","date":"2025-03-07","arxiv_id":"2503.05132","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/r1-zero-s-aha-moment-in-visual-reasoning-on-a#ran","syntology_url":"https://syntology.ai/paper/2503.05132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.05132"}},"official":{"repos":["turningpoint-ai/visualthinker-r1-zero"],"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"]}}},{"url":"/paper/r1-onevision-an-open-source-multimodal-large","slug":"r1-onevision-an-open-source-multimodal-large","title":"R1-Onevision：An Open-Source Multimodal Large Language Model Capable of Deep Reasoning","date":"2025-02-24","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unraveling-the-geometry-of-visual-relational","slug":"unraveling-the-geometry-of-visual-relational","title":"Unraveling the geometry of visual relational reasoning","date":"2025-02-24","arxiv_id":"2502.17382","repositories_listed":1,"syntology":null},{"url":"/paper/forgotten-polygons-multimodal-large-language","slug":"forgotten-polygons-multimodal-large-language","title":"Forgotten Polygons: Multimodal Large Language Models are Shape-Blind","date":"2025-02-21","arxiv_id":"2502.15969","repositories_listed":1,"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/forgotten-polygons-multimodal-large-language#ran","syntology_url":"https://syntology.ai/paper/2502.15969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.15969"}},"official":{"repos":["rsinghlab/shape-blind"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/knowzrel-common-sense-knowledge-based-zero","slug":"knowzrel-common-sense-knowledge-based-zero","title":"KnowZRel: Common Sense Knowledge-based Zero-Shot Relationship Retrieval for Generalised Scene Graph Generation","date":"2025-02-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/alphamaze-enhancing-large-language-models","slug":"alphamaze-enhancing-large-language-models","title":"AlphaMaze: Enhancing Large Language Models' Spatial Intelligence via GRPO","date":"2025-02-20","arxiv_id":"2502.14669","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-cognition-and-explainability-of","slug":"enhancing-cognition-and-explainability-of","title":"Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data","date":"2025-02-19","arxiv_id":"2502.14044","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/enhancing-cognition-and-explainability-of#ran","syntology_url":"https://syntology.ai/paper/2502.14044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.14044"}},"official":{"repos":["sycny/selfsynthx"],"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"]}}},{"url":"/paper/llamav-o1-rethinking-step-by-step-visual","slug":"llamav-o1-rethinking-step-by-step-visual","title":"LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs","date":"2025-01-10","arxiv_id":"2501.06186","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/llamav-o1-rethinking-step-by-step-visual#ran","syntology_url":"https://syntology.ai/paper/2501.06186","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.06186"}},"official":{"repos":["mbzuai-oryx/llamav-o1"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/refocus-visual-editing-as-a-chain-of-thought","slug":"refocus-visual-editing-as-a-chain-of-thought","title":"ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding","date":"2025-01-09","arxiv_id":"2501.05452","repositories_listed":1,"syntology":null},{"url":"/paper/socratic-questioning-learn-to-self-guide","slug":"socratic-questioning-learn-to-self-guide","title":"Socratic Questioning: Learn to Self-guide Multimodal Reasoning in the Wild","date":"2025-01-06","arxiv_id":"2501.02964","repositories_listed":1,"syntology":null},{"url":"/paper/generalizing-from-simple-to-hard-visual","slug":"generalizing-from-simple-to-hard-visual","title":"Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?","date":"2025-01-05","arxiv_id":"2501.02669","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generalizing-from-simple-to-hard-visual#ran","syntology_url":"https://syntology.ai/paper/2501.02669","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.02669"}},"official":{"repos":["princeton-pli/vlm_s2h"],"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/hallucinogen-a-benchmark-for-evaluating","slug":"hallucinogen-a-benchmark-for-evaluating","title":"HALLUCINOGEN: A Benchmark for Evaluating Object Hallucination in Large Visual-Language Models","date":"2024-12-29","arxiv_id":"2412.20622","repositories_listed":1,"syntology":null},{"url":"/paper/progressive-multi-granular-alignments-for","slug":"progressive-multi-granular-alignments-for","title":"Progressive Multi-granular Alignments for Grounded Reasoning in Large Vision-Language Models","date":"2024-12-11","arxiv_id":"2412.08125","repositories_listed":1,"syntology":null},{"url":"/paper/mm-poe-multiple-choice-reasoning-via-process","slug":"mm-poe-multiple-choice-reasoning-via-process","title":"MM-PoE: Multiple Choice Reasoning via. Process of Elimination using Multi-Modal Models","date":"2024-12-10","arxiv_id":"2412.07148","repositories_listed":1,"syntology":null},{"url":"/paper/learning-visual-abstract-reasoning-through","slug":"learning-visual-abstract-reasoning-through","title":"Learning Visual Abstract Reasoning through Dual-Stream Networks","date":"2024-11-29","arxiv_id":"2411.19451","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":8,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 8 samples that ran constructed an object rather than computing a result","sample_list":"/paper/learning-visual-abstract-reasoning-through#ran","syntology_url":"https://syntology.ai/paper/2411.19451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.19451"}},"official":{"repos":["VecchioID/DRNet"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":8,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/immune-improving-safety-against-jailbreaks-in","slug":"immune-improving-safety-against-jailbreaks-in","title":"Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment","date":"2024-11-27","arxiv_id":"2411.18688","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/immune-improving-safety-against-jailbreaks-in#ran","syntology_url":"https://syntology.ai/paper/2411.18688","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.18688"}},"official":null}},{"url":"/paper/insight-v-exploring-long-chain-visual","slug":"insight-v-exploring-long-chain-visual","title":"Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models","date":"2024-11-21","arxiv_id":"2411.14432","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":10,"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) · 5 unverified","sample_list":"/paper/insight-v-exploring-long-chain-visual#ran","syntology_url":"https://syntology.ai/paper/2411.14432","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.14432"}},"official":{"repos":["dongyh20/insight-v"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/visual-contexts-clarify-ambiguous-expressions","slug":"visual-contexts-clarify-ambiguous-expressions","title":"Visual Contexts Clarify Ambiguous Expressions: A Benchmark Dataset","date":"2024-11-21","arxiv_id":"2411.14137","repositories_listed":1,"syntology":null},{"url":"/paper/clevrskills-compositional-language-and-visual","slug":"clevrskills-compositional-language-and-visual","title":"ClevrSkills: Compositional Language and Visual Reasoning in Robotics","date":"2024-11-13","arxiv_id":"2411.09052","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/clevrskills-compositional-language-and-visual#ran","syntology_url":"https://syntology.ai/paper/2411.09052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.09052"}},"official":{"repos":["Qualcomm-AI-research/ClevrSkills"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hourvideo-1-hour-video-language-understanding","slug":"hourvideo-1-hour-video-language-understanding","title":"HourVideo: 1-Hour Video-Language Understanding","date":"2024-11-07","arxiv_id":"2411.04998","repositories_listed":1,"syntology":{"n":16,"n_ran":14,"n_constructed":0,"n_ran_checked":13,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":1,"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) · 2 unverified","sample_list":"/paper/hourvideo-1-hour-video-language-understanding#ran","syntology_url":"https://syntology.ai/paper/2411.04998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04998"}},"official":{"repos":["keshik6/HourVideo"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/on-erroneous-agreements-of-clip-image","slug":"on-erroneous-agreements-of-clip-image","title":"On Erroneous Agreements of CLIP Image Embeddings","date":"2024-11-07","arxiv_id":"2411.05195","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":11,"phrase":"7 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; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/on-erroneous-agreements-of-clip-image#ran","syntology_url":"https://syntology.ai/paper/2411.05195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.05195"}},"official":{"repos":["lst627/CLIP-Embeds"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/inference-optimal-vlms-need-only-one-visual","slug":"inference-optimal-vlms-need-only-one-visual","title":"Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters","date":"2024-11-05","arxiv_id":"2411.03312","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/inference-optimal-vlms-need-only-one-visual#ran","syntology_url":"https://syntology.ai/paper/2411.03312","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.03312"}},"official":{"repos":["locuslab/llava-token-compression"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/logicity-advancing-neuro-symbolic-ai-with","slug":"logicity-advancing-neuro-symbolic-ai-with","title":"LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulation","date":"2024-11-01","arxiv_id":"2411.00773","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/logicity-advancing-neuro-symbolic-ai-with#ran","syntology_url":"https://syntology.ai/paper/2411.00773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00773"}},"official":{"repos":["Jaraxxus-Me/LogiCity"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bongard-in-wonderland-visual-puzzles-that","slug":"bongard-in-wonderland-visual-puzzles-that","title":"Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad?","date":"2024-10-25","arxiv_id":"2410.19546","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/bongard-in-wonderland-visual-puzzles-that#ran","syntology_url":"https://syntology.ai/paper/2410.19546","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.19546"}},"official":{"repos":["ml-research/bongard-in-wonderland"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/camel-bench-a-comprehensive-arabic-lmm","slug":"camel-bench-a-comprehensive-arabic-lmm","title":"CAMEL-Bench: A Comprehensive Arabic LMM Benchmark","date":"2024-10-24","arxiv_id":"2410.18976","repositories_listed":1,"syntology":null},{"url":"/paper/humaneval-v-evaluating-visual-understanding","slug":"humaneval-v-evaluating-visual-understanding","title":"HumanEval-V: Evaluating Visual Understanding and Reasoning Abilities of Large Multimodal Models Through Coding Tasks","date":"2024-10-16","arxiv_id":"2410.12381","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/humaneval-v-evaluating-visual-understanding#ran","syntology_url":"https://syntology.ai/paper/2410.12381","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.12381"}},"official":{"repos":["HumanEval-V/HumanEval-V-Benchmark"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mctbench-multimodal-cognition-towards-text","slug":"mctbench-multimodal-cognition-towards-text","title":"MCTBench: Multimodal Cognition towards Text-Rich Visual Scenes Benchmark","date":"2024-10-15","arxiv_id":"2410.11538","repositories_listed":1,"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":3,"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/mctbench-multimodal-cognition-towards-text#ran","syntology_url":"https://syntology.ai/paper/2410.11538","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11538"}},"official":{"repos":["xfey/mctbench"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-efficient-visual-language-alignment","slug":"towards-efficient-visual-language-alignment","title":"Towards Efficient Visual-Language Alignment of the Q-Former for Visual Reasoning Tasks","date":"2024-10-12","arxiv_id":"2410.09489","repositories_listed":1,"syntology":null},{"url":"/paper/tackling-the-abstraction-and-reasoning-corpus-1","slug":"tackling-the-abstraction-and-reasoning-corpus-1","title":"Tackling the Abstraction and Reasoning Corpus with Vision Transformers: the Importance of 2D Representation, Positions, and Objects","date":"2024-10-08","arxiv_id":"2410.06405","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"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 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) · 1 unverified","sample_list":"/paper/tackling-the-abstraction-and-reasoning-corpus-1#ran","syntology_url":"https://syntology.ai/paper/2410.06405","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.06405"}},"official":{"repos":["khalil-research/ViTARC"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mind-the-gap-glimpse-based-active-perception","slug":"mind-the-gap-glimpse-based-active-perception","title":"Mind the GAP: Glimpse-based Active Perception improves generalization and sample efficiency of visual reasoning","date":"2024-09-30","arxiv_id":"2409.20213","repositories_listed":1,"syntology":null},{"url":"/paper/from-seconds-to-hours-reviewing-multimodal","slug":"from-seconds-to-hours-reviewing-multimodal","title":"From Seconds to Hours: Reviewing MultiModal Large Language Models on Comprehensive Long Video Understanding","date":"2024-09-27","arxiv_id":"2409.18938","repositories_listed":1,"syntology":null},{"url":"/paper/finecops-ref-a-new-dataset-and-task-for-fine","slug":"finecops-ref-a-new-dataset-and-task-for-fine","title":"FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension","date":"2024-09-23","arxiv_id":"2409.14750","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"6 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; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/finecops-ref-a-new-dataset-and-task-for-fine#ran","syntology_url":"https://syntology.ai/paper/2409.14750","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.14750"}},"official":{"repos":["liujunzhuo/FineCops-Ref"],"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/journeybench-a-challenging-one-stop-vision","slug":"journeybench-a-challenging-one-stop-vision","title":"JourneyBench: A Challenging One-Stop Vision-Language Understanding Benchmark of Generated Images","date":"2024-09-19","arxiv_id":"2409.12953","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"7 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/journeybench-a-challenging-one-stop-vision#ran","syntology_url":"https://syntology.ai/paper/2409.12953","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.12953"}},"official":{"repos":["journeybench/journeybench"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/how-to-determine-the-preferred-image","slug":"how-to-determine-the-preferred-image","title":"How to Determine the Preferred Image Distribution of a Black-Box Vision-Language Model?","date":"2024-09-03","arxiv_id":"2409.02253","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/how-to-determine-the-preferred-image#ran","syntology_url":"https://syntology.ai/paper/2409.02253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.02253"}},"official":{"repos":["asgsaeid/cad_vqa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-modal-dialogue-state-tracking-for","slug":"multi-modal-dialogue-state-tracking-for","title":"Multi-Modal Dialogue State Tracking for Playing GuessWhich Game","date":"2024-08-15","arxiv_id":"2408.08431","repositories_listed":1,"syntology":null},{"url":"/paper/unibench-visual-reasoning-requires-rethinking","slug":"unibench-visual-reasoning-requires-rethinking","title":"UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling","date":"2024-08-09","arxiv_id":"2408.04810","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":9,"phrase":"5 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; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/unibench-visual-reasoning-requires-rethinking#ran","syntology_url":"https://syntology.ai/paper/2408.04810","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04810"}},"official":{"repos":["facebookresearch/unibench"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/artvlm-attribute-recognition-through-vision","slug":"artvlm-attribute-recognition-through-vision","title":"ArtVLM: Attribute Recognition Through Vision-Based Prefix Language Modeling","date":"2024-08-07","arxiv_id":"2408.04102","repositories_listed":1,"syntology":null},{"url":"/paper/a-plug-and-play-method-for-rare-human-object","slug":"a-plug-and-play-method-for-rare-human-object","title":"A Plug-and-Play Method for Rare Human-Object Interactions Detection by Bridging Domain Gap","date":"2024-07-31","arxiv_id":"2407.21438","repositories_listed":1,"syntology":null},{"url":"/paper/solving-robotics-problems-in-zero-shot-with","slug":"solving-robotics-problems-in-zero-shot-with","title":"Wonderful Team: Zero-Shot Physical Task Planning with Visual LLMs","date":"2024-07-26","arxiv_id":"2407.19094","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-learning-independent-abstract","slug":"investigating-learning-independent-abstract","title":"Untrained neural networks can demonstrate memorization-independent abstract reasoning","date":"2024-07-25","arxiv_id":"2407.17791","repositories_listed":1,"syntology":null},{"url":"/paper/kiva-kid-inspired-visual-analogies-for","slug":"kiva-kid-inspired-visual-analogies-for","title":"KiVA: Kid-inspired Visual Analogies for Testing Large Multimodal Models","date":"2024-07-25","arxiv_id":"2407.17773","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/kiva-kid-inspired-visual-analogies-for#ran","syntology_url":"https://syntology.ai/paper/2407.17773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.17773"}},"official":{"repos":["ey242/kiva"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/figure-it-out-analyzing-based-jailbreak","slug":"figure-it-out-analyzing-based-jailbreak","title":"LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models","date":"2024-07-23","arxiv_id":"2407.16205","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-self-instruct-synthetic-abstract","slug":"multimodal-self-instruct-synthetic-abstract","title":"Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Model","date":"2024-07-09","arxiv_id":"2407.07053","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/multimodal-self-instruct-synthetic-abstract#ran","syntology_url":"https://syntology.ai/paper/2407.07053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07053"}},"official":{"repos":["zwq2018/multi-modal-self-instruct"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tokenpacker-efficient-visual-projector-for","slug":"tokenpacker-efficient-visual-projector-for","title":"TokenPacker: Efficient Visual Projector for Multimodal LLM","date":"2024-07-02","arxiv_id":"2407.02392","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/tokenpacker-efficient-visual-projector-for#ran","syntology_url":"https://syntology.ai/paper/2407.02392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02392"}},"official":{"repos":["circleradon/tokenpacker"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/we-math-does-your-large-multimodal-model","slug":"we-math-does-your-large-multimodal-model","title":"We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?","date":"2024-07-01","arxiv_id":"2407.01284","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":0,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/we-math-does-your-large-multimodal-model#ran","syntology_url":"https://syntology.ai/paper/2407.01284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01284"}},"official":{"repos":["we-math/we-math"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/selective-vision-is-the-challenge-for-visual","slug":"selective-vision-is-the-challenge-for-visual","title":"Selective Vision is the Challenge for Visual Reasoning: A Benchmark for Visual Argument Understanding","date":"2024-06-27","arxiv_id":"2406.18925","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":10,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/selective-vision-is-the-challenge-for-visual#ran","syntology_url":"https://syntology.ai/paper/2406.18925","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18925"}},"official":{"repos":["jiwanchung/visargs"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/think-step-by-step-chain-of-gesture-prompting","slug":"think-step-by-step-chain-of-gesture-prompting","title":"Think Step by Step: Chain-of-Gesture Prompting for Error Detection in Robotic Surgical Videos","date":"2024-06-27","arxiv_id":"2406.19217","repositories_listed":1,"syntology":null},{"url":"/paper/visual-reasoning-and-multi-agent-approach-in","slug":"visual-reasoning-and-multi-agent-approach-in","title":"Visual Reasoning and Multi-Agent Approach in Multimodal Large Language Models (MLLMs): Solving TSP and mTSP Combinatorial Challenges","date":"2024-06-26","arxiv_id":"2407.00092","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-the-doors-of-perception-vision","slug":"beyond-the-doors-of-perception-vision","title":"Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects","date":"2024-06-22","arxiv_id":"2406.15955","repositories_listed":1,"syntology":null},{"url":"/paper/vdebugger-harnessing-execution-feedback-for","slug":"vdebugger-harnessing-execution-feedback-for","title":"VDebugger: Harnessing Execution Feedback for Debugging Visual Programs","date":"2024-06-19","arxiv_id":"2406.13444","repositories_listed":1,"syntology":null},{"url":"/paper/rs-gpt4v-a-unified-multimodal-instruction","slug":"rs-gpt4v-a-unified-multimodal-instruction","title":"RS-GPT4V: A Unified Multimodal Instruction-Following Dataset for Remote Sensing Image Understanding","date":"2024-06-18","arxiv_id":"2406.12479","repositories_listed":1,"syntology":null},{"url":"/paper/slot-state-space-models","slug":"slot-state-space-models","title":"Slot State Space Models","date":"2024-06-18","arxiv_id":"2406.12272","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":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) · 1 unverified","sample_list":"/paper/slot-state-space-models#ran","syntology_url":"https://syntology.ai/paper/2406.12272","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12272"}},"official":{"repos":["jindongjiang/slotssms"],"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/clawmachine-fetching-visual-tokens-as-an","slug":"clawmachine-fetching-visual-tokens-as-an","title":"ClawMachine: Learning to Fetch Visual Tokens for Referential Comprehension","date":"2024-06-17","arxiv_id":"2406.11327","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"6 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/clawmachine-fetching-visual-tokens-as-an#ran","syntology_url":"https://syntology.ai/paper/2406.11327","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11327"}},"official":{"repos":["martian422/clawmachine"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/neural-concept-binder","slug":"neural-concept-binder","title":"Neural Concept Binder","date":"2024-06-14","arxiv_id":"2406.09949","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/neural-concept-binder#ran","syntology_url":"https://syntology.ai/paper/2406.09949","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09949"}},"official":{"repos":["ml-research/neuralconceptbinder"],"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"]}}},{"url":"/paper/what-is-the-visual-cognition-gap-between","slug":"what-is-the-visual-cognition-gap-between","title":"What is the Visual Cognition Gap between Humans and Multimodal LLMs?","date":"2024-06-14","arxiv_id":"2406.10424","repositories_listed":1,"syntology":null},{"url":"/paper/ins-mmbench-a-comprehensive-benchmark-for","slug":"ins-mmbench-a-comprehensive-benchmark-for","title":"INS-MMBench: A Comprehensive Benchmark for Evaluating LVLMs' Performance in Insurance","date":"2024-06-13","arxiv_id":"2406.09105","repositories_listed":1,"syntology":null},{"url":"/paper/visual-sketchpad-sketching-as-a-visual-chain","slug":"visual-sketchpad-sketching-as-a-visual-chain","title":"Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models","date":"2024-06-13","arxiv_id":"2406.09403","repositories_listed":1,"syntology":null},{"url":"/paper/vdgd-mitigating-lvlm-hallucinations-in","slug":"vdgd-mitigating-lvlm-hallucinations-in","title":"Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs","date":"2024-05-24","arxiv_id":"2405.15683","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/vdgd-mitigating-lvlm-hallucinations-in#ran","syntology_url":"https://syntology.ai/paper/2405.15683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15683"}},"official":{"repos":["sreyan88/vdgd"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/learning-to-compose-improving-object-centric","slug":"learning-to-compose-improving-object-centric","title":"Learning to Compose: Improving Object Centric Learning by Injecting Compositionality","date":"2024-05-01","arxiv_id":"2405.00646","repositories_listed":1,"syntology":null},{"url":"/paper/list-items-one-by-one-a-new-data-source-and","slug":"list-items-one-by-one-a-new-data-source-and","title":"List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs","date":"2024-04-25","arxiv_id":"2404.16375","repositories_listed":1,"syntology":null},{"url":"/paper/marvel-multidimensional-abstraction-and","slug":"marvel-multidimensional-abstraction-and","title":"MARVEL: Multidimensional Abstraction and Reasoning through Visual Evaluation and Learning","date":"2024-04-21","arxiv_id":"2404.13591","repositories_listed":1,"syntology":null},{"url":"/paper/text-based-reasoning-about-vector-graphics","slug":"text-based-reasoning-about-vector-graphics","title":"Visually Descriptive Language Model for Vector Graphics Reasoning","date":"2024-04-09","arxiv_id":"2404.06479","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-embeddings-the-promise-of-visual-table","slug":"beyond-embeddings-the-promise-of-visual-table","title":"Beyond Embeddings: The Promise of Visual Table in Visual Reasoning","date":"2024-03-27","arxiv_id":"2403.18252","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":3,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 2 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/beyond-embeddings-the-promise-of-visual-table#ran","syntology_url":"https://syntology.ai/paper/2403.18252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18252"}},"official":{"repos":["lavi-lab/visual-table"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/llava-prumerge-adaptive-token-reduction-for","slug":"llava-prumerge-adaptive-token-reduction-for","title":"LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models","date":"2024-03-22","arxiv_id":"2403.15388","repositories_listed":1,"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/llava-prumerge-adaptive-token-reduction-for#ran","syntology_url":"https://syntology.ai/paper/2403.15388","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.15388"}},"official":null}},{"url":"/paper/vurf-a-general-purpose-reasoning-and-self","slug":"vurf-a-general-purpose-reasoning-and-self","title":"VURF: A General-purpose Reasoning and Self-refinement Framework for Video Understanding","date":"2024-03-21","arxiv_id":"2403.14743","repositories_listed":1,"syntology":null},{"url":"/paper/hydra-a-hyper-agent-for-dynamic-compositional","slug":"hydra-a-hyper-agent-for-dynamic-compositional","title":"HYDRA: A Hyper Agent for Dynamic Compositional Visual Reasoning","date":"2024-03-19","arxiv_id":"2403.12884","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 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; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hydra-a-hyper-agent-for-dynamic-compositional#ran","syntology_url":"https://syntology.ai/paper/2403.12884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12884"}},"official":{"repos":["ControlNet/HYDRA"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/just-shift-it-test-time-prototype-shifting","slug":"just-shift-it-test-time-prototype-shifting","title":"Just Shift It: Test-Time Prototype Shifting for Zero-Shot Generalization with Vision-Language Models","date":"2024-03-19","arxiv_id":"2403.12952","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"4 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/just-shift-it-test-time-prototype-shifting#ran","syntology_url":"https://syntology.ai/paper/2403.12952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12952"}},"official":{"repos":["elaine-sui/tps"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/how-far-are-we-from-intelligent-visual","slug":"how-far-are-we-from-intelligent-visual","title":"How Far Are We from Intelligent Visual Deductive Reasoning?","date":"2024-03-07","arxiv_id":"2403.04732","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"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","sample_list":"/paper/how-far-are-we-from-intelligent-visual#ran","syntology_url":"https://syntology.ai/paper/2403.04732","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04732"}},"official":{"repos":["apple/ml-rpm-bench"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/what-is-missing-in-multilingual-visual","slug":"what-is-missing-in-multilingual-visual","title":"What Is Missing in Multilingual Visual Reasoning and How to Fix It","date":"2024-03-03","arxiv_id":"2403.01404","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/what-is-missing-in-multilingual-visual#ran","syntology_url":"https://syntology.ai/paper/2403.01404","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01404"}},"official":{"repos":["yueqis/multilingual_visual_reasoning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/peacock-a-family-of-arabic-multimodal-large","slug":"peacock-a-family-of-arabic-multimodal-large","title":"Peacock: A Family of Arabic Multimodal Large Language Models and Benchmarks","date":"2024-03-01","arxiv_id":"2403.01031","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-disentanglement-in-downstream","slug":"revisiting-disentanglement-in-downstream","title":"Revisiting Disentanglement in Downstream Tasks: A Study on Its Necessity for Abstract Visual Reasoning","date":"2024-03-01","arxiv_id":"2403.00352","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":10,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/revisiting-disentanglement-in-downstream#ran","syntology_url":"https://syntology.ai/paper/2403.00352","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00352"}},"official":{"repos":["richard-coder-nai/disentanglement-lib-necessity"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/palo-a-polyglot-large-multimodal-model-for-5b","slug":"palo-a-polyglot-large-multimodal-model-for-5b","title":"PALO: A Polyglot Large Multimodal Model for 5B People","date":"2024-02-22","arxiv_id":"2402.14818","repositories_listed":1,"syntology":null}],"record_sha256":"75347f4a6fa911af2731f7491a4c5d122d760ddd54293480f941bf95df9748ce","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}