{"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-question-answering-1/papers/3","list_of":"/task/visual-question-answering-1","task":"Visual Question Answering","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":3,"pages_in_order":22,"rows_per_page":100,"rows":[201,300],"of":2177,"counts":{"archive_papers_tagged":2177,"with_a_code_link":1042,"where_syntology_ran_a_sample":378,"not_listed_spam_title":0,"listed":2177,"listed_where_code_ran":378,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":308,"every_run_a_failure_of_syntologys_instrument":70,"listed_with_a_run_with_no_instrument_failure":308,"listed_every_run_a_failure_of_syntologys_instrument":70,"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-question-answering-1","prev":"/task/visual-question-answering-1/papers/2","next":"/task/visual-question-answering-1/papers/4","papers":[{"url":"/paper/slotpi-physics-informed-object-centric","slug":"slotpi-physics-informed-object-centric","title":"SlotPi: Physics-informed Object-centric Reasoning Models","date":"2025-06-12","arxiv_id":"2506.10778","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"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; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/slotpi-physics-informed-object-centric#ran","syntology_url":"https://syntology.ai/paper/2506.10778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.10778"}},"official":{"repos":["intell-sci-comput/slotpi"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/outside-knowledge-conversational-video-okcv","slug":"outside-knowledge-conversational-video-okcv","title":"Outside Knowledge Conversational Video (OKCV) Dataset -- Dialoguing over Videos","date":"2025-06-11","arxiv_id":"2506.09953","repositories_listed":1,"syntology":null},{"url":"/paper/flagevalmm-a-flexible-framework-for","slug":"flagevalmm-a-flexible-framework-for","title":"FlagEvalMM: A Flexible Framework for Comprehensive Multimodal Model Evaluation","date":"2025-06-10","arxiv_id":"2506.09081","repositories_listed":1,"syntology":null},{"url":"/paper/haibu-remud-reasoning-multimodal-ultrasound","slug":"haibu-remud-reasoning-multimodal-ultrasound","title":"HAIBU-ReMUD: Reasoning Multimodal Ultrasound Dataset and Model Bridging to General Specific Domains","date":"2025-06-09","arxiv_id":"2506.07837","repositories_listed":1,"syntology":null},{"url":"/paper/multi-step-visual-reasoning-with-visual","slug":"multi-step-visual-reasoning-with-visual","title":"Multi-Step Visual Reasoning with Visual Tokens Scaling and Verification","date":"2025-06-08","arxiv_id":"2506.07235","repositories_listed":1,"syntology":null},{"url":"/paper/videocad-a-large-scale-video-dataset-for","slug":"videocad-a-large-scale-video-dataset-for","title":"VideoCAD: A Large-Scale Video Dataset for Learning UI Interactions and 3D Reasoning from CAD Software","date":"2025-05-30","arxiv_id":"2505.24838","repositories_listed":1,"syntology":null},{"url":"/paper/interpreting-chest-x-rays-like-a-radiologist","slug":"interpreting-chest-x-rays-like-a-radiologist","title":"Interpreting Chest X-rays Like a Radiologist: A Benchmark with Clinical Reasoning","date":"2025-05-29","arxiv_id":"2505.23143","repositories_listed":1,"syntology":null},{"url":"/paper/multi-sourced-compositional-generalization-in","slug":"multi-sourced-compositional-generalization-in","title":"Multi-Sourced Compositional Generalization in Visual Question Answering","date":"2025-05-29","arxiv_id":"2505.23045","repositories_listed":1,"syntology":null},{"url":"/paper/qlip-a-dynamic-quadtree-vision-prior-enhances","slug":"qlip-a-dynamic-quadtree-vision-prior-enhances","title":"QLIP: A Dynamic Quadtree Vision Prior Enhances MLLM Performance Without Retraining","date":"2025-05-29","arxiv_id":"2505.23004","repositories_listed":1,"syntology":null},{"url":"/paper/synthetic-document-question-answering-in","slug":"synthetic-document-question-answering-in","title":"Synthetic Document Question Answering in Hungarian","date":"2025-05-29","arxiv_id":"2505.23008","repositories_listed":1,"syntology":null},{"url":"/paper/frames-vqa-benchmarking-fine-tuning-1","slug":"frames-vqa-benchmarking-fine-tuning-1","title":"FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering","date":"2025-05-27","arxiv_id":"2505.21755","repositories_listed":1,"syntology":null},{"url":"/paper/mangavqa-and-mangalmm-a-benchmark-and","slug":"mangavqa-and-mangalmm-a-benchmark-and","title":"MangaVQA and MangaLMM: A Benchmark and Specialized Model for Multimodal Manga Understanding","date":"2025-05-26","arxiv_id":"2505.20298","repositories_listed":1,"syntology":null},{"url":"/paper/mineanybuild-benchmarking-spatial-planning","slug":"mineanybuild-benchmarking-spatial-planning","title":"MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agents","date":"2025-05-26","arxiv_id":"2505.20148","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/mineanybuild-benchmarking-spatial-planning#ran","syntology_url":"https://syntology.ai/paper/2505.20148","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.20148"}},"official":{"repos":["mineanybuild/mineanybuild"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/mm-prompt-cross-modal-prompt-tuning-for","slug":"mm-prompt-cross-modal-prompt-tuning-for","title":"MM-Prompt: Cross-Modal Prompt Tuning for Continual Visual Question Answering","date":"2025-05-26","arxiv_id":"2505.19455","repositories_listed":1,"syntology":null},{"url":"/paper/visualized-text-to-image-retrieval","slug":"visualized-text-to-image-retrieval","title":"Visualized Text-to-Image Retrieval","date":"2025-05-26","arxiv_id":"2505.20291","repositories_listed":1,"syntology":null},{"url":"/paper/are-vision-language-models-ready-for-clinical","slug":"are-vision-language-models-ready-for-clinical","title":"Are Vision Language Models Ready for Clinical Diagnosis? A 3D Medical Benchmark for Tumor-centric Visual Question Answering","date":"2025-05-25","arxiv_id":"2505.18915","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/are-vision-language-models-ready-for-clinical#ran","syntology_url":"https://syntology.ai/paper/2505.18915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.18915"}},"official":{"repos":["schuture/deeptumorvqa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/satori-r1-incentivizing-multimodal-reasoning","slug":"satori-r1-incentivizing-multimodal-reasoning","title":"SATORI-R1: Incentivizing Multimodal Reasoning with Spatial Grounding and Verifiable Rewards","date":"2025-05-25","arxiv_id":"2505.19094","repositories_listed":1,"syntology":null},{"url":"/paper/vtool-r1-vlms-learn-to-think-with-images-via","slug":"vtool-r1-vlms-learn-to-think-with-images-via","title":"VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool Use","date":"2025-05-25","arxiv_id":"2505.19255","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/vtool-r1-vlms-learn-to-think-with-images-via#ran","syntology_url":"https://syntology.ai/paper/2505.19255","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19255"}},"official":null}},{"url":"/paper/cxreasonbench-a-benchmark-for-evaluating","slug":"cxreasonbench-a-benchmark-for-evaluating","title":"CXReasonBench: A Benchmark for Evaluating Structured Diagnostic Reasoning in Chest X-rays","date":"2025-05-23","arxiv_id":"2505.18087","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/cxreasonbench-a-benchmark-for-evaluating#ran","syntology_url":"https://syntology.ai/paper/2505.18087","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.18087"}},"official":{"repos":["ttumyche/cxreasonbench"],"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/scaling-up-biomedical-vision-language-models","slug":"scaling-up-biomedical-vision-language-models","title":"Scaling Up Biomedical Vision-Language Models: Fine-Tuning, Instruction Tuning, and Multi-Modal Learning","date":"2025-05-23","arxiv_id":"2505.17436","repositories_listed":1,"syntology":null},{"url":"/paper/veattack-downstream-agnostic-vision-encoder","slug":"veattack-downstream-agnostic-vision-encoder","title":"VEAttack: Downstream-agnostic Vision Encoder Attack against Large Vision Language Models","date":"2025-05-23","arxiv_id":"2505.17440","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-retrieval-augmented-multimomal","slug":"benchmarking-retrieval-augmented-multimomal","title":"Benchmarking Retrieval-Augmented Multimomal Generation for Document Question Answering","date":"2025-05-22","arxiv_id":"2505.16470","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/benchmarking-retrieval-augmented-multimomal#ran","syntology_url":"https://syntology.ai/paper/2505.16470","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.16470"}},"official":{"repos":["mmdocrag/mmdocrag"],"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/mitigating-hallucinations-in-vision-language","slug":"mitigating-hallucinations-in-vision-language","title":"Mitigating Hallucinations in Vision-Language Models through Image-Guided Head Suppression","date":"2025-05-22","arxiv_id":"2505.16411","repositories_listed":1,"syntology":null},{"url":"/paper/snap-a-benchmark-for-testing-the-effects-of","slug":"snap-a-benchmark-for-testing-the-effects-of","title":"SNAP: A Benchmark for Testing the Effects of Capture Conditions on Fundamental Vision Tasks","date":"2025-05-21","arxiv_id":"2505.15628","repositories_listed":1,"syntology":null},{"url":"/paper/timecausality-evaluating-the-causal-ability","slug":"timecausality-evaluating-the-causal-ability","title":"TimeCausality: Evaluating the Causal Ability in Time Dimension for Vision Language Models","date":"2025-05-21","arxiv_id":"2505.15435","repositories_listed":1,"syntology":null},{"url":"/paper/traveling-across-languages-benchmarking-cross","slug":"traveling-across-languages-benchmarking-cross","title":"Traveling Across Languages: Benchmarking Cross-Lingual Consistency in Multimodal LLMs","date":"2025-05-21","arxiv_id":"2505.15075","repositories_listed":1,"syntology":null},{"url":"/paper/ravenea-a-benchmark-for-multimodal-retrieval","slug":"ravenea-a-benchmark-for-multimodal-retrieval","title":"RAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture Understanding","date":"2025-05-20","arxiv_id":"2505.14462","repositories_listed":1,"syntology":null},{"url":"/paper/reasoning-ocr-can-large-multimodal-models","slug":"reasoning-ocr-can-large-multimodal-models","title":"Reasoning-OCR: Can Large Multimodal Models Solve Complex Logical Reasoning Problems from OCR Cues?","date":"2025-05-19","arxiv_id":"2505.12766","repositories_listed":1,"syntology":null},{"url":"/paper/medagentboard-benchmarking-multi-agent","slug":"medagentboard-benchmarking-multi-agent","title":"MedAgentBoard: Benchmarking Multi-Agent Collaboration with Conventional Methods for Diverse Medical Tasks","date":"2025-05-18","arxiv_id":"2505.12371","repositories_listed":1,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/medagentboard-benchmarking-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2505.12371","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.12371"}},"official":{"repos":["yhzhu99/medagentboard"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/2505-11404","slug":"2505-11404","title":"Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert Reasoner","date":"2025-05-16","arxiv_id":"2505.11404","repositories_listed":1,"syntology":null},{"url":"/paper/2505-11454","slug":"2505-11454","title":"HumaniBench: A Human-Centric Framework for Large Multimodal Models Evaluation","date":"2025-05-16","arxiv_id":"2505.11454","repositories_listed":1,"syntology":null},{"url":"/paper/tcc-bench-benchmarking-the-traditional","slug":"tcc-bench-benchmarking-the-traditional","title":"TCC-Bench: Benchmarking the Traditional Chinese Culture Understanding Capabilities of MLLMs","date":"2025-05-16","arxiv_id":"2505.11275","repositories_listed":1,"syntology":null},{"url":"/paper/probabilistic-embeddings-for-frozen-vision","slug":"probabilistic-embeddings-for-frozen-vision","title":"Probabilistic Embeddings for Frozen Vision-Language Models: Uncertainty Quantification with Gaussian Process Latent Variable Models","date":"2025-05-08","arxiv_id":"2505.05163","repositories_listed":1,"syntology":null},{"url":"/paper/sim2real-transfer-for-vision-based-grasp","slug":"sim2real-transfer-for-vision-based-grasp","title":"Sim2Real Transfer for Vision-Based Grasp Verification","date":"2025-05-05","arxiv_id":"2505.03046","repositories_listed":1,"syntology":null},{"url":"/paper/adcare-vlm-leveraging-large-vision-language","slug":"adcare-vlm-leveraging-large-vision-language","title":"AdCare-VLM: Leveraging Large Vision Language Model (LVLM) to Monitor Long-Term Medication Adherence and Care","date":"2025-05-01","arxiv_id":"2505.00275","repositories_listed":1,"syntology":{"n":10,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/adcare-vlm-leveraging-large-vision-language#ran","syntology_url":"https://syntology.ai/paper/2505.00275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.00275"}},"official":{"repos":["asad14053/AdCare-VLM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/unlearning-sensitive-information-in","slug":"unlearning-sensitive-information-in","title":"Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation","date":"2025-05-01","arxiv_id":"2505.01456","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unlearning-sensitive-information-in#ran","syntology_url":"https://syntology.ai/paper/2505.01456","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.01456"}},"official":{"repos":["vaidehi99/unlok-vqa"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/unibiomed-a-universal-foundation-model-for","slug":"unibiomed-a-universal-foundation-model-for","title":"UniBiomed: A Universal Foundation Model for Grounded Biomedical Image Interpretation","date":"2025-04-30","arxiv_id":"2504.21336","repositories_listed":1,"syntology":null},{"url":"/paper/chestx-reasoner-advancing-radiology","slug":"chestx-reasoner-advancing-radiology","title":"ChestX-Reasoner: Advancing Radiology Foundation Models with Reasoning through Step-by-Step Verification","date":"2025-04-29","arxiv_id":"2504.20930","repositories_listed":1,"syntology":null},{"url":"/paper/2504-18589","slug":"2504-18589","title":"Benchmarking Multimodal Mathematical Reasoning with Explicit Visual Dependency","date":"2025-04-24","arxiv_id":"2504.18589","repositories_listed":1,"syntology":null},{"url":"/paper/are-vision-llms-road-ready-a-comprehensive","slug":"are-vision-llms-road-ready-a-comprehensive","title":"Are Vision LLMs Road-Ready? A Comprehensive Benchmark for Safety-Critical Driving Video Understanding","date":"2025-04-20","arxiv_id":"2504.14526","repositories_listed":1,"syntology":null},{"url":"/paper/qava-query-agnostic-visual-attack-to-large","slug":"qava-query-agnostic-visual-attack-to-large","title":"QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models","date":"2025-04-15","arxiv_id":"2504.11038","repositories_listed":1,"syntology":null},{"url":"/paper/reasondrive-efficient-visual-question","slug":"reasondrive-efficient-visual-question","title":"ReasonDrive: Efficient Visual Question Answering for Autonomous Vehicles with Reasoning-Enhanced Small Vision-Language Models","date":"2025-04-14","arxiv_id":"2504.10757","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-efficient-vision-language-models","slug":"a-survey-on-efficient-vision-language-models","title":"A Survey on Efficient Vision-Language Models","date":"2025-04-13","arxiv_id":"2504.09724","repositories_listed":1,"syntology":null},{"url":"/paper/resource-efficient-inference-with-foundation","slug":"resource-efficient-inference-with-foundation","title":"Resource-efficient Inference with Foundation Model Programs","date":"2025-04-09","arxiv_id":"2504.07247","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-compositional-reasoning-in-vision","slug":"enhancing-compositional-reasoning-in-vision","title":"Enhancing Compositional Reasoning in Vision-Language Models with Synthetic Preference Data","date":"2025-04-07","arxiv_id":"2504.04740","repositories_listed":1,"syntology":null},{"url":"/paper/medm-vl-what-makes-a-good-medical-lvlm","slug":"medm-vl-what-makes-a-good-medical-lvlm","title":"MedM-VL: What Makes a Good Medical LVLM?","date":"2025-04-06","arxiv_id":"2504.04323","repositories_listed":1,"syntology":null},{"url":"/paper/sting-bee-towards-vision-language-model-for","slug":"sting-bee-towards-vision-language-model-for","title":"STING-BEE: Towards Vision-Language Model for Real-World X-ray Baggage Security Inspection","date":"2025-04-03","arxiv_id":"2504.02823","repositories_listed":1,"syntology":null},{"url":"/paper/gmai-vl-r1-harnessing-reinforcement-learning","slug":"gmai-vl-r1-harnessing-reinforcement-learning","title":"GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning","date":"2025-04-02","arxiv_id":"2504.01886","repositories_listed":1,"syntology":null},{"url":"/paper/illume-illuminating-unified-mllm-with-dual","slug":"illume-illuminating-unified-mllm-with-dual","title":"ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement","date":"2025-04-02","arxiv_id":"2504.01934","repositories_listed":1,"syntology":{"n":20,"n_ran":19,"n_constructed":0,"n_ran_checked":18,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":17,"n_pointer_only":0,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 1 violated, 17 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/illume-illuminating-unified-mllm-with-dual#ran","syntology_url":"https://syntology.ai/paper/2504.01934","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.01934"}},"official":null}},{"url":"/paper/fortisavqa-and-maven-a-benchmark-dataset-and","slug":"fortisavqa-and-maven-a-benchmark-dataset-and","title":"FortisAVQA and MAVEN: a Benchmark Dataset and Debiasing Framework for Robust Multimodal Reasoning","date":"2025-04-01","arxiv_id":"2504.00487","repositories_listed":1,"syntology":null},{"url":"/paper/koffvqa-an-objectively-evaluated-free-form","slug":"koffvqa-an-objectively-evaluated-free-form","title":"KOFFVQA: An Objectively Evaluated Free-form VQA Benchmark for Large Vision-Language Models in the Korean Language","date":"2025-03-31","arxiv_id":"2503.23730","repositories_listed":1,"syntology":null},{"url":"/paper/opendrivevla-towards-end-to-end-autonomous","slug":"opendrivevla-towards-end-to-end-autonomous","title":"OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model","date":"2025-03-30","arxiv_id":"2503.23463","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"4 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; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/opendrivevla-towards-end-to-end-autonomous#ran","syntology_url":"https://syntology.ai/paper/2503.23463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.23463"}},"official":{"repos":["DriveVLA/OpenDriveVLA"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/facebench-a-multi-view-multi-level-facial","slug":"facebench-a-multi-view-multi-level-facial","title":"FaceBench: A Multi-View Multi-Level Facial Attribute VQA Dataset for Benchmarking Face Perception MLLMs","date":"2025-03-27","arxiv_id":"2503.21457","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"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 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) · 1 unverified","sample_list":"/paper/facebench-a-multi-view-multi-level-facial#ran","syntology_url":"https://syntology.ai/paper/2503.21457","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.21457"}},"official":{"repos":["cvi-szu/facebench"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/fine-grained-evaluation-of-large-vision","slug":"fine-grained-evaluation-of-large-vision","title":"Fine-Grained Evaluation of Large Vision-Language Models in Autonomous Driving","date":"2025-03-27","arxiv_id":"2503.21505","repositories_listed":1,"syntology":null},{"url":"/paper/med3dvlm-an-efficient-vision-language-model","slug":"med3dvlm-an-efficient-vision-language-model","title":"Med3DVLM: An Efficient Vision-Language Model for 3D Medical Image Analysis","date":"2025-03-25","arxiv_id":"2503.20047","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"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) · 5 unverified","sample_list":"/paper/med3dvlm-an-efficient-vision-language-model#ran","syntology_url":"https://syntology.ai/paper/2503.20047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.20047"}},"official":{"repos":["mirthai/med3dvlm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/mind-the-gap-benchmarking-spatial-reasoning","slug":"mind-the-gap-benchmarking-spatial-reasoning","title":"Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models","date":"2025-03-25","arxiv_id":"2503.19707","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/mind-the-gap-benchmarking-spatial-reasoning#ran","syntology_url":"https://syntology.ai/paper/2503.19707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.19707"}},"official":{"repos":["stogiannidis/srbench"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pave-patching-and-adapting-video-large","slug":"pave-patching-and-adapting-video-large","title":"PAVE: Patching and Adapting Video Large Language Models","date":"2025-03-25","arxiv_id":"2503.19794","repositories_listed":1,"syntology":null},{"url":"/paper/vgat-a-cancer-survival-analysis-framework","slug":"vgat-a-cancer-survival-analysis-framework","title":"VGAT: A Cancer Survival Analysis Framework Transitioning from Generative Visual Question Answering to Genomic Reconstruction","date":"2025-03-25","arxiv_id":"2503.19367","repositories_listed":1,"syntology":null},{"url":"/paper/mc-llava-multi-concept-personalized-vision-1","slug":"mc-llava-multi-concept-personalized-vision-1","title":"MC-LLaVA: Multi-Concept Personalized Vision-Language Model","date":"2025-03-24","arxiv_id":"2503.18854","repositories_listed":1,"syntology":null},{"url":"/paper/progressive-prompt-detailing-for-improved","slug":"progressive-prompt-detailing-for-improved","title":"Progressive Prompt Detailing for Improved Alignment in Text-to-Image Generative Models","date":"2025-03-22","arxiv_id":"2503.17794","repositories_listed":1,"syntology":null},{"url":"/paper/does-chain-of-thought-reasoning-help-mobile","slug":"does-chain-of-thought-reasoning-help-mobile","title":"Does Chain-of-Thought Reasoning Help Mobile GUI Agent? An Empirical Study","date":"2025-03-21","arxiv_id":"2503.16788","repositories_listed":1,"syntology":null},{"url":"/paper/umit-unifying-medical-imaging-tasks-via","slug":"umit-unifying-medical-imaging-tasks-via","title":"UMIT: Unifying Medical Imaging Tasks via Vision-Language Models","date":"2025-03-20","arxiv_id":"2503.15892","repositories_listed":1,"syntology":null},{"url":"/paper/where-do-large-vision-language-models-look-at","slug":"where-do-large-vision-language-models-look-at","title":"Where do Large Vision-Language Models Look at when Answering Questions?","date":"2025-03-18","arxiv_id":"2503.13891","repositories_listed":1,"syntology":null},{"url":"/paper/microvqa-a-multimodal-reasoning-benchmark-for","slug":"microvqa-a-multimodal-reasoning-benchmark-for","title":"MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Research","date":"2025-03-17","arxiv_id":"2503.13399","repositories_listed":1,"syntology":null},{"url":"/paper/nuplanqa-a-large-scale-dataset-and-benchmark","slug":"nuplanqa-a-large-scale-dataset-and-benchmark","title":"NuPlanQA: A Large-Scale Dataset and Benchmark for Multi-View Driving Scene Understanding in Multi-Modal Large Language Models","date":"2025-03-17","arxiv_id":"2503.12772","repositories_listed":1,"syntology":null},{"url":"/paper/t2i-fineeval-fine-grained-compositional","slug":"t2i-fineeval-fine-grained-compositional","title":"T2I-FineEval: Fine-Grained Compositional Metric for Text-to-Image Evaluation","date":"2025-03-14","arxiv_id":"2503.11481","repositories_listed":1,"syntology":null},{"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/simlingo-vision-only-closed-loop-autonomous","slug":"simlingo-vision-only-closed-loop-autonomous","title":"SimLingo: Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignment","date":"2025-03-12","arxiv_id":"2503.09594","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":8,"n_ran_checked":8,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"11 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/simlingo-vision-only-closed-loop-autonomous#ran","syntology_url":"https://syntology.ai/paper/2503.09594","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.09594"}},"official":null}},{"url":"/paper/treble-counterfactual-vlms-a-causal-approach","slug":"treble-counterfactual-vlms-a-causal-approach","title":"Treble Counterfactual VLMs: A Causal Approach to Hallucination","date":"2025-03-08","arxiv_id":"2503.06169","repositories_listed":1,"syntology":null},{"url":"/paper/anyanomaly-zero-shot-customizable-video-1","slug":"anyanomaly-zero-shot-customizable-video-1","title":"AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM","date":"2025-03-06","arxiv_id":"2503.04504","repositories_listed":1,"syntology":null},{"url":"/paper/keeping-yourself-is-important-in-downstream","slug":"keeping-yourself-is-important-in-downstream","title":"Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model","date":"2025-03-06","arxiv_id":"2503.04543","repositories_listed":1,"syntology":null},{"url":"/paper/question-aware-gaussian-experts-for-audio","slug":"question-aware-gaussian-experts-for-audio","title":"Question-Aware Gaussian Experts for Audio-Visual Question Answering","date":"2025-03-06","arxiv_id":"2503.04459","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-vietnamese-vqa-through-curriculum","slug":"enhancing-vietnamese-vqa-through-curriculum","title":"Enhancing Vietnamese VQA through Curriculum Learning on Raw and Augmented Text Representations","date":"2025-03-05","arxiv_id":"2503.03285","repositories_listed":1,"syntology":null},{"url":"/paper/biod2c-a-dual-level-semantic-consistency","slug":"biod2c-a-dual-level-semantic-consistency","title":"BioD2C: A Dual-level Semantic Consistency Constraint Framework for Biomedical VQA","date":"2025-03-04","arxiv_id":"2503.02476","repositories_listed":1,"syntology":null},{"url":"/paper/watch-out-your-album-on-the-inadvertent","slug":"watch-out-your-album-on-the-inadvertent","title":"Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models","date":"2025-03-03","arxiv_id":"2503.01208","repositories_listed":1,"syntology":null},{"url":"/paper/medhalltune-an-instruction-tuning-benchmark","slug":"medhalltune-an-instruction-tuning-benchmark","title":"MedHallTune: An Instruction-Tuning Benchmark for Mitigating Medical Hallucination in Vision-Language Models","date":"2025-02-28","arxiv_id":"2502.20780","repositories_listed":1,"syntology":null},{"url":"/paper/mllms-know-where-to-look-training-free","slug":"mllms-know-where-to-look-training-free","title":"MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs","date":"2025-02-24","arxiv_id":"2502.17422","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"0 ran · 4 unverified","sample_list":"/paper/mllms-know-where-to-look-training-free#ran","syntology_url":"https://syntology.ai/paper/2502.17422","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.17422"}},"official":{"repos":["saccharomycetes/mllms_know"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"url":"/paper/chatvla-unified-multimodal-understanding-and","slug":"chatvla-unified-multimodal-understanding-and","title":"ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model","date":"2025-02-20","arxiv_id":"2502.14420","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-rewardbench-holistic-evaluation-of","slug":"multimodal-rewardbench-holistic-evaluation-of","title":"Multimodal RewardBench: Holistic Evaluation of Reward Models for Vision Language Models","date":"2025-02-20","arxiv_id":"2502.14191","repositories_listed":1,"syntology":null},{"url":"/paper/pitvqa-vector-matrix-low-rank-adaptation-for","slug":"pitvqa-vector-matrix-low-rank-adaptation-for","title":"PitVQA++: Vector Matrix-Low-Rank Adaptation for Open-Ended Visual Question Answering in Pituitary Surgery","date":"2025-02-19","arxiv_id":"2502.14149","repositories_listed":1,"syntology":null},{"url":"/paper/re-align-aligning-vision-language-models-via","slug":"re-align-aligning-vision-language-models-via","title":"Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization","date":"2025-02-18","arxiv_id":"2502.13146","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/re-align-aligning-vision-language-models-via#ran","syntology_url":"https://syntology.ai/paper/2502.13146","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.13146"}},"official":{"repos":["taco-group/re-align"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mmxu-a-multi-modal-and-multi-x-ray","slug":"mmxu-a-multi-modal-and-multi-x-ray","title":"MMXU: A Multi-Modal and Multi-X-ray Understanding Dataset for Disease Progression","date":"2025-02-17","arxiv_id":"2502.11651","repositories_listed":1,"syntology":null},{"url":"/paper/clinkd-cross-modal-clinical-knowledge","slug":"clinkd-cross-modal-clinical-knowledge","title":"ClinKD: Cross-Modal Clinical Knowledge Distiller For Multi-Task Medical Images","date":"2025-02-09","arxiv_id":"2502.05928","repositories_listed":1,"syntology":null},{"url":"/paper/docmia-document-level-membership-inference","slug":"docmia-document-level-membership-inference","title":"DocMIA: Document-Level Membership Inference Attacks against DocVQA Models","date":"2025-02-06","arxiv_id":"2502.03692","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"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) · 2 unverified","sample_list":"/paper/docmia-document-level-membership-inference#ran","syntology_url":"https://syntology.ai/paper/2502.03692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.03692"}},"official":{"repos":["khanhnguyen21006/mia_docvqa"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/no-images-no-problem-retaining-knowledge-in","slug":"no-images-no-problem-retaining-knowledge-in","title":"No Images, No Problem: Retaining Knowledge in Continual VQA with Questions-Only Memory","date":"2025-02-06","arxiv_id":"2502.04469","repositories_listed":1,"syntology":null},{"url":"/paper/pixfoundation-are-we-heading-in-the-right","slug":"pixfoundation-are-we-heading-in-the-right","title":"PixFoundation: Are We Heading in the Right Direction with Pixel-level Vision Foundation Models?","date":"2025-02-06","arxiv_id":"2502.04192","repositories_listed":1,"syntology":null},{"url":"/paper/robust-llava-on-the-effectiveness-of-large","slug":"robust-llava-on-the-effectiveness-of-large","title":"Robust-LLaVA: On the Effectiveness of Large-Scale Robust Image Encoders for Multi-modal Large Language Models","date":"2025-02-03","arxiv_id":"2502.01576","repositories_listed":1,"syntology":null},{"url":"/paper/janus-pro-unified-multimodal-understanding","slug":"janus-pro-unified-multimodal-understanding","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","date":"2025-01-29","arxiv_id":"2501.17811","repositories_listed":1,"syntology":null},{"url":"/paper/large-models-in-dialogue-for-active","slug":"large-models-in-dialogue-for-active","title":"Large Models in Dialogue for Active Perception and Anomaly Detection","date":"2025-01-27","arxiv_id":"2501.16300","repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-and-boosting-the-power-of-fine","slug":"analyzing-and-boosting-the-power-of-fine","title":"Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models","date":"2025-01-25","arxiv_id":"2501.15140","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"4 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; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/analyzing-and-boosting-the-power-of-fine#ran","syntology_url":"https://syntology.ai/paper/2501.15140","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.15140"}},"official":{"repos":["pku-icst-mipl/finedefics_iclr2025"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/patent-figure-classification-using-large","slug":"patent-figure-classification-using-large","title":"Patent Figure Classification using Large Vision-language Models","date":"2025-01-22","arxiv_id":"2501.12751","repositories_listed":1,"syntology":null},{"url":"/paper/a-simple-aerial-detection-baseline-of","slug":"a-simple-aerial-detection-baseline-of","title":"A Simple Aerial Detection Baseline of Multimodal Language Models","date":"2025-01-16","arxiv_id":"2501.09720","repositories_listed":1,"syntology":null},{"url":"/paper/parameter-inverted-image-pyramid-networks-for","slug":"parameter-inverted-image-pyramid-networks-for","title":"Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding","date":"2025-01-14","arxiv_id":"2501.07783","repositories_listed":1,"syntology":null},{"url":"/paper/automated-generation-of-challenging-multiple","slug":"automated-generation-of-challenging-multiple","title":"Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation","date":"2025-01-06","arxiv_id":"2501.03225","repositories_listed":1,"syntology":null},{"url":"/paper/redit-re-evaluating-large-visual-question","slug":"redit-re-evaluating-large-visual-question","title":"ReDiT: Re‑evaluating large visual question answering model confidence by defining input scenario Difficulty and applying Temperature mapping","date":"2025-01-06","arxiv_id":null,"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/avqacl-a-novel-benchmark-for-audio-visual","slug":"avqacl-a-novel-benchmark-for-audio-visual","title":"AVQACL: A Novel Benchmark for Audio-Visual Question Answering Continual Learning","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/notes-guided-mllm-reasoning-enhancing-mllm","slug":"notes-guided-mllm-reasoning-enhancing-mllm","title":"Notes-guided MLLM Reasoning: Enhancing MLLM with Knowledge and Visual Notes for Visual Question Answering","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dual-diffusion-for-unified-image-generation","slug":"dual-diffusion-for-unified-image-generation","title":"Dual Diffusion for Unified Image Generation and Understanding","date":"2024-12-31","arxiv_id":"2501.00289","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dual-diffusion-for-unified-image-generation#ran","syntology_url":"https://syntology.ai/paper/2501.00289","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.00289"}},"official":null}}],"record_sha256":"bac487f5e0a1198523aa30c02d2679b77d71c51b1b774b083e4142db7f31f8c4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}