{"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/12","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":12,"pages_in_order":22,"rows_per_page":100,"rows":[1101,1200],"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/11","next":"/task/visual-question-answering-1/papers/13","papers":[{"url":null,"slug":"multi-modal-explainable-medical-ai-assistant","title":"Multi-Modal Explainable Medical AI Assistant for Trustworthy Human-AI Collaboration","date":"2025-05-11","arxiv_id":"2505.06898","repositories_listed":0,"syntology":null},{"url":"/paper/omgm-orchestrate-multiple-granularities-and","slug":"omgm-orchestrate-multiple-granularities-and","title":"OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval","date":"2025-05-10","arxiv_id":"2505.07879","repositories_listed":0,"syntology":{"n":5,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 ran (of which 4 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; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/omgm-orchestrate-multiple-granularities-and#ran","syntology_url":"https://syntology.ai/paper/2505.07879","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.07879"}},"official":null}},{"url":null,"slug":"natural-reflection-backdoor-attack-on-vision","title":"Natural Reflection Backdoor Attack on Vision Language Model for Autonomous Driving","date":"2025-05-09","arxiv_id":"2505.06413","repositories_listed":0,"syntology":null},{"url":null,"slug":"site-towards-spatial-intelligence-thorough","title":"SITE: towards Spatial Intelligence Thorough Evaluation","date":"2025-05-08","arxiv_id":"2505.05456","repositories_listed":0,"syntology":null},{"url":null,"slug":"structure-causal-models-and-llms-integration","title":"Structure Causal Models and LLMs Integration in Medical Visual Question Answering","date":"2025-05-05","arxiv_id":"2505.02703","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-oriented-semantic-communication-in-large","title":"Task-Oriented Semantic Communication in Large Multimodal Models-based Vehicle Networks","date":"2025-05-05","arxiv_id":"2505.02413","repositories_listed":0,"syntology":null},{"url":null,"slug":"compositional-image-text-matching-and","title":"Compositional Image-Text Matching and Retrieval by Grounding Entities","date":"2025-05-04","arxiv_id":"2505.02278","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-token-boundaries-integrating-human","title":"Adaptive Token Boundaries: Integrating Human Chunking Mechanisms into Multimodal LLMs","date":"2025-05-03","arxiv_id":"2505.04637","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-augmented-language-models","title":"Knowledge-Augmented Language Models Interpreting Structured Chest X-Ray Findings","date":"2025-05-03","arxiv_id":"2505.01711","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounding-task-assistance-with-multimodal","title":"Grounding Task Assistance with Multimodal Cues from a Single Demonstration","date":"2025-05-02","arxiv_id":"2505.01578","repositories_listed":0,"syntology":null},{"url":null,"slug":"transferable-adversarial-attacks-on-black-box","title":"Transferable Adversarial Attacks on Black-Box Vision-Language Models","date":"2025-05-02","arxiv_id":"2505.01050","repositories_listed":0,"syntology":null},{"url":null,"slug":"calibrating-uncertainty-quantification-of","title":"Calibrating Uncertainty Quantification of Multi-Modal LLMs using Grounding","date":"2025-04-30","arxiv_id":"2505.03788","repositories_listed":0,"syntology":null},{"url":null,"slug":"lmme3dhf-benchmarking-and-evaluating","title":"LMME3DHF: Benchmarking and Evaluating Multimodal 3D Human Face Generation with LMMs","date":"2025-04-29","arxiv_id":"2504.20466","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatialreasoner-towards-explicit-and","title":"SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning","date":"2025-04-28","arxiv_id":"2504.20024","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-calibration-of-prediction-sets-in","title":"Data-Driven Calibration of Prediction Sets in Large Vision-Language Models Based on Inductive Conformal Prediction","date":"2025-04-24","arxiv_id":"2504.17671","repositories_listed":0,"syntology":null},{"url":null,"slug":"travellama-facilitating-multi-modal-large","title":"TraveLLaMA: Facilitating Multi-modal Large Language Models to Understand Urban Scenes and Provide Travel Assistance","date":"2025-04-23","arxiv_id":"2504.16505","repositories_listed":0,"syntology":null},{"url":null,"slug":"neglected-risks-the-disturbing-reality-of","title":"Neglected Risks: The Disturbing Reality of Children's Images in Datasets and the Urgent Call for Accountability","date":"2025-04-20","arxiv_id":"2504.14446","repositories_listed":0,"syntology":null},{"url":null,"slug":"hadamard-product-in-deep-learning","title":"Hadamard product in deep learning: Introduction, Advances and Challenges","date":"2025-04-17","arxiv_id":"2504.13112","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-the-semantic-gaps-improving-medical","title":"Bridging the Semantic Gaps: Improving Medical VQA Consistency with LLM-Augmented Question Sets","date":"2025-04-16","arxiv_id":"2504.11777","repositories_listed":0,"syntology":null},{"url":null,"slug":"instruction-augmented-multimodal-alignment","title":"Instruction-augmented Multimodal Alignment for Image-Text and Element Matching","date":"2025-04-16","arxiv_id":"2504.12018","repositories_listed":0,"syntology":null},{"url":null,"slug":"lvlm-csp-accelerating-large-vision-language","title":"LVLM_CSP: Accelerating Large Vision Language Models via Clustering, Scattering, and Pruning for Reasoning Segmentation","date":"2025-04-15","arxiv_id":"2504.10854","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-trustworthy-multimodal-ai-a-review","title":"Building Trustworthy Multimodal AI: A Review of Fairness, Transparency, and Ethics in Vision-Language Tasks","date":"2025-04-14","arxiv_id":"2504.13199","repositories_listed":0,"syntology":null},{"url":null,"slug":"mmkb-rag-a-multi-modal-knowledge-based","title":"MMKB-RAG: A Multi-Modal Knowledge-Based Retrieval-Augmented Generation Framework","date":"2025-04-14","arxiv_id":"2504.10074","repositories_listed":0,"syntology":null},{"url":null,"slug":"vdocrag-retrieval-augmented-generation-over","title":"VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents","date":"2025-04-14","arxiv_id":"2504.09795","repositories_listed":0,"syntology":null},{"url":null,"slug":"notes-bank-benchmarking-neural-transcription","title":"NoTeS-Bank: Benchmarking Neural Transcription and Search for Scientific Notes Understanding","date":"2025-04-12","arxiv_id":"2504.09249","repositories_listed":0,"syntology":null},{"url":null,"slug":"astrollava-towards-the-unification-of","title":"AstroLLaVA: towards the unification of astronomical data and natural language","date":"2025-04-11","arxiv_id":"2504.08583","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-the-frame-generating-360deg-panoramic","title":"Beyond the Frame: Generating 360° Panoramic Videos from Perspective Videos","date":"2025-04-10","arxiv_id":"2504.07940","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-metabolism-an-efficient-data-design","title":"Data Metabolism: An Efficient Data Design Schema For Vision Language Model","date":"2025-04-10","arxiv_id":"2504.12316","repositories_listed":0,"syntology":null},{"url":null,"slug":"tokenfocus-vqa-enhancing-text-to-image","title":"TokenFocus-VQA: Enhancing Text-to-Image Alignment with Position-Aware Focus and Multi-Perspective Aggregations on LVLMs","date":"2025-04-10","arxiv_id":"2504.07556","repositories_listed":0,"syntology":null},{"url":null,"slug":"rs-rag-bridging-remote-sensing-imagery-and","title":"RS-RAG: Bridging Remote Sensing Imagery and Comprehensive Knowledge with a Multi-Modal Dataset and Retrieval-Augmented Generation Model","date":"2025-04-07","arxiv_id":"2504.04988","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-modeling-for-medical-visual","title":"Hierarchical Modeling for Medical Visual Question Answering with Cross-Attention Fusion","date":"2025-04-04","arxiv_id":"2504.03135","repositories_listed":0,"syntology":null},{"url":null,"slug":"qirl-boosting-visual-question-answering-via","title":"QIRL: Boosting Visual Question Answering via Optimized Question-Image Relation Learning","date":"2025-04-04","arxiv_id":"2504.03337","repositories_listed":0,"syntology":null},{"url":null,"slug":"socialgesture-delving-into-multi-person","title":"SocialGesture: Delving into Multi-person Gesture Understanding","date":"2025-04-03","arxiv_id":"2504.02244","repositories_listed":0,"syntology":null},{"url":null,"slug":"mpdrive-improving-spatial-understanding-with","title":"MPDrive: Improving Spatial Understanding with Marker-Based Prompt Learning for Autonomous Driving","date":"2025-04-01","arxiv_id":"2504.00379","repositories_listed":0,"syntology":null},{"url":null,"slug":"sviqa-a-unified-speech-vision-multimodal","title":"SViQA: A Unified Speech-Vision Multimodal Model for Textless Visual Question Answering","date":"2025-04-01","arxiv_id":"2504.01049","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-well-can-vison-language-models-understand","title":"How Well Can Vison-Language Models Understand Humans' Intention? An Open-ended Theory of Mind Question Evaluation Benchmark","date":"2025-03-28","arxiv_id":"2503.22093","repositories_listed":0,"syntology":null},{"url":null,"slug":"ctrl-o-language-controllable-object-centric","title":"CTRL-O: Language-Controllable Object-Centric Visual Representation Learning","date":"2025-03-27","arxiv_id":"2503.21747","repositories_listed":0,"syntology":null},{"url":null,"slug":"jeem-vision-language-understanding-in-four","title":"JEEM: Vision-Language Understanding in Four Arabic Dialects","date":"2025-03-27","arxiv_id":"2503.21910","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature4x-bridging-any-monocular-video-to-4d","title":"Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields","date":"2025-03-26","arxiv_id":"2503.20776","repositories_listed":0,"syntology":null},{"url":null,"slug":"instruction-oriented-preference-alignment-for","title":"Instruction-Oriented Preference Alignment for Enhancing Multi-Modal Comprehension Capability of MLLMs","date":"2025-03-26","arxiv_id":"2503.20309","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-low-level-visual-hallucinations","title":"Mitigating Low-Level Visual Hallucinations Requires Self-Awareness: Database, Model and Training Strategy","date":"2025-03-26","arxiv_id":"2503.20673","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-amplified-semantic-entropy-for","title":"Vision-Amplified Semantic Entropy for Hallucination Detection in Medical Visual Question Answering","date":"2025-03-26","arxiv_id":"2503.20504","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-alignment-of-modalities-in-large","title":"Improved Alignment of Modalities in Large Vision Language Models","date":"2025-03-25","arxiv_id":"2503.19508","repositories_listed":0,"syntology":null},{"url":null,"slug":"lego-puzzles-how-good-are-mllms-at-multi-step","title":"LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?","date":"2025-03-25","arxiv_id":"2503.19990","repositories_listed":0,"syntology":null},{"url":"/paper/orion-a-holistic-end-to-end-autonomous","slug":"orion-a-holistic-end-to-end-autonomous","title":"ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation","date":"2025-03-25","arxiv_id":"2503.19755","repositories_listed":0,"syntology":null},{"url":null,"slug":"din-diffusion-model-for-robust-medical-vqa","title":"DiN: Diffusion Model for Robust Medical VQA with Semantic Noisy Labels","date":"2025-03-24","arxiv_id":"2503.18536","repositories_listed":0,"syntology":null},{"url":null,"slug":"magic-vqa-multimodal-and-grounded-inference","title":"MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering","date":"2025-03-24","arxiv_id":"2503.18491","repositories_listed":0,"syntology":null},{"url":null,"slug":"where-is-this-coming-from-making-groundedness","title":"Where is this coming from? Making groundedness count in the evaluation of Document VQA models","date":"2025-03-24","arxiv_id":"2503.19120","repositories_listed":0,"syntology":null},{"url":null,"slug":"expanding-the-boundaries-of-vision-prior","title":"Expanding the Boundaries of Vision Prior Knowledge in Multi-modal Large Language Models","date":"2025-03-23","arxiv_id":"2503.18034","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-vision-centric-remote-sensing-benchmark","title":"A Vision Centric Remote Sensing Benchmark","date":"2025-03-20","arxiv_id":"2503.15816","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficientllava-generalizable-auto-pruning-for","title":"EfficientLLaVA:Generalizable Auto-Pruning for Large Vision-language Models","date":"2025-03-19","arxiv_id":"2503.15369","repositories_listed":0,"syntology":null},{"url":null,"slug":"graspcorrect-robotic-grasp-correction-via","title":"GraspCorrect: Robotic Grasp Correction via Vision-Language Model-Guided Feedback","date":"2025-03-19","arxiv_id":"2503.15035","repositories_listed":0,"syntology":null},{"url":null,"slug":"truthlens-a-training-free-paradigm-for","title":"TruthLens:A Training-Free Paradigm for DeepFake Detection","date":"2025-03-19","arxiv_id":"2503.15342","repositories_listed":0,"syntology":null},{"url":null,"slug":"upme-an-unsupervised-peer-review-framework","title":"UPME: An Unsupervised Peer Review Framework for Multimodal Large Language Model Evaluation","date":"2025-03-19","arxiv_id":"2503.14941","repositories_listed":0,"syntology":null},{"url":"/paper/marten-visual-question-answering-with-mask","slug":"marten-visual-question-answering-with-mask","title":"Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding","date":"2025-03-18","arxiv_id":"2503.14140","repositories_listed":0,"syntology":{"n":3,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/marten-visual-question-answering-with-mask#ran","syntology_url":"https://syntology.ai/paper/2503.14140","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.14140"}},"official":null}},{"url":null,"slug":"from-head-to-tail-towards-balanced","title":"From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibration","date":"2025-03-17","arxiv_id":"2503.12821","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-oriented-feature-compression-for","title":"Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference","date":"2025-03-17","arxiv_id":"2503.12926","repositories_listed":0,"syntology":null},{"url":null,"slug":"georsmllm-a-multimodal-large-language-model","title":"GeoRSMLLM: A Multimodal Large Language Model for Vision-Language Tasks in Geoscience and Remote Sensing","date":"2025-03-16","arxiv_id":"2503.12490","repositories_listed":0,"syntology":null},{"url":null,"slug":"pebench-a-fictitious-dataset-to-benchmark","title":"PEBench: A Fictitious Dataset to Benchmark Machine Unlearning for Multimodal Large Language Models","date":"2025-03-16","arxiv_id":"2503.12545","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynrsl-vlm-enhancing-autonomous-driving","title":"DynRsl-VLM: Enhancing Autonomous Driving Perception with Dynamic Resolution Vision-Language Models","date":"2025-03-14","arxiv_id":"2503.11265","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-limitations-of-vision-language-models","title":"On the Limitations of Vision-Language Models in Understanding Image Transforms","date":"2025-03-12","arxiv_id":"2503.09837","repositories_listed":0,"syntology":null},{"url":null,"slug":"surgicalvlm-agent-towards-an-interactive-ai","title":"SurgicalVLM-Agent: Towards an Interactive AI Co-Pilot for Pituitary Surgery","date":"2025-03-12","arxiv_id":"2503.09474","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeing-and-reasoning-with-confidence","title":"Seeing and Reasoning with Confidence: Supercharging Multimodal LLMs with an Uncertainty-Aware Agentic Framework","date":"2025-03-11","arxiv_id":"2503.08308","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-text-to-visuals-using-llms-to-generate","title":"From Text to Visuals: Using LLMs to Generate Math Diagrams with Vector Graphics","date":"2025-03-10","arxiv_id":"2503.07429","repositories_listed":0,"syntology":null},{"url":null,"slug":"robusto-1-dataset-comparing-humans-and-vlms","title":"Robusto-1 Dataset: Comparing Humans and VLMs on real out-of-distribution Autonomous Driving VQA from Peru","date":"2025-03-10","arxiv_id":"2503.07587","repositories_listed":0,"syntology":null},{"url":null,"slug":"ti-jepa-an-innovative-energy-based-joint","title":"TI-JEPA: An Innovative Energy-based Joint Embedding Strategy for Text-Image Multimodal Systems","date":"2025-03-09","arxiv_id":"2503.06380","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-frequency-domain-representations","title":"Integrating Frequency-Domain Representations with Low-Rank Adaptation in Vision-Language Models","date":"2025-03-08","arxiv_id":"2503.06003","repositories_listed":0,"syntology":null},{"url":null,"slug":"moemoe-question-guided-dense-and-scalable","title":"MoEMoE: Question Guided Dense and Scalable Sparse Mixture-of-Expert for Multi-source Multi-modal Answering","date":"2025-03-08","arxiv_id":"2503.06296","repositories_listed":0,"syntology":null},{"url":null,"slug":"splattalk-3d-vqa-with-gaussian-splatting","title":"SplatTalk: 3D VQA with Gaussian Splatting","date":"2025-03-08","arxiv_id":"2503.06271","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-sam-with-efficient-prompting-and","title":"Enhancing SAM with Efficient Prompting and Preference Optimization for Semi-supervised Medical Image Segmentation","date":"2025-03-06","arxiv_id":"2503.04639","repositories_listed":0,"syntology":null},{"url":null,"slug":"owlviz-an-open-world-benchmark-for-visual","title":"OWLViz: An Open-World Benchmark for Visual Question Answering","date":"2025-03-04","arxiv_id":"2503.07631","repositories_listed":0,"syntology":null},{"url":null,"slug":"funbench-benchmarking-fundus-reading-skills","title":"FunBench: Benchmarking Fundus Reading Skills of MLLMs","date":"2025-03-02","arxiv_id":"2503.00901","repositories_listed":0,"syntology":null},{"url":null,"slug":"cl-moe-enhancing-multimodal-large-language","title":"CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering","date":"2025-03-01","arxiv_id":"2503.00413","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-retrieval-augmented-generation","title":"Fine-Grained Retrieval-Augmented Generation for Visual Question Answering","date":"2025-02-28","arxiv_id":"2502.20964","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-large-language-models-unveil-the","title":"Can Large Language Models Unveil the Mysteries? An Exploration of Their Ability to Unlock Information in Complex Scenarios","date":"2025-02-27","arxiv_id":"2502.19973","repositories_listed":0,"syntology":null},{"url":null,"slug":"medvlm-r1-incentivizing-medical-reasoning","title":"MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning","date":"2025-02-26","arxiv_id":"2502.19634","repositories_listed":0,"syntology":null},{"url":null,"slug":"talking-to-the-brain-using-large-language","title":"Talking to the brain: Using Large Language Models as Proxies to Model Brain Semantic Representation","date":"2025-02-26","arxiv_id":"2502.18725","repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-knowledge-boundary-of-vision-large","title":"Detecting Knowledge Boundary of Vision Large Language Models by Sampling-Based Inference","date":"2025-02-25","arxiv_id":"2502.18023","repositories_listed":0,"syntology":null},{"url":null,"slug":"filterrag-zero-shot-informed-retrieval","title":"FilterRAG: Zero-Shot Informed Retrieval-Augmented Generation to Mitigate Hallucinations in VQA","date":"2025-02-25","arxiv_id":"2502.18536","repositories_listed":0,"syntology":null},{"url":null,"slug":"all-in-one-understanding-and-generation-in","title":"All-in-one: Understanding and Generation in Multimodal Reasoning with the MAIA Benchmark","date":"2025-02-24","arxiv_id":"2502.16989","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-augmented-visual-question-answering-1","title":"Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines","date":"2025-02-23","arxiv_id":"2502.16641","repositories_listed":0,"syntology":null},{"url":null,"slug":"tracking-the-copyright-of-large-vision","title":"Tracking the Copyright of Large Vision-Language Models through Parameter Learning Adversarial Images","date":"2025-02-23","arxiv_id":"2502.16593","repositories_listed":0,"syntology":null},{"url":null,"slug":"directional-gradient-projection-for-robust","title":"Directional Gradient Projection for Robust Fine-Tuning of Foundation Models","date":"2025-02-21","arxiv_id":"2502.15895","repositories_listed":0,"syntology":null},{"url":null,"slug":"transmamba-fast-universal-architecture","title":"TransMamba: Fast Universal Architecture Adaption from Transformers to Mamba","date":"2025-02-21","arxiv_id":"2502.15130","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-advanced-techniques-for-visual","title":"Exploring Advanced Techniques for Visual Question Answering: A Comprehensive Comparison","date":"2025-02-20","arxiv_id":"2502.14827","repositories_listed":0,"syntology":null},{"url":null,"slug":"sce2drivex-a-generalized-mllm-framework-for","title":"Sce2DriveX: A Generalized MLLM Framework for Scene-to-Drive Learning","date":"2025-02-19","arxiv_id":"2502.14917","repositories_listed":0,"syntology":null},{"url":null,"slug":"simplevqa-multimodal-factuality-evaluation","title":"SimpleVQA: Multimodal Factuality Evaluation for Multimodal Large Language Models","date":"2025-02-18","arxiv_id":"2502.13059","repositories_listed":0,"syntology":null},{"url":null,"slug":"see-the-world-discover-knowledge-a-chinese","title":"\"See the World, Discover Knowledge\": A Chinese Factuality Evaluation for Large Vision Language Models","date":"2025-02-17","arxiv_id":"2502.11718","repositories_listed":0,"syntology":null},{"url":null,"slug":"abduction-of-domain-relationships-from-data","title":"Abduction of Domain Relationships from Data for VQA","date":"2025-02-13","arxiv_id":"2502.09219","repositories_listed":0,"syntology":null},{"url":null,"slug":"emoassist-emotional-assistant-for-visual","title":"EmoAssist: Emotional Assistant for Visual Impairment Community","date":"2025-02-13","arxiv_id":"2502.09285","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-graph-question-answering-with-asp-and","title":"Visual Graph Question Answering with ASP and LLMs for Language Parsing","date":"2025-02-13","arxiv_id":"2502.09211","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-language-models-for-edge-networks-a","title":"Vision-Language Models for Edge Networks: A Comprehensive Survey","date":"2025-02-11","arxiv_id":"2502.07855","repositories_listed":0,"syntology":null},{"url":null,"slug":"performance-analysis-of-traditional-vqa","title":"Performance Analysis of Traditional VQA Models Under Limited Computational Resources","date":"2025-02-09","arxiv_id":"2502.05738","repositories_listed":0,"syntology":null},{"url":null,"slug":"hummingbird-high-fidelity-image-generation","title":"Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment","date":"2025-02-07","arxiv_id":"2502.05153","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-few-shot-continual-learning-in","title":"Efficient Few-Shot Continual Learning in Vision-Language Models","date":"2025-02-06","arxiv_id":"2502.04098","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-spatial-language-grounding-through","title":"Exploring Spatial Language Grounding Through Referring Expressions","date":"2025-02-04","arxiv_id":"2502.04359","repositories_listed":0,"syntology":null},{"url":null,"slug":"hypo3d-exploring-hypothetical-reasoning-in-3d","title":"Hypo3D: Exploring Hypothetical Reasoning in 3D","date":"2025-02-02","arxiv_id":"2502.00954","repositories_listed":0,"syntology":null},{"url":null,"slug":"vlm-assisted-continual-learning-for-visual","title":"VLM-Assisted Continual learning for Visual Question Answering in Self-Driving","date":"2025-02-02","arxiv_id":"2502.00843","repositories_listed":0,"syntology":null},{"url":null,"slug":"anatomy-might-be-all-you-need-forecasting","title":"Anatomy Might Be All You Need: Forecasting What to Do During Surgery","date":"2025-01-29","arxiv_id":"2501.18011","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-large-vision-language-models-for","title":"Scaling Large Vision-Language Models for Enhanced Multimodal Comprehension In Biomedical Image Analysis","date":"2025-01-26","arxiv_id":"2501.15370","repositories_listed":0,"syntology":null}],"record_sha256":"4fc303a774f2960bef74c7391f9b2e51b3979f6708c7e9a7a0ef1198fdbe16c0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}