{"total":54,"rows":[{"id":"2411.10332","title":"Number it: Temporal Grounding Videos like Flipping Manga","created":"2024-11-15","cited_by_count":65,"area":null},{"id":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"id":"2504.17207","title":"Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulation","created":"2025-04-24","cited_by_count":42,"area":"lr"},{"id":"2505.18657","title":"MLLMs are Deeply Affected by Modality Bias","created":"2025-05-24","cited_by_count":40,"area":"mllm"},{"id":"2508.10922","title":"A Survey on Video Temporal Grounding with Multimodal Large Language Model","created":"2025-08-07","cited_by_count":20,"area":"mllm"},{"id":"2511.01571","title":"PixelVLA: Advancing Pixel-level Understanding in Vision-Language-Action Model","created":"2025-11-03","cited_by_count":18,"area":"vla"},{"id":"2410.05629","title":"Vector-ICL: In-context Learning with Continuous Vector Representations","created":"2024-10-08","cited_by_count":13,"area":null},{"id":"2503.19851","title":"Towards Online Multi-Modal Social Interaction Understanding","created":"2025-03-25","cited_by_count":12,"area":null},{"id":"2602.01851","title":"How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editing","created":"2026-02-02","cited_by_count":12,"area":null},{"id":"2504.12795","title":"EarthGPT-X: A Spatial MLLM for Multi-level Multi-Source Remote Sensing Imagery Understanding with Visual Prompting","created":"2025-04-17","cited_by_count":11,"area":"lr"},{"id":"2506.04220","title":"Struct2D: A Perception-Guided Framework for Spatial Reasoning in MLLMs","created":"2025-06-04","cited_by_count":10,"area":"lr"},{"id":"2509.04744","title":"WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning","created":"2025-09-05","cited_by_count":10,"area":"lr"},{"id":"2605.02913","title":"Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning","created":"2026-04-08","cited_by_count":9,"area":"lr"},{"id":"2411.11362","title":"MAIRA-Seg: Enhancing Radiology Report Generation with Segmentation-Aware Multimodal Large Language Models","created":"2024-11-18","cited_by_count":7,"area":"mllm"},{"id":"2505.24025","title":"DINO-R1: Incentivizing Reasoning Capability in Vision Foundation Models","created":"2025-05-29","cited_by_count":6,"area":"lr"},{"id":"2509.23724","title":"Video Panels for Long Video Understanding","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2603.12238","title":"SceneAssistant: A Visual Feedback Agent for Open-Vocabulary 3D Scene Generation","created":"2026-03-12","cited_by_count":6,"area":"agents"},{"id":"2411.18142","title":"Autonomous Imagination: Closed-Loop Decomposition of Visual-to-Textual Conversion in Visual Reasoning for Multimodal Large Language Models","created":"2024-11-27","cited_by_count":5,"area":"lr"},{"id":"2506.07575","title":"Uncertainty-o: One Model-agnostic Framework for Unveiling Uncertainty in Large Multimodal Models","created":"2025-06-09","cited_by_count":5,"area":"mllm"},{"id":"2601.09575","title":"OpenVoxel: Training-Free Grouping and Captioning Voxels for Open-Vocabulary 3D Scene Understanding","created":"2026-01-14","cited_by_count":5,"area":"mllm"},{"id":"2505.02867","title":"RESAnything: Attribute Prompting for Arbitrary Referring Segmentation","created":"2025-05-03","cited_by_count":4,"area":null},{"id":"2506.04650","title":"Neural Network Reprogrammability: A Unified Theme on Model Reprogramming, Prompt Tuning, and Prompt Instruction","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2602.12533","title":"AMPS: Adaptive Modality Preference Steering via Functional Entropy","created":"2026-02-13","cited_by_count":4,"area":"mllm"},{"id":"2603.14659","title":"VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting","created":"2026-03-15","cited_by_count":4,"area":"distill"},{"id":"2509.21874","title":"Abductive Logical Rule Induction by Bridging Inductive Logic Programming and Multimodal Large Language Models","created":"2025-09-26","cited_by_count":3,"area":"mllm"},{"id":"2511.02384","title":"RxnCaption: Reformulating Reaction Diagram Parsing as Visual Prompt Guided Captioning","created":"2025-11-04","cited_by_count":3,"area":null},{"id":"2505.14340","title":"Plane Geometry Problem Solving with Multi-modal Reasoning: A Survey","created":"2025-05-20","cited_by_count":2,"area":"lr"},{"id":"2506.16112","title":"AutoV: Loss-Oriented Ranking for Visual Prompt Retrieval in LVLMs","created":"2025-06-19","cited_by_count":2,"area":"mllm"},{"id":"2507.18447","title":"PDB-Eval: An Evaluation of Large Multimodal Models for Description and Explanation of Personalized Driving Behavior","created":"2025-07-24","cited_by_count":2,"area":"mllm"},{"id":"2510.24152","title":"Enhancing Vision-Language Models for Autonomous Driving through Task-Specific Prompting and Spatial Reasoning","created":"2025-10-28","cited_by_count":2,"area":"lr"},{"id":"2603.08007","title":"ViSA-Enhanced Aerial VLN: A Visual-Spatial Reasoning Enhanced Framework for Aerial Vision-Language Navigation","created":"2026-03-09","cited_by_count":2,"area":"lr"},{"id":"2604.03667","title":"Leveraging Gaze and Set-of-Mark in VLLMs for Human-Object Interaction Anticipation from Egocentric Videos","created":"2026-04-04","cited_by_count":2,"area":null},{"id":"2605.11169","title":"OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct Agents","created":"2026-05-11","cited_by_count":2,"area":"lr"},{"id":"2508.10065","title":"Invisible Watermarks, Visible Gains: Steering Machine Unlearning with Bi-Level Watermarking Design","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2602.11073","title":"Chatting with Images for Introspective Visual Thinking","created":"2026-02-11","cited_by_count":1,"area":"lr"},{"id":"2603.12533","title":"Do You See What I Am Pointing At? Gesture-Based Egocentric Video Question Answering","created":"2026-03-13","cited_by_count":1,"area":null},{"id":"2605.08526","title":"Skill-CMIB: Multimodal Agent Skill for Consistent Action via Conditional Multimodal Information Bottleneck","created":"2026-05-08","cited_by_count":1,"area":"agents"},{"id":"2605.15342","title":"Minerva-Ego: Spatiotemporal Hints for Egocentric Video Understanding","created":"2026-05-14","cited_by_count":1,"area":"lr"},{"id":"2607.24407","title":"Mixture-of-Thought-Tokens: Unifying Perception and Reasoning for Free-form Multimodal Grounding","created":"2026-07-27","cited_by_count":1,"area":"lr"},{"id":"2609.31193","title":"Who Says What: Symbolic Trimodal Binding Mechanisms in Audio-Visual LLMs","created":"2026-09-25","cited_by_count":1,"area":"lr"},{"id":"2502.15389","title":"The Role of Background Information in Reducing Object Hallucination in Vision-Language Models: Insights from Cutoff API Prompting","created":"2025-02-21","cited_by_count":0,"area":"mllm"},{"id":"2508.05053","title":"Finding Needles in Images: Can Multimodal LLMs Locate Fine Details?","created":"2025-08-07","cited_by_count":0,"area":"mllm"},{"id":"2508.11808","title":"Labels or Input? Rethinking Augmentation in Multimodal Hate Detection","created":"2025-08-15","cited_by_count":0,"area":"lr"},{"id":"2511.22499","title":"What Shape Is Optimal for Masks in Text Removal?","created":"2025-11-27","cited_by_count":0,"area":null},{"id":"2602.18941","title":"Global Commander and Local Operative: A Dual-Agent Framework for Scene Navigation","created":"2026-02-21","cited_by_count":0,"area":"agents"},{"id":"2603.16250","title":"Visual Prompt Discovery via Semantic Exploration","created":"2026-03-17","cited_by_count":0,"area":"lr"},{"id":"2603.16958","title":"PhysQuantAgent: An Inference Pipeline of Mass Estimation for Vision-Language Models","created":"2026-03-17","cited_by_count":0,"area":"mllm"},{"id":"2604.08846","title":"Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs","created":"2026-04-10","cited_by_count":0,"area":"mllm"},{"id":"2604.16993","title":"Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2604.22875","title":"SketchVLM: Vision language models can annotate images to explain thoughts and guide users","created":"2026-04-23","cited_by_count":0,"area":"lr"},{"id":"2605.25821","title":"[CLS] is Not Enough: Multi-Label Recognition via Patch-Level Inference and Adaptive Aggregation","created":"2026-05-25","cited_by_count":0,"area":"mllm"},{"id":"2608.14286","title":"Seeing Red, Thinking Bad: Color Bias in Vision Language Models","created":"2026-08-14","cited_by_count":0,"area":"lr"},{"id":"2610.06293","title":"VepAgent: Bridging Causal-Transition via Tool-Augmented Reinforcement Learning for Video Event Prediction","created":"2026-10-05","cited_by_count":0,"area":"lr"},{"id":"2610.18161","title":"Benchmarking Multimodal Large Language Models for Zero-Shot Human-Object Interaction","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}