{"total":40,"rows":[{"id":"2509.19012","title":"Pure Vision Language Action (VLA) Models: A Comprehensive Survey","created":"2025-09-23","cited_by_count":49,"area":"mllm"},{"id":"2412.02611","title":"AV-Odyssey Bench: Can Your Multimodal LLMs Really Understand Audio-Visual Information?","created":"2024-12-03","cited_by_count":47,"area":"mllm"},{"id":"2411.18499","title":"OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved Image-Text Generation","created":"2024-11-27","cited_by_count":31,"area":"mllm"},{"id":"2409.18127","title":"EgoLM: Multi-Modal Language Model of Egocentric Motions","created":"2024-09-26","cited_by_count":28,"area":"mllm"},{"id":"2410.07177","title":"MM-Ego: Towards Building Egocentric Multimodal LLMs for Video QA","created":"2024-10-09","cited_by_count":24,"area":"mllm"},{"id":"2506.05287","title":"EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?","created":"2025-06-05","cited_by_count":21,"area":"mllm"},{"id":"2512.02231","title":"See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models","created":"2025-12-01","cited_by_count":20,"area":"mllm"},{"id":"2412.21080","title":"Vinci: A Real-time Embodied Smart Assistant based on Egocentric Vision-Language Model","created":"2024-12-30","cited_by_count":19,"area":"mllm"},{"id":"2501.04336","title":"Building a Mind Palace: Structuring Environment-Grounded Semantic Graphs for Effective Long Video Analysis with LLMs","created":"2025-01-08","cited_by_count":19,"area":"mllm"},{"id":"2412.13187","title":"HandsOnVLM: Vision-Language Models for Hand-Object Interaction Prediction","created":"2024-12-17","cited_by_count":15,"area":"mllm"},{"id":"2406.10221","title":"Long Story Short: Story-level Video Understanding from 20K Short Films","created":"2024-06-14","cited_by_count":12,"area":"mllm"},{"id":"2506.07016","title":"MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks","created":"2025-06-08","cited_by_count":12,"area":"mllm"},{"id":"2503.22610","title":"Evaluating Multimodal Language Models as Visual Assistants for Visually Impaired Users","created":"2025-03-28","cited_by_count":11,"area":"mllm"},{"id":"2602.14122","title":"EgoSound: Benchmarking Sound Understanding in Egocentric Videos","created":"2026-02-15","cited_by_count":11,"area":"mllm"},{"id":"2404.09933","title":"HOI-Ref: Hand-Object Interaction Referral in Egocentric Vision","created":"2024-04-15","cited_by_count":9,"area":"mllm"},{"id":"2401.10039","title":"GPT4Ego: Unleashing the Potential of Pre-trained Models for Zero-Shot Egocentric Action Recognition","created":"2024-01-18","cited_by_count":8,"area":"mllm"},{"id":"2503.04250","title":"An Egocentric Vision-Language Model based Portable Real-time Smart Assistant","created":"2025-03-06","cited_by_count":8,"area":"mllm"},{"id":"2604.01966","title":"Ego-Grounding for Personalized Question-Answering in Egocentric Videos","created":"2026-04-02","cited_by_count":7,"area":"mllm"},{"id":"2508.00399","title":"iSafetyBench: A video-language benchmark for safety in industrial environment","created":"2025-08-01","cited_by_count":5,"area":"mllm"},{"id":"2511.13261","title":"Building Egocentric Procedural AI Assistant: Methods, Benchmarks, and Challenges","created":"2025-11-17","cited_by_count":5,"area":"mllm"},{"id":"2501.05711","title":"From My View to Yours: Learning Egocentric Cues from Exocentric Video using Privileged Egocentric Supervision","created":"2025-01-10","cited_by_count":4,"area":"mllm"},{"id":"2502.01218","title":"Provable Ordering and Continuity in Vision-Language Pretraining for Generalizable Embodied Agents","created":"2025-02-03","cited_by_count":4,"area":"mllm"},{"id":"2512.24271","title":"Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation","created":"2025-12-30","cited_by_count":4,"area":"mllm"},{"id":"2510.22571","title":"STATUS Bench: A Rigorous Benchmark for Evaluating Object State Understanding in Vision-Language Models","created":"2025-10-26","cited_by_count":3,"area":"mllm"},{"id":"2504.00839","title":"Context-Aware Human Behavior Prediction Using Multimodal Large Language Models: Challenges and Insights","created":"2025-04-01","cited_by_count":2,"area":"mllm"},{"id":"2506.21586","title":"Can Vision Language Models Understand Mimed Actions?","created":"2025-06-17","cited_by_count":2,"area":"mllm"},{"id":"2509.14227","title":"Cin\\'{e}aste: A Fine-grained Contextual Movie Question Answering Benchmark","created":"2025-09-17","cited_by_count":2,"area":"mllm"},{"id":"2510.11509","title":"Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model","created":"2025-10-13","cited_by_count":2,"area":"mllm"},{"id":"2603.29281","title":"PRISM: A Multi-View Multi-Capability Retail Video Dataset for Embodied Vision-Language Models","created":"2026-03-31","cited_by_count":2,"area":"mllm"},{"id":"2608.05381","title":"C$^3$PO: Evaluating Cross-Modal Composition and Counterfactual Performance in Omnimodal Models","created":"2026-08-05","cited_by_count":2,"area":"mllm"},{"id":"2512.15957","title":"Seeing is Believing (and Predicting): Context-Aware Multi-Human Behavior Prediction with Vision Language Models","created":"2025-12-17","cited_by_count":1,"area":"mllm"},{"id":"2603.06999","title":"TrajPred: Trajectory-Conditioned Joint Embedding Prediction for Surgical Instrument-Tissue Interaction Recognition in Vision-Language Models","created":"2026-03-07","cited_by_count":1,"area":"mllm"},{"id":"2605.17070","title":"EPIC-Bench: A Perception-Centric Benchmark for Fine-Grained Embodied Visual Grounding in Vision-Language Models","created":"2026-05-16","cited_by_count":1,"area":"mllm"},{"id":"2606.09142","title":"Decoding Pedestrian Crossing Intention from Egocentric Vision via Vision Language Models","created":"2026-06-08","cited_by_count":1,"area":"mllm"},{"id":"2606.25084","title":"Are We There Yet? Exploring the Capabilities of MLLMs in Assistive AI Applications","created":"2026-06-23","cited_by_count":1,"area":"mllm"},{"id":"2607.00218","title":"EgoSafetyBench: A Diagnostic Egocentric Video Benchmark for Evaluating Embodied VLMs as Runtime Safety Guards","created":"2026-06-30","cited_by_count":1,"area":"mllm"},{"id":"2606.25160","title":"Toward Low-Latency Vision-Language Models with Doubly-Correct Predictions in Egocentric Visual Understanding","created":"2026-06-23","cited_by_count":0,"area":"mllm"},{"id":"2606.31187","title":"Learning to Deny: Action Denial in Multimodal Large Language Models","created":"2026-06-30","cited_by_count":0,"area":"mllm"},{"id":"2608.04589","title":"The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question Answering","created":"2026-08-05","cited_by_count":0,"area":"mllm"},{"id":"2609.17688","title":"CapMem: A Benchmark for Caption-Based Episodic Memory in Egocentric Video","created":"2026-09-15","cited_by_count":0,"area":"mllm"}],"next_cursor":null}