{"total":115,"rows":[{"id":"2210.07474","title":"SQA3D: Situated Question Answering in 3D Scenes","created":"2022-10-14","cited_by_count":314,"area":"lr"},{"id":"2405.14093","title":"A Survey on Vision-Language-Action Models for Embodied AI","created":"2024-05-23","cited_by_count":279,"area":"vla"},{"id":"2403.11481","title":"VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding","created":"2024-03-18","cited_by_count":229,"area":"mllm"},{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130,"area":null},{"id":"2408.14023","title":"Video-CCAM: Enhancing Video-Language Understanding with Causal Cross-Attention Masks for Short and Long Videos","created":"2024-08-26","cited_by_count":98,"area":"mllm"},{"id":"2403.16182","title":"EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World","created":"2024-03-24","cited_by_count":95,"area":null},{"id":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91,"area":null},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84,"area":null},{"id":"2410.08202","title":"Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training","created":"2024-10-10","cited_by_count":82,"area":"mllm"},{"id":"2411.15296","title":"MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs","created":"2024-11-22","cited_by_count":72,"area":"mllm"},{"id":"2312.06722","title":"EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning","created":"2023-12-11","cited_by_count":69,"area":"lr"},{"id":"2508.13073","title":"Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey","created":"2025-08-18","cited_by_count":69,"area":"vla"},{"id":"2408.02718","title":"MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models","created":"2024-08-05","cited_by_count":67,"area":"mllm"},{"id":"2504.15271","title":"Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models","created":"2025-04-21","cited_by_count":64,"area":"mllm"},{"id":"2303.18230","title":"Procedure-Aware Pretraining for Instructional Video Understanding","created":"2023-03-31","cited_by_count":48,"area":null},{"id":"2502.07411","title":"EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering","created":"2025-02-11","cited_by_count":44,"area":null},{"id":"2503.13646","title":"Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos","created":"2025-03-17","cited_by_count":44,"area":"mllm"},{"id":"2412.04447","title":"EgoPlan-Bench2: A Benchmark for Multimodal Large Language Model Planning in Real-World Scenarios","created":"2024-12-05","cited_by_count":41,"area":"lr"},{"id":"2308.07893","title":"Memory-and-Anticipation Transformer for Online Action Understanding","created":"2023-08-15","cited_by_count":39,"area":null},{"id":"2504.02438","title":"Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation","created":"2025-04-03","cited_by_count":37,"area":"mllm"},{"id":"2406.07544","title":"Situational Awareness Matters in 3D Vision Language Reasoning","created":"2024-06-11","cited_by_count":33,"area":null},{"id":"2411.19083","title":"ObjectRelator: Enabling Cross-View Object Relation Understanding Across Ego-Centric and Exo-Centric Perspectives","created":"2024-11-28","cited_by_count":29,"area":null},{"id":"2510.13747","title":"InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2409.18127","title":"EgoLM: Multi-Modal Language Model of Egocentric Motions","created":"2024-09-26","cited_by_count":28,"area":"mllm"},{"id":"2410.16668","title":"Satori: Towards Proactive AR Assistant with Belief-Desire-Intention User Modeling","created":"2024-10-22","cited_by_count":25,"area":null},{"id":"2412.09613","title":"PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models","created":"2024-12-12","cited_by_count":25,"area":"mllm"},{"id":"2503.09143","title":"Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding","created":"2025-03-12","cited_by_count":25,"area":null},{"id":"2501.00358","title":"Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding","created":"2024-12-31","cited_by_count":24,"area":null},{"id":"2503.14935","title":"FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding","created":"2025-03-19","cited_by_count":24,"area":"mllm"},{"id":"2507.18342","title":"EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs","created":"2025-07-24","cited_by_count":23,"area":null},{"id":"2509.01106","title":"Robix: A Unified Model for Robot Interaction, Reasoning and Planning","created":"2025-09-01","cited_by_count":23,"area":null},{"id":"2503.08221","title":"EgoBlind: Towards Egocentric Visual Assistance for the Blind","created":"2025-03-11","cited_by_count":21,"area":"mllm"},{"id":"2508.10729","title":"EgoCross: Benchmarking Multimodal Large Language Models for Cross-Domain Egocentric Video Question Answering","created":"2025-08-14","cited_by_count":21,"area":"mllm"},{"id":"2511.12609","title":"Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data","created":"2025-11-16","cited_by_count":21,"area":"moe"},{"id":"2503.15275","title":"Challenges and Trends in Egocentric Vision: A Survey","created":"2025-03-19","cited_by_count":20,"area":null},{"id":"2502.18778","title":"M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance","created":"2025-02-26","cited_by_count":19,"area":null},{"id":"2510.06218","title":"EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark","created":"2025-10-07","cited_by_count":19,"area":null},{"id":"2504.08449","title":"Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Input","created":"2025-04-11","cited_by_count":17,"area":null},{"id":"2501.06835","title":"X-LeBench: A Benchmark for Extremely Long Egocentric Video Understanding","created":"2025-01-12","cited_by_count":15,"area":null},{"id":"2506.05414","title":"SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing","created":"2025-06-04","cited_by_count":15,"area":"lr"},{"id":"2410.14682","title":"ET-Plan-Bench: Embodied Task-level Planning Benchmark Towards Spatial-Temporal Cognition with Foundation Models","created":"2024-10-02","cited_by_count":13,"area":null},{"id":"2501.05037","title":"LongViTU: Instruction Tuning for Long-Form Video Understanding","created":"2025-01-09","cited_by_count":13,"area":null},{"id":"2506.17629","title":"CLiViS: Unleashing Cognitive Map through Linguistic-Visual Synergy for Embodied Visual Reasoning","created":"2025-06-21","cited_by_count":13,"area":"lr"},{"id":"2507.12566","title":"Mono-InternVL-1.5: Towards Cheaper and Faster Monolithic Multimodal Large Language Models","created":"2025-07-16","cited_by_count":13,"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":"2503.22152","title":"EgoToM: Benchmarking Theory of Mind Reasoning from Egocentric Videos","created":"2025-03-28","cited_by_count":12,"area":"lr"},{"id":"2409.19650","title":"Grounding 3D Scene Affordance From Egocentric Interactions","created":"2024-09-29","cited_by_count":11,"area":null},{"id":"2602.14122","title":"EgoSound: Benchmarking Sound Understanding in Egocentric Videos","created":"2026-02-15","cited_by_count":11,"area":"mllm"},{"id":"2304.08492","title":"STRAP: Structured Object Affordance Segmentation with Point Supervision","created":"2023-04-17","cited_by_count":10,"area":null},{"id":"2412.16158","title":"HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding","created":"2024-12-20","cited_by_count":10,"area":"mllm"},{"id":"2405.19794","title":"Video Question Answering for People with Visual Impairments Using an Egocentric 360-Degree Camera","created":"2024-05-30","cited_by_count":9,"area":null},{"id":"2406.13123","title":"ViLCo-Bench: VIdeo Language COntinual learning Benchmark","created":"2024-06-19","cited_by_count":9,"area":null},{"id":"2502.16671","title":"MimeQA: Towards Socially-Intelligent Nonverbal Foundation Models","created":"2025-02-23","cited_by_count":9,"area":null},{"id":"2603.26586","title":"MA-Bench: Towards Fine-grained Micro-Action Understanding","created":"2026-03-27","cited_by_count":9,"area":"mllm"},{"id":"2401.01529","title":"Glance and Focus: Memory Prompting for Multi-Event Video Question Answering","created":"2024-01-03","cited_by_count":8,"area":null},{"id":"2504.04550","title":"Advancing Egocentric Video Question Answering with Multimodal Large Language Models","created":"2025-04-06","cited_by_count":8,"area":"lr"},{"id":"2505.12911","title":"HiERO: understanding the hierarchy of human behavior enhances reasoning on egocentric videos","created":"2025-05-19","cited_by_count":7,"area":null},{"id":"2604.01966","title":"Ego-Grounding for Personalized Question-Answering in Egocentric Videos","created":"2026-04-02","cited_by_count":7,"area":"mllm"},{"id":"2311.00556","title":"ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab","created":"2023-11-01","cited_by_count":6,"area":null},{"id":"2606.24422","title":"EgoSAT: A Comprehensive Benchmark of Egocentric Streaming Interaction Understanding","created":"2026-06-23","cited_by_count":6,"area":"mllm"},{"id":"2607.24744","title":"Data Pyramid for Embodied Manipulation: A Survey","created":"2026-07-27","cited_by_count":6,"area":null},{"id":"2404.00973","title":"VideoDistill: Language-aware Vision Distillation for Video Question Answering","created":"2024-04-01","cited_by_count":5,"area":null},{"id":"2502.02487","title":"Hier-EgoPack: Hierarchical Egocentric Video Understanding with Diverse Task Perspectives","created":"2025-02-04","cited_by_count":5,"area":null},{"id":"2504.01472","title":"ANNEXE: Unified Analyzing, Answering, and Pixel Grounding for Egocentric Interaction","created":"2025-04-02","cited_by_count":5,"area":null},{"id":"2603.00490","title":"LifeEval: A Multimodal Benchmark for Assistive AI in Egocentric Daily Life Tasks","created":"2026-02-28","cited_by_count":5,"area":"mllm"},{"id":"2603.22529","title":"Ego2Web: A Web Agent Benchmark Grounded in Egocentric Videos","created":"2026-03-23","cited_by_count":5,"area":"agents"},{"id":"2605.29793","title":"Fewer Steps, Better Performance: Efficient Cross-Modal Clip Trimming for Video Moment Retrieval Using Language","created":"2026-05-28","cited_by_count":5,"area":null},{"id":"2607.11523","title":"Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos","created":"2026-07-13","cited_by_count":5,"area":null},{"id":"2503.11345","title":"EgoSplat: Open-Vocabulary Egocentric Scene Understanding with Language Embedded 3D Gaussian Splatting","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2505.17114","title":"RAVEN: Query-Guided Representation Alignment for Question Answering over Audio, Video, Embedded Sensors, and Natural Language","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2512.11362","title":"An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges","created":"2025-12-12","cited_by_count":4,"area":"vla"},{"id":"2512.13238","title":"Ego-EXTRA: video-language Egocentric Dataset for EXpert-TRAinee assistance","created":"2025-12-15","cited_by_count":4,"area":null},{"id":"2605.24456","title":"EgoProx: Evaluating MLLMs on Egocentric 3D Proximity Reasoning Across a Cognitive Hierarchy","created":"2026-05-23","cited_by_count":4,"area":"lr"},{"id":"2407.09503","title":"PARSE-Ego4D: Personal Action Recommendation Suggestions for Egocentric Videos","created":"2024-06-14","cited_by_count":3,"area":null},{"id":"2504.03948","title":"ProbRes: Probabilistic Jump Diffusion for Open-World Egocentric Activity Recognition","created":"2025-04-04","cited_by_count":3,"area":null},{"id":"2506.14189","title":"Egocentric Human-Object Interaction Detection: A New Benchmark and Method","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2601.00092","title":"Spatial4D-Bench: A Versatile 4D Spatial Intelligence Benchmark","created":"2025-12-31","cited_by_count":3,"area":"lr"},{"id":"2602.06139","title":"EgoAVU: Egocentric Audio-Visual Understanding","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2602.18996","title":"Learning Cross-View Object Correspondence via Cycle-Consistent Mask Prediction","created":"2026-02-22","cited_by_count":3,"area":null},{"id":"2603.12701","title":"Seeing Eye to Eye: Enabling Cognitive Alignment Through Shared First-Person Perspective in Human-AI Collaboration","created":"2026-03-13","cited_by_count":3,"area":null},{"id":"2605.10936","title":"Personal Visual Context Learning in Large Multimodal Models","created":"2026-05-11","cited_by_count":3,"area":"mllm"},{"id":"2607.11270","title":"Towards Predictive, Aligned, and Scalable Robot Learning","created":"2026-07-13","cited_by_count":3,"area":"wm"},{"id":"2310.03325","title":"Learning Concept-Based Causal Transition and Symbolic Reasoning for Visual Planning","created":"2023-10-05","cited_by_count":2,"area":"lr"},{"id":"2512.00885","title":"HanDyVQA: A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics","created":"2025-11-30","cited_by_count":2,"area":null},{"id":"2607.13792","title":"EgoProceVQA: A Novel Egocentric Procedural Understanding Task with Self-Skill-Exploration Agent","created":"2026-07-15","cited_by_count":2,"area":"agents"},{"id":"2510.12126","title":"MetaCaptioner: Towards Generalist Visual Captioning with Open-source Suites","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2512.13019","title":"SneakPeek: Future-Guided Instructional Streaming Video Generation","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2603.09731","title":"EXPLORE-Bench: Egocentric Scene Prediction with Long-Horizon Reasoning","created":"2026-03-10","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":"2605.15342","title":"Minerva-Ego: Spatiotemporal Hints for Egocentric Video Understanding","created":"2026-05-14","cited_by_count":1,"area":"lr"},{"id":"2605.17262","title":"EgoIntrospect: An Egocentric Dataset and Benchmark for User-Centric Internal State Reasoning","created":"2026-05-17","cited_by_count":1,"area":"lr"},{"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":"2606.25842","title":"Graph it first! Enabling Reasoning on Long-form Egocentric Videos through Scene Graphs","created":"2026-06-24","cited_by_count":1,"area":"lr"},{"id":"2607.02425","title":"Learning to Evolve Scenes: Reasoning about Human Activities with Scene Graphs","created":"2026-07-02","cited_by_count":1,"area":"lr"},{"id":"2501.18324","title":"A Video-grounded Dialogue Dataset and Metric for Event-driven Activities","created":"2025-01-30","cited_by_count":0,"area":null},{"id":"2504.07597","title":"Learning Long Short-Term Intention within Human Daily Behaviors","created":"2025-04-10","cited_by_count":0,"area":null},{"id":"2509.06485","title":"WS$^2$: Weakly Supervised Segmentation using Before-After Supervision in Waste Sorting","created":"2025-09-08","cited_by_count":0,"area":null},{"id":"2509.21980","title":"Resolving Ambiguity in Gaze-Facilitated Visual Assistant Interaction Paradigm","created":"2025-09-26","cited_by_count":0,"area":"mllm"},{"id":"2510.20285","title":"DMC$^3$: Dual-Modal Counterfactual Contrastive Construction for Egocentric Video Question Answering","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2511.08348","title":"VideoChain: A Transformer-Based Framework for Multi-hop Video Question Generation","created":"2025-11-11","cited_by_count":0,"area":null}],"next_cursor":"100"}