{"total":104,"rows":[{"id":"2507.15597","title":"Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos","created":"2025-07-21","cited_by_count":102,"area":"vla"},{"id":"2510.07077","title":"Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications","created":"2025-10-08","cited_by_count":84,"area":"mllm"},{"id":"2506.13654","title":"Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning","created":"2025-06-16","cited_by_count":68,"area":"lr"},{"id":"2605.12090","title":"World Action Models: The Next Frontier in Embodied AI","created":"2026-05-12","cited_by_count":50,"area":"wm"},{"id":"2602.03310","title":"RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalization","created":"2026-02-03","cited_by_count":30,"area":"vla"},{"id":"2503.12542","title":"ST-Think: How Multimodal Large Language Models Reason About 4D Worlds from Ego-Centric Videos","created":"2025-03-16","cited_by_count":21,"area":"lr"},{"id":"2506.05425","title":"SIV-Bench: A Video Benchmark for Social Interaction Understanding and Reasoning","created":"2025-06-05","cited_by_count":18,"area":"lr"},{"id":"2602.21736","title":"Joint-Aligned Latent Action: Towards Scalable VLA Pretraining in the Wild","created":"2026-02-25","cited_by_count":15,"area":"vla"},{"id":"2603.01455","title":"From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents","created":"2026-03-02","cited_by_count":15,"area":"lr"},{"id":"2507.21045","title":"Reconstructing 4D Spatial Intelligence: A Survey","created":"2025-07-28","cited_by_count":14,"area":null},{"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":"2512.04451","title":"StreamEQA: Towards Streaming Video Understanding for Embodied Scenarios","created":"2025-12-04","cited_by_count":12,"area":null},{"id":"2606.20781","title":"World Action Models: A Survey","created":"2026-06-18","cited_by_count":12,"area":"wm"},{"id":"2505.24287","title":"EgoExOR: An Ego-Exo-Centric Operating Room Dataset for Surgical Activity Understanding","created":"2025-05-30","cited_by_count":11,"area":null},{"id":"2508.00518","title":"Fine-grained Spatiotemporal Grounding on Egocentric Videos","created":"2025-08-01","cited_by_count":11,"area":null},{"id":"2509.21986","title":"Developing Vision-Language-Action Model from Egocentric Videos","created":"2025-09-26","cited_by_count":11,"area":"vla"},{"id":"2602.14122","title":"EgoSound: Benchmarking Sound Understanding in Egocentric Videos","created":"2026-02-15","cited_by_count":11,"area":"mllm"},{"id":"2506.06253","title":"Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Vision","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2508.07470","title":"AURA: A Fine-Grained Benchmark and Decomposed Metric for Audio-Visual Reasoning","created":"2025-08-10","cited_by_count":8,"area":"lr"},{"id":"2602.13444","title":"FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation","created":"2026-02-13","cited_by_count":7,"area":null},{"id":"2605.24500","title":"EgoAdapt: A Multi-Scene Egocentric Adaptation Method for CVPR 2026 HD-EPIC VQA Challenge","created":"2026-05-23","cited_by_count":7,"area":null},{"id":"2507.05258","title":"Spatio-Temporal LLM: Reasoning about Environments and Actions","created":"2025-07-07","cited_by_count":6,"area":"lr"},{"id":"2508.07251","title":"Understanding Dynamic Scenes in Ego Centric 4D Point Clouds","created":"2025-08-10","cited_by_count":6,"area":"lr"},{"id":"2510.16134","title":"Aria Gen 2 Pilot Dataset","created":"2025-10-17","cited_by_count":6,"area":null},{"id":"2605.26102","title":"InstructSAM: Segment Any Instance with Any Instructions","created":"2026-05-25","cited_by_count":6,"area":null},{"id":"2607.24744","title":"Data Pyramid for Embodied Manipulation: A Survey","created":"2026-07-27","cited_by_count":6,"area":null},{"id":"2605.31557","title":"EGOSTREAM: A Diagnostic Benchmark for Streaming Episodic Memory in Egocentric Vision","created":"2026-05-29","cited_by_count":5,"area":"inference"},{"id":"2606.18558","title":"MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction","created":"2026-06-17","cited_by_count":5,"area":null},{"id":"2511.16595","title":"TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding","created":"2025-11-20","cited_by_count":4,"area":"mllm"},{"id":"2511.18242","title":"EgoVITA: Learning to Plan and Verify for Egocentric Video Reasoning","created":"2025-11-23","cited_by_count":4,"area":"lr"},{"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":"2512.14870","title":"HERBench: A Benchmark for Multi-Evidence Integration in Video Question Answering","created":"2025-12-16","cited_by_count":4,"area":null},{"id":"2512.16908","title":"SceneDiff: A Benchmark and Method for Multiview Object Change Detection","created":"2025-12-18","cited_by_count":4,"area":null},{"id":"2601.10228","title":"Optimizing Multimodal LLMs for Egocentric Video Understanding: A Solution for the HD-EPIC VQA Challenge","created":"2026-01-15","cited_by_count":3,"area":"lr"},{"id":"2603.01104","title":"Egocentric Co-Pilot: Web-Native Smart-Glasses Agents for Assistive Egocentric AI","created":"2026-03-01","cited_by_count":3,"area":"agents"},{"id":"2604.16170","title":"neuralCAD-Edit: An Expert Benchmark for Multimodal-Instructed 3D CAD Model Editing","created":"2026-04-17","cited_by_count":3,"area":null},{"id":"2606.00825","title":"SuperMemory-VQA: An Egocentric Visual Question-Answering Benchmark for Long-Horizon Memory","created":"2026-05-30","cited_by_count":3,"area":null},{"id":"2607.28625","title":"ACE-Data-0: Human-Centric Ambient Capture as Embodied Data Engine","created":"2026-07-30","cited_by_count":3,"area":null},{"id":"2506.12312","title":"Perspective on Utilizing Foundation Models for Laboratory Automation in Materials Research","created":"2025-06-14","cited_by_count":2,"area":null},{"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":"2512.04085","title":"Unique Lives, Shared World: Learning from Single-Life Videos","created":"2025-12-03","cited_by_count":2,"area":null},{"id":"2601.04491","title":"A Closed-Loop Multi-Agent System Driven by LLMs for Meal-Level Personalized Nutrition Management","created":"2026-01-08","cited_by_count":2,"area":null},{"id":"2603.13741","title":"Ego-1K -- A Large-Scale Multiview Video Dataset for Egocentric Vision","created":"2026-03-14","cited_by_count":2,"area":null},{"id":"2603.25539","title":"PAWS: Perception of Articulation in the Wild at Scale from Egocentric Videos","created":"2026-03-26","cited_by_count":2,"area":null},{"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":"2604.19564","title":"EgoSelf: From Memory to Personalized Egocentric Assistant","created":"2026-04-21","cited_by_count":2,"area":null},{"id":"2605.18553","title":"StableHand: Quality-Aware Flow Matching for World-Space Dual-Hand Motion Estimation from Egocentric Video","created":"2026-05-18","cited_by_count":2,"area":"diffusion"},{"id":"2607.08537","title":"Whareformer: Learning to Track What is Where in Long Egocentric Videos","created":"2026-07-09","cited_by_count":2,"area":null},{"id":"2512.16456","title":"Prime and Reach: Synthesising Body Motion for Gaze-Primed Object Reach","created":"2025-12-18","cited_by_count":1,"area":null},{"id":"2603.06561","title":"EgoReasoner: Learning Egocentric 4D Reasoning via Task-Adaptive Structured Thinking","created":"2026-03-06","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":"2603.12147","title":"EgoIntent: A Pre-Outcome Micro-Step Benchmark for Understanding What, Why, and Next","created":"2026-03-12","cited_by_count":1,"area":null},{"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":"2603.17993","title":"GMT: Goal-Conditioned Multimodal Transformer for 6-DOF Object Trajectory Synthesis in 3D Scenes","created":"2026-03-18","cited_by_count":1,"area":"lr"},{"id":"2604.09886","title":"Not Your Stereo-Typical Estimator: Combining Vision and Language for Volume Perception","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2604.11038","title":"EgoFun3D: Modeling Interactive Objects from Egocentric Videos using Function Templates","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2604.17873","title":"Spatiotemporal Sycophancy: Negation-Based Gaslighting in Video Large Language Models","created":"2026-04-20","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":"2605.18214","title":"EgoInteract: Synthetic Egocentric Videos Generation for Interaction Understanding and Anticipation","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2606.13497","title":"SPARC: Reliable Spatial Annotations from Robot Demonstrations at Scale","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2606.17384","title":"Improving and Evaluating Hand-Object Interaction Detection","created":"2026-06-16","cited_by_count":1,"area":null},{"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":"2608.05215","title":"VLAff: Vision-Language-Affordance Model for Unified Actionable Affordances","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2503.23447","title":"CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition","created":"2025-03-30","cited_by_count":0,"area":null},{"id":"2505.20788","title":"Enhancing Wearable Tap Water Audio Detection through Subclass Annotation in the HD-Epic Dataset","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2506.06748","title":"THU-Warwick Submission for EPIC-KITCHEN Challenge 2025: Semi-Supervised Video Object Segmentation","created":"2025-06-07","cited_by_count":0,"area":null},{"id":"2510.23253","title":"A Video Is Not Worth a Thousand Words","created":"2025-10-27","cited_by_count":0,"area":"mllm"},{"id":"2512.07668","title":"EgoCampus: Egocentric Pedestrian Eye Gaze Model and Dataset","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2512.11393","title":"The N-Body Problem: Parallel Execution from Single-Person Egocentric Video","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2512.15006","title":"Evaluating the Capability of Video Question Generation for Expert Knowledge Elicitation","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2602.16545","title":"Let's Split Up: Zero-Shot Classifier Edits for Fine-Grained Video Understanding","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2603.02363","title":"Beyond Caption-Based Queries for Video Moment Retrieval","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2603.03944","title":"SCP: Spatial Causal Prediction in Video","created":"2026-03-04","cited_by_count":0,"area":"lr"},{"id":"2603.22450","title":"Static Scene Reconstruction from Dynamic Egocentric Videos","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2604.01421","title":"EgoFlow: Gradient-Guided Flow Matching for Egocentric 6DoF Object Motion Generation","created":"2026-04-01","cited_by_count":0,"area":"diffusion"},{"id":"2604.08342","title":"EgoEverything: A Benchmark for Human Behavior Inspired Long Context Egocentric Video Understanding in AR Environment","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.11913","title":"V-Nutri: Dish-Level Nutrition Estimation from Egocentric Cooking Videos","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.24893","title":"Interactive Episodic Memory with User Feedback","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.12074","title":"BARISTA: A Multi-Task Egocentric Benchmark for Compositional Visual Understanding","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.13335","title":"Ego2World: Compiling Egocentric Cooking Videos into Executable Worlds for Belief-State Planning","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.15417","title":"From Frames to Temporal Graphs: In-Context Egocentric Action Recognition with Vision-Language Models","created":"2026-06-13","cited_by_count":0,"area":"mllm"},{"id":"2607.02096","title":"LongEgoRefer: A Benchmark for Long-Form Egocentric Video Referring Expression Comprehension","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.04057","title":"PreSIST: Vision-Language-Informed Object Persistence Prediction in Open-World Scenes","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2607.08514","title":"Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.14350","title":"Beyond Pairwise Relations: Dynamic Manipulation Hypergraphs for Vision-Based Human Activity Recognition","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2608.02140","title":"HiResNets: Native Full-HD Video Recognition with Foveal Residual Streams","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.04865","title":"Cooking beyond Frames: A Stereo Event Camera Dataset in the Kitchen","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.08016","title":"EgoTrack3D: A Modular Framework for Egocentric 3D Object Tracking","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.12627","title":"EgoCITE: Context-Augmented Indexing and Time-Aware Retrieval for Long-Horizon Egocentric Memory","created":"2026-08-12","cited_by_count":0,"area":"agents"},{"id":"2608.16263","title":"Seeing Before Answering: Training-Free Visual Layer Profiling for Vision-Language Models","created":"2026-08-17","cited_by_count":0,"area":"mllm"},{"id":"2608.26495","title":"Video-FLAIR: Not Whether to Reason, But How","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2608.27562","title":"VidParse: Online Parsing of Egocentric Procedures Like a Pro","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.07135","title":"NutriBench-Kitchen: Benchmarking Embodied AI for Nutrition Management","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.12408","title":"GSO-Net: Visual State Machines for Hazardous Freight Transfer Compliance at Petrochemical Logistics Nodes","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.17064","title":"Neuro-Symbolic Hierarchical Intention Anticipation in Human Behavior","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.30981","title":"STORM-Bench: Evaluating Online Video QA under Evolving and Incomplete Evidence","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.36691","title":"Video2Skill: From Streaming Experience to Reusable Embodied Skills","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.37559","title":"APM-Bench: Benchmarking Cross-session Persistent Memory for Egocentric Streaming Video Assistants","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39166","title":"Beyond the Remembered World: Predictive 4D Belief for Persistent Navigation in Evolving Worlds","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39665","title":"ChronoGraph: Functional 4D Scene Graphs with Vision-Language Models for Interaction Understanding and Grounded Planning","created":"2026-09-30","cited_by_count":0,"area":"mllm"}],"next_cursor":"100"}