{"total":91,"rows":[{"id":"2503.21460","title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","created":"2025-03-27","cited_by_count":205,"area":"agents"},{"id":"2503.13377","title":"Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding","created":"2025-03-17","cited_by_count":146,"area":"mllm"},{"id":"2604.02317","title":"A Simple Baseline for Streaming Video Understanding","created":"2026-04-02","cited_by_count":33,"area":null},{"id":"2508.13142","title":"Holistic Evaluation of Multimodal LLMs on Spatial Intelligence","created":"2025-08-18","cited_by_count":29,"area":"mllm"},{"id":"2602.05665","title":"Graph-based Agent Memory: Taxonomy, Techniques, and Applications","created":"2026-02-05","cited_by_count":25,"area":"agents"},{"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":"2506.21356","title":"ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models","created":"2025-06-26","cited_by_count":22,"area":"mllm"},{"id":"2510.12422","title":"VideoLucy: Deep Memory Backtracking for Long Video Understanding","created":"2025-10-14","cited_by_count":22,"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":"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":"2510.23569","title":"EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT","created":"2025-10-27","cited_by_count":16,"area":"lr"},{"id":"2505.24869","title":"SiLVR: A Simple Language-based Video Reasoning Framework","created":"2025-05-30","cited_by_count":14,"area":"lr"},{"id":"2503.19851","title":"Towards Online Multi-Modal Social Interaction Understanding","created":"2025-03-25","cited_by_count":12,"area":null},{"id":"2511.01755","title":"3EED: Ground Everything Everywhere in 3D","created":"2025-11-03","cited_by_count":12,"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":"2602.00288","title":"TimeBlind: A Spatio-Temporal Compositionality Benchmark for Video LLMs","created":"2026-01-30","cited_by_count":11,"area":null},{"id":"2510.22443","title":"Benchmarking Egocentric Multimodal Goal Inference for Assistive Wearable Agents","created":"2025-10-25","cited_by_count":8,"area":"mllm"},{"id":"2603.05484","title":"Towards Multimodal Lifelong Understanding: A Dataset and Agentic Baseline","created":"2026-03-05","cited_by_count":8,"area":"agents"},{"id":"2503.18950","title":"Target-Aware Video Diffusion Models","created":"2025-03-24","cited_by_count":7,"area":"diffusion"},{"id":"2510.23397","title":"VideoTG-R1: Boosting Video Temporal Grounding via Curriculum Reinforcement Learning on Reflected Boundary Annotations","created":"2025-10-27","cited_by_count":7,"area":"lr"},{"id":"2606.16353","title":"What Should a Streaming Video Model Remember?","created":"2026-06-15","cited_by_count":7,"area":null},{"id":"2508.01915","title":"EgoTrigger: Toward Audio-Driven Image Capture for Human Memory Enhancement in All-Day Energy-Efficient Smart Glasses","created":"2025-08-03","cited_by_count":6,"area":null},{"id":"2604.03486","title":"VisionClaw: Always-On AI Agents through Smart Glasses","created":"2026-04-03","cited_by_count":6,"area":"agents"},{"id":"2605.28732","title":"MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems","created":"2026-05-27","cited_by_count":6,"area":"lr"},{"id":"2607.24744","title":"Data Pyramid for Embodied Manipulation: A Survey","created":"2026-07-27","cited_by_count":6,"area":null},{"id":"2511.13261","title":"Building Egocentric Procedural AI Assistant: Methods, Benchmarks, and Challenges","created":"2025-11-17","cited_by_count":5,"area":"mllm"},{"id":"2603.09827","title":"MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents","created":"2026-03-10","cited_by_count":5,"area":null},{"id":"2605.24481","title":"OmniEgo-R$^2$: A Routed Reasoning Framework for the 1st Cross-Domain EgoCross Challenge at CVPR 2026","created":"2026-05-23","cited_by_count":5,"area":"lr"},{"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":"2607.11523","title":"Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos","created":"2026-07-13","cited_by_count":5,"area":null},{"id":"2608.12122","title":"HandEdit: A Unified Benchmark for Egocentric Human-to-Robot Dexterous Hand Image Editing","created":"2026-08-12","cited_by_count":5,"area":null},{"id":"2608.13416","title":"StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMs","created":"2026-08-13","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":"2602.20597","title":"Interaction-aware Representation Modeling with Co-occurrence Consistency for Egocentric Hand-Object Parsing","created":"2026-02-24","cited_by_count":4,"area":null},{"id":"2605.08271","title":"Bridging Modalities, Spanning Time: Structured Memory for Ultra-Long Agentic Video Reasoning","created":"2026-05-08","cited_by_count":4,"area":"lr"},{"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":"2601.19850","title":"EgoHandICL: Egocentric 3D Hand Reconstruction with In-Context Learning","created":"2026-01-27","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":"2605.16481","title":"Visual Agentic Memory: Enabling Online Long Video Understanding via Online Indexing, Hierarchical Memory, and Agentic Retrieval","created":"2026-05-15","cited_by_count":3,"area":"agents"},{"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":"2608.05703","title":"StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding","created":"2026-08-06","cited_by_count":3,"area":"agents"},{"id":"2608.13113","title":"EgoMonth: A Month-Level Egocentric Video Benchmark for Long-Term Spatiotemporal Memory","created":"2026-08-13","cited_by_count":3,"area":"mllm"},{"id":"2604.19564","title":"EgoSelf: From Memory to Personalized Egocentric Assistant","created":"2026-04-21","cited_by_count":2,"area":null},{"id":"2605.26316","title":"E$^3$C: Video Generation with 3D Environmental Memory and Ego-Exo Human Pose Control","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2606.05008","title":"M$^3$Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Tasks","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2607.02689","title":"S-EMBER: A Large-Scale Benchmark for Streaming Egocentric Memory Retrieval","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2608.07663","title":"Keep It Simple: Multi-Key Episodic Memory Retrieval for Ultra-Long Video Understanding","created":"2026-08-07","cited_by_count":2,"area":"mllm"},{"id":"2601.17622","title":"Memento: Towards Proactive Visualization of Everyday Memories with Personal Wearable AR Assistant","created":"2026-01-24","cited_by_count":1,"area":null},{"id":"2602.22455","title":"Exploring Multimodal LMMs for Online Episodic Memory Question Answering on the Edge","created":"2026-02-25","cited_by_count":1,"area":"mllm"},{"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":"2605.31075","title":"Task-Focused Memorization for Multimodal Agents","created":"2026-05-29","cited_by_count":1,"area":"agents"},{"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":"2606.13141","title":"Rethinking RAG in Long Videos: What to Retrieve and How to Use It?","created":"2026-06-11","cited_by_count":1,"area":"rag"},{"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":"2607.02991","title":"GuideMe: Multi-Domain Task Guidance and Intervention in Streaming Video","created":"2026-07-03","cited_by_count":1,"area":"mllm"},{"id":"2511.09894","title":"EgoEMS: A High-Fidelity Multimodal Egocentric Dataset for Cognitive Assistance in Emergency Medical Services","created":"2025-11-13","cited_by_count":0,"area":null},{"id":"2604.01128","title":"Paper Reconstruction Evaluation: Evaluating Presentation and Hallucination in AI-written Papers","created":"2026-04-01","cited_by_count":0,"area":"agents"},{"id":"2604.07331","title":"RoSHI: A Versatile Robot-oriented Suit for Human Data In-the-Wild","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.15823","title":"Watching Movies Like a Human: Egocentric Emotion Understanding for Embodied Companions","created":"2026-04-17","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":"2606.02482","title":"X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2607.00547","title":"EgoGapBench: Benchmarking Egocentric Action Selection in Multi-Agent Scenes","created":"2026-07-01","cited_by_count":0,"area":"agents"},{"id":"2607.03934","title":"EgoInertia-MI: A Multimodal Egocentric Vision and IMU Benchmark for Motor Impairment Assessment","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2607.10269","title":"Devil in the Lens: Analyzing and Defending Physical Prompt Injection Against Vision-Language Models on Wearable Devices","created":"2026-07-11","cited_by_count":0,"area":"safety"},{"id":"2607.10350","title":"ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory","created":"2026-07-11","cited_by_count":0,"area":"agents"},{"id":"2607.14497","title":"Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation","created":"2026-07-16","cited_by_count":0,"area":"mllm"},{"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":"2608.18711","title":"EgoHRV: Continuous Heart Rate Variability Estimation from Egocentric Systems for Autonomic Response and Skill Assessment","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.21360","title":"OmniAssistBench: Assistant-style Interaction Benchmark for Omni-LLMs","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.22975","title":"Budget-Constrained Embodied Perception: Four Resource Walls and a Pre-Registered Evaluation of Access-Structured Perception on Open Models at less than 31B","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.25559","title":"AdaVDR: Adaptive Tool Use and Reflection for Video Deep Research","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.04438","title":"ICM-Bench: Person-Level Identity Reasoning in Multimodal Agents with Long-Term Memory","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.04802","title":"Linguistic Trajectory Encoding for Efficient Long-Horizon Spatial Memory in Embodied Agents","created":"2026-09-04","cited_by_count":0,"area":"agents"},{"id":"2609.06504","title":"CAM: Question Answering on Entity-Centric Videos with Continuous Extraction and Adaptive Querying","created":"2026-09-06","cited_by_count":0,"area":"mllm"},{"id":"2609.14973","title":"PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models","created":"2026-09-14","cited_by_count":0,"area":"mllm"},{"id":"2609.19167","title":"To Memories and Beyond: From Remembering to Knowing You across Long-Term Multimodal Personal Archives","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.19793","title":"AI Smart Glasses for Wearable Intelligence: From Egocentric Sensing to Agentic Personalization","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.22691","title":"Generative Embodied Multiple Behavior Control Systems for Human-like Agents","created":"2026-09-19","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":"2609.37938","title":"Does Local Video Understanding Transfer Across Encounters? The EgoGears Benchmark","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38155","title":"Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.40195","title":"MemLife: Curating and Reasoning over Long-Term Egocentric Video Memories","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01461","title":"NextMe-800: Anticipating Personal Behavior from Months of Egocentric Video","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.05013","title":"EMBER-Bench: Benchmarking Cross-Event Causal Memory in Long-Horizon Embodied Tasks","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.17128","title":"EgoProbe: Benchmarking Long-Range and Exact Memory in Streaming Egocentric Videos","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.17728","title":"Safety for Whom? Benchmarking Understanding Beyond Refusal in Egocentric Multimodal Assistants","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.18499","title":"EgoOmniWorld: Unifying Egocentric Understanding via Ego-Action-World Interactions","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}