{"total":58,"rows":[{"id":"2509.22548","title":"JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation","created":"2025-09-26","cited_by_count":89,"area":null},{"id":"2509.24871","title":"StreamForest: Efficient Online Video Understanding with Persistent Event Memory","created":"2025-09-29","cited_by_count":78,"area":"mllm"},{"id":"2508.21046","title":"CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification","created":"2025-08-28","cited_by_count":74,"area":"mllm"},{"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":"2505.05467","title":"StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant","created":"2025-05-08","cited_by_count":63,"area":null},{"id":"2503.06220","title":"StreamMind: Unlocking Full Frame Rate Streaming Video Dialogue through Event-Gated Cognition","created":"2025-03-08","cited_by_count":46,"area":null},{"id":"2505.16827","title":"GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent","created":"2025-05-22","cited_by_count":35,"area":"agents"},{"id":"2508.01875","title":"StreamAgent: Towards Anticipatory Agents for Streaming Video Understanding","created":"2025-08-03","cited_by_count":33,"area":"inference"},{"id":"2511.07278","title":"StreamKV: Streaming Video Question-Answering with Segment-based KV Cache Retrieval and Compression","created":"2025-11-10","cited_by_count":26,"area":"inference"},{"id":"2512.00903","title":"SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead","created":"2025-11-30","cited_by_count":26,"area":"mllm"},{"id":"2511.05299","title":"LiveStar: Live Streaming Assistant for Real-World Online Video Understanding","created":"2025-11-07","cited_by_count":25,"area":null},{"id":"2511.10518","title":"SemanticVLA: Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation","created":"2025-11-13","cited_by_count":21,"area":"vla"},{"id":"2506.10387","title":"Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills","created":"2025-06-12","cited_by_count":19,"area":"mllm"},{"id":"2507.23372","title":"UniEmo: Unifying Emotional Understanding and Generation with Learnable Expert Queries","created":"2025-07-31","cited_by_count":18,"area":null},{"id":"2603.12938","title":"Thinking in Streaming Video","created":"2026-03-13","cited_by_count":16,"area":null},{"id":"2511.13193","title":"Cost-Effective Communication: An Auction-based Method for Language Agent Interaction","created":"2025-11-17","cited_by_count":14,"area":"agents"},{"id":"2512.01763","title":"HiconAgent: History Context-aware Policy Optimization for GUI Agents","created":"2025-12-01","cited_by_count":13,"area":"agents"},{"id":"2507.08064","title":"PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning","created":"2025-07-10","cited_by_count":11,"area":"distill"},{"id":"2603.08361","title":"$\\Delta$VLA: Prior-Guided Vision-Language-Action Models via World Knowledge Variation","created":"2026-03-09","cited_by_count":10,"area":"vla"},{"id":"2601.06843","title":"Speak While Watching: Unleashing TRUE Real-Time Video Understanding Capability of Multimodal Large Language Models","created":"2026-01-11","cited_by_count":8,"area":"mllm"},{"id":"2603.19054","title":"Em-Garde: A Propose-Match Framework for Proactive Streaming Video Understanding","created":"2026-03-19","cited_by_count":7,"area":null},{"id":"2605.27074","title":"IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams","created":"2026-05-26","cited_by_count":7,"area":"mllm"},{"id":"2601.10323","title":"ROMA: Real-time Omni-Multimodal Assistant with Interactive Streaming Understanding","created":"2026-01-15","cited_by_count":6,"area":"mllm"},{"id":"2605.05126","title":"ConsisVLA-4D: Advancing Spatiotemporal Consistency in Efficient 3D-Perception and 4D-Reasoning for Robotic Manipulation","created":"2026-05-06","cited_by_count":6,"area":"lr"},{"id":"2605.22671","title":"From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model","created":"2026-05-21","cited_by_count":6,"area":"vla"},{"id":"2510.13170","title":"Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism","created":"2025-10-15","cited_by_count":4,"area":"lr"},{"id":"2603.27593","title":"STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding","created":"2026-03-29","cited_by_count":4,"area":"lr"},{"id":"2606.08615","title":"Harnessing Streaming Video in the Wild","created":"2026-06-07","cited_by_count":4,"area":"mllm"},{"id":"2607.13298","title":"FOLIO: Focused Semantic Memory for Streaming Video Understanding","created":"2026-07-14","cited_by_count":4,"area":null},{"id":"2603.04592","title":"From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models","created":"2026-03-04","cited_by_count":3,"area":null},{"id":"2603.26746","title":"TDEC: Deep Embedded Image Clustering with Transformer and Distribution Information","created":"2026-03-23","cited_by_count":3,"area":null},{"id":"2605.05646","title":"MUSE: Resolving Manifold Misalignment in Visual Tokenization via Topological Orthogonality","created":"2026-05-07","cited_by_count":3,"area":null},{"id":"2511.21998","title":"Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance?","created":"2025-11-27","cited_by_count":2,"area":"mllm"},{"id":"2605.01858","title":"Decouple and Cache: KV Cache Construction for Streaming Video Understanding","created":"2026-05-03","cited_by_count":2,"area":"inference"},{"id":"2605.07575","title":"Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2605.19322","title":"DynaTok: Temporally Adaptive and Positional Bias-Aware Token Compression for Video-LLMs","created":"2026-05-19","cited_by_count":2,"area":"lr"},{"id":"2606.17798","title":"LiveStarPro: Proactive Streaming Video Understanding with Hierarchical Memory for Long-Horizon Streams","created":"2026-06-16","cited_by_count":2,"area":"inference"},{"id":"2510.01618","title":"Automated Genomic Interpretation via Concept Bottleneck Models for Medical Robotics","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2511.18811","title":"Mitigating Long-Tail Bias in HOI Detection via Adaptive Diversity Cache","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2602.15707","title":"Proactive Conversational Assistant for a Procedural Manual Task based on Audio and IMU","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2603.17930","title":"Interpretable Traffic Responsibility from Dashcam Video via Legal Multi Agent Reasoning","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2603.26744","title":"CNMBI: Determining the Number of Clusters Using Center Pairwise Matching and Boundary Filtering","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2604.03306","title":"Deep Image Clustering Based on Curriculum Learning and Density Information","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2606.00620","title":"FlowNar: Scalable Streaming Narration for Long-Form Videos","created":"2026-05-30","cited_by_count":1,"area":"mllm"},{"id":"2606.06991","title":"Don't Pause: Streaming Video-Language Synchrony for Online Video Understanding","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2606.09547","title":"Streaming Interventions: Can Video Large Language Models Correct Mistakes as They Occur?","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2606.19849","title":"ViCoStream: Streaming VideoLLMs Can Run Beyond 100 FPS with Stage-Wise Coordinated Inference","created":"2026-06-18","cited_by_count":1,"area":"inference"},{"id":"2608.27881","title":"StreamEMS: Streaming Video Understanding with Self-Evolving Memory Scheme for Vision-Language Models","created":"2026-08-28","cited_by_count":1,"area":"mllm"},{"id":"2609.11875","title":"UniMPA: A Unified Memory-Prediction-Action Model via Action-Grounded Transition Modeling","created":"2026-09-10","cited_by_count":1,"area":"vla"},{"id":"2609.18540","title":"SVMemAgent: A Streaming Video Memory Agent for Query-Agnostic Online Frame Selection","created":"2026-09-16","cited_by_count":1,"area":null},{"id":"2610.01762","title":"OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction","created":"2026-10-01","cited_by_count":1,"area":null},{"id":"2512.00812","title":"Causal Invariance and Counterfactual Learning Driven Cooperative Game for Multi-Label Classification","created":"2025-11-30","cited_by_count":0,"area":null},{"id":"2604.14176","title":"The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discovery","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2608.09723","title":"LookAgain: Closed-Loop GUI Grounding with Visually Grounded Reflection","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.06578","title":"Learning to Use Imagination: Progress-Conditioned Future Utilization for World Action Models","created":"2026-09-06","cited_by_count":0,"area":"wm"},{"id":"2609.31713","title":"Agentic Video Understanding: A Survey","created":"2026-09-21","cited_by_count":0,"area":"agents"},{"id":"2610.03123","title":"Foresight: planning future perception in streaming VLMs without retraining","created":"2026-10-02","cited_by_count":0,"area":"mllm"},{"id":"2610.05940","title":"ReMem: Streaming Video Understanding With Long Context Retention","created":"2026-10-05","cited_by_count":0,"area":"mllm"}],"next_cursor":null}