{"list":"other","total":64,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"2306.13649","title":"On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes","created":"2023-06-23","cited_by_count":939},{"id":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"id":"2407.15754","title":"LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding","created":"2024-07-22","cited_by_count":665},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"1609.05140","title":"The Option-Critic Architecture","created":"2016-09-16","cited_by_count":448},{"id":"2409.07429","title":"Agent Workflow Memory","created":"2024-09-11","cited_by_count":383},{"id":"1907.01657","title":"Dynamics-Aware Unsupervised Discovery of Skills","created":"2019-07-02","cited_by_count":313},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287},{"id":"2404.05726","title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","created":"2024-04-08","cited_by_count":229},{"id":"1908.09884","title":"Learning to Discover Novel Visual Categories via Deep Transfer Clustering","created":"2019-08-26","cited_by_count":225},{"id":"2010.11944","title":"Accelerating Reinforcement Learning with Learned Skill Priors","created":"2020-10-22","cited_by_count":223},{"id":"2201.02609","title":"Generalized Category Discovery","created":"2022-01-07","cited_by_count":211},{"id":"1903.08225","title":"Cross-task weakly supervised learning from instructional videos","created":"2019-03-19","cited_by_count":199},{"id":"2504.07079","title":"SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills","created":"2025-04-09","cited_by_count":192},{"id":"2307.00595","title":"RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot","created":"2023-07-02","cited_by_count":183},{"id":"2311.05997","title":"JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models","created":"2023-11-10","cited_by_count":171},{"id":"2411.03628","title":"StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding","created":"2024-11-06","cited_by_count":144},{"id":"2501.05510","title":"OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?","created":"2025-01-09","cited_by_count":142},{"id":"2501.03218","title":"Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction","created":"2025-01-06","cited_by_count":127},{"id":"2502.04144","title":"HD-EPIC: A Highly-Detailed Egocentric Video Dataset","created":"2025-02-06","cited_by_count":104},{"id":"2107.03377","title":"Long Short-Term Transformer for Online Action Detection","created":"2021-07-07","cited_by_count":88},{"id":"2310.08887","title":"METRA: Scalable Unsupervised RL with Metric-Aware Abstraction","created":"2023-10-13","cited_by_count":86},{"id":"2310.10021","title":"Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidance","created":"2023-10-16","cited_by_count":86},{"id":"2109.13841","title":"Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation","created":"2021-09-28","cited_by_count":83},{"id":"2506.23825","title":"Flash-VStream: Efficient Real-Time Understanding for Long Video Streams","created":"2025-06-30","cited_by_count":81},{"id":"1811.07391","title":"Temporal Recurrent Networks for Online Action Detection","created":"2018-11-18","cited_by_count":80},{"id":"1904.04189","title":"Unsupervised learning of action classes with continuous temporal embedding","created":"2019-04-08","cited_by_count":76},{"id":"2307.09955","title":"XSkill: Cross Embodiment Skill Discovery","created":"2023-07-19","cited_by_count":75},{"id":"2311.02058","title":"LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discovery","created":"2023-11-03","cited_by_count":67},{"id":"1803.09490","title":"Unsupervised Learning and Segmentation of Complex Activities from Video","created":"2018-03-26","cited_by_count":61},{"id":"2605.18747","title":"Code as Agent Harness","created":"2026-05-18","cited_by_count":47},{"id":"2406.07502","title":"Image Textualization: An Automatic Framework for Creating Accurate and Detailed Image Descriptions","created":"2024-06-11","cited_by_count":43},{"id":"2308.11063","title":"MetaGCD: Learning to Continually Learn in Generalized Category Discovery","created":"2023-08-21","cited_by_count":42},{"id":"2505.22654","title":"VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models","created":"2025-05-28","cited_by_count":41},{"id":"2505.08787","title":"UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations","created":"2025-05-13","cited_by_count":35},{"id":"2210.04174","title":"Grow and Merge: A Unified Framework for Continuous Categories Discovery","created":"2022-10-09","cited_by_count":33},{"id":"2502.12084","title":"VLM2-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues","created":"2025-02-17","cited_by_count":33},{"id":"2410.07113","title":"Personalized Visual Instruction Tuning","created":"2024-10-09","cited_by_count":24},{"id":"2410.06535","title":"Happy: A Debiased Learning Framework for Continual Generalized Category Discovery","created":"2024-10-09","cited_by_count":18},{"id":"2601.15224","title":"PROGRESSLM: Towards Progress Reasoning in Vision-Language Models","created":"2026-01-21","cited_by_count":15},{"id":"2603.00905","title":"pySpatial: Generating 3D Visual Programs for Zero-Shot Spatial Reasoning","created":"2026-03-01","cited_by_count":14},{"id":"2605.09874","title":"EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding","created":"2026-05-11","cited_by_count":13},{"id":"2510.14438","title":"WebAggregator: Enhancing Compositional Reasoning Capabilities of Deep Research Agent Foundation Models","created":"2025-10-16","cited_by_count":10},{"id":"2603.02623","title":"Uni-Skill: Building Self-Evolving Skill Repository for Generalizable Robotic Manipulation","created":"2026-03-03","cited_by_count":9},{"id":"2402.01348","title":"CORE: Mitigating Catastrophic Forgetting in Continual Learning through Cognitive Replay","created":"2024-02-02","cited_by_count":5},{"id":"2603.15800","title":"Evolving Contextual Safety in Multi-Modal Large Language Models via Inference-Time Self-Reflective Memory","created":"2026-03-16","cited_by_count":5},{"id":"2607.21655","title":"Progress Reward Modeling for Robotic Learning: A Comprehensive Survey","created":"2026-07-22","cited_by_count":5},{"id":"2607.14252","title":"MEMORA: Embodied Action Memory from Egocentric Videos for Reasoning and Planning","created":"2026-07-15","cited_by_count":4},{"id":"2609.00291","title":"StreamScout: Learning When to Look Deeper for Streaming Video Understanding","created":"2026-08-31","cited_by_count":3},{"id":"2609.19445","title":"From Models to Systems: A Comprehensive Survey of Efficient Multimodal Learning","created":"2026-09-16","cited_by_count":3},{"id":"2511.18203","title":"SkillWrapper: Generative Predicate Invention for Task-level Robot Planning","created":"2025-11-22","cited_by_count":2},{"id":"2607.25125","title":"LENS: Adaptive Spatio-Temporal Zooming for Keyframe Sampling in Long-Form Videos","created":"2026-07-27","cited_by_count":2},{"id":"2605.16412","title":"SCAR: Self-Supervised Continuous Action Representation Learning","created":"2026-05-13","cited_by_count":1}],"next_cursor":null}