{"list":"other","total":51,"rows":[{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568},{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410},{"id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","created":"2025-03-18","cited_by_count":1225},{"id":"2410.07864","title":"RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation","created":"2024-10-10","cited_by_count":691},{"id":"2112.03227","title":"CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks","created":"2021-12-06","cited_by_count":584},{"id":"2501.15830","title":"SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model","created":"2025-01-27","cited_by_count":519},{"id":"2506.18088","title":"RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation","created":"2025-06-22","cited_by_count":518},{"id":"2505.06111","title":"UniVLA: Learning to Act Anywhere with Task-centric Latent Actions","created":"2025-05-09","cited_by_count":410},{"id":"2402.07865","title":"Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models","created":"2024-02-12","cited_by_count":339},{"id":"2206.11251","title":"Behavior Transformers: Cloning $k$ modes with one stone","created":"2022-06-22","cited_by_count":304},{"id":"2412.14803","title":"Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations","created":"2024-12-19","cited_by_count":289},{"id":"2508.19236","title":"MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation","created":"2025-08-26","cited_by_count":192},{"id":"2412.15109","title":"Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation","created":"2024-12-19","cited_by_count":161},{"id":"2403.03181","title":"Behavior Generation with Latent Actions","created":"2024-03-05","cited_by_count":160},{"id":"2503.07511","title":"PointVLA: Injecting the 3D World into Vision-Language-Action Models","created":"2025-03-10","cited_by_count":105},{"id":"2304.02556","title":"Detecting and Grounding Multi-Modal Media Manipulation","created":"2023-04-05","cited_by_count":99},{"id":"2408.03615","title":"Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks","created":"2024-08-07","cited_by_count":84},{"id":"2510.13778","title":"InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy","created":"2025-10-15","cited_by_count":84},{"id":"2311.11860","title":"LION : Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge","created":"2023-11-20","cited_by_count":81},{"id":"2404.16823","title":"Learning Visuotactile Skills with Two Multifingered Hands","created":"2024-04-25","cited_by_count":76},{"id":"2508.21046","title":"CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification","created":"2025-08-28","cited_by_count":74},{"id":"2408.15980","title":"In-Context Imitation Learning via Next-Token Prediction","created":"2024-08-28","cited_by_count":70},{"id":"2507.01016","title":"VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers","created":"2025-07-01","cited_by_count":70},{"id":"2409.13682","title":"ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation","created":"2024-09-20","cited_by_count":67},{"id":"2503.03663","title":"LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant","created":"2025-03-05","cited_by_count":58},{"id":"2309.14203","title":"Detecting and Grounding Multi-Modal Media Manipulation and Beyond","created":"2023-09-25","cited_by_count":56},{"id":"2306.10007","title":"Robot Learning with Sensorimotor Pre-training","created":"2023-06-16","cited_by_count":51},{"id":"2203.13504","title":"EmoCaps: Emotion Capsule based Model for Conversational Emotion Recognition","created":"2022-03-25","cited_by_count":48},{"id":"2409.18313","title":"Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation","created":"2024-09-26","cited_by_count":44},{"id":"2404.11699","title":"Retrieval-Augmented Embodied Agents","created":"2024-04-17","cited_by_count":31},{"id":"2407.12381","title":"Flow Matching Imitation Learning for Multi-Support Manipulation","created":"2024-07-17","cited_by_count":29},{"id":"2511.09516","title":"MAP-VLA: Memory-Augmented Prompting for Vision-Language-Action Model in Robotic Manipulation","created":"2025-11-12","cited_by_count":28},{"id":"2502.19902","title":"Optimus-2: Multimodal Minecraft Agent with Goal-Observation-Action Conditioned Policy","created":"2025-02-27","cited_by_count":25},{"id":"2510.20808","title":"The Reality Gap in Robotics: Challenges, Solutions, and Best Practices","created":"2025-10-23","cited_by_count":24},{"id":"2504.03515","title":"Dexterous Manipulation through Imitation Learning: A Survey","created":"2025-04-04","cited_by_count":21},{"id":"2511.10518","title":"SemanticVLA: Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation","created":"2025-11-13","cited_by_count":21},{"id":"2501.16297","title":"FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers","created":"2025-01-27","cited_by_count":20},{"id":"2602.20200","title":"Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation","created":"2026-02-22","cited_by_count":20},{"id":"2506.10387","title":"Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills","created":"2025-06-12","cited_by_count":19},{"id":"2511.17079","title":"H-GAR: A Hierarchical Interaction Framework via Goal-Driven Observation-Action Refinement for Robotic Manipulation","created":"2025-11-21","cited_by_count":17},{"id":"2511.18112","title":"EchoVLA: Robotic Vision-Language-Action Model with Synergistic Declarative Memory for Mobile Manipulation","created":"2025-11-22","cited_by_count":15},{"id":"2506.03863","title":"STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization","created":"2025-06-04","cited_by_count":13},{"id":"2512.01763","title":"HiconAgent: History Context-aware Policy Optimization for GUI Agents","created":"2025-12-01","cited_by_count":13},{"id":"2505.12410","title":"MTIL: Encoding Full History with Mamba for Temporal Imitation Learning","created":"2025-05-18","cited_by_count":10},{"id":"2603.12138","title":"HATS: Hardness-Aware Trajectory Synthesis for GUI Agents","created":"2026-03-12","cited_by_count":9},{"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},{"id":"2509.19658","title":"RoboSSM: Scalable In-context Imitation Learning via State-Space Models","created":"2025-09-24","cited_by_count":5}],"next_cursor":null}