{"list":"other","total":52,"rows":[{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2410.24164","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","created":"2024-10-31","cited_by_count":2407},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2504.16054","title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","created":"2025-04-22","cited_by_count":1761},{"id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","created":"2025-03-18","cited_by_count":1225},{"id":"2312.07104","title":"SGLang: Efficient Execution of Structured Language Model Programs","created":"2023-12-12","cited_by_count":1141},{"id":"2501.09747","title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","created":"2025-01-16","cited_by_count":665},{"id":"2602.15922","title":"World Action Models are Zero-shot Policies","created":"2026-02-17","cited_by_count":465},{"id":"2411.19650","title":"CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation","created":"2024-11-29","cited_by_count":422},{"id":"2603.16666","title":"Fast-WAM: Do World Action Models Need Test-time Future Imagination?","created":"2026-03-17","cited_by_count":349},{"id":"2501.01005","title":"FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving","created":"2025-01-02","cited_by_count":258},{"id":"2506.07339","title":"Real-Time Execution of Action Chunking Flow Policies","created":"2025-06-09","cited_by_count":216},{"id":"2606.02800","title":"Cosmos 3: Omnimodal World Models for Physical AI","created":"2026-06-01","cited_by_count":165},{"id":"2603.17240","title":"GigaWorld-Policy: An Efficient Action-Centered World--Action Model","created":"2026-03-18","cited_by_count":139},{"id":"2604.15483","title":"${\\pi}_{0.7}$: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities","created":"2026-04-16","cited_by_count":138},{"id":"2604.05014","title":"StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing","created":"2026-04-06","cited_by_count":112},{"id":"2602.11236","title":"ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning","created":"2026-02-11","cited_by_count":103},{"id":"2506.10100","title":"EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models","created":"2025-06-11","cited_by_count":93},{"id":"2502.02175","title":"VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching","created":"2025-02-04","cited_by_count":86},{"id":"2511.17502","title":"RynnVLA-002: A Unified Vision-Language-Action and World Model","created":"2025-11-21","cited_by_count":74},{"id":"2602.22818","title":"LeRobot: An Open-Source Library for End-to-End Robot Learning","created":"2026-02-26","cited_by_count":73},{"id":"2509.15965","title":"RLinf: Flexible and Efficient Large-scale Reinforcement Learning via Macro-to-Micro Flow Transformation","created":"2025-09-19","cited_by_count":57},{"id":"2605.12090","title":"World Action Models: The Next Frontier in Embodied AI","created":"2026-05-12","cited_by_count":50},{"id":"2602.12684","title":"Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution","created":"2026-02-13","cited_by_count":45},{"id":"2510.19430","title":"GigaBrain-0: A World Model-Powered Vision-Language-Action Model","created":"2025-10-22","cited_by_count":44},{"id":"2510.26742","title":"Running VLAs at Real-time Speed","created":"2025-10-30","cited_by_count":43},{"id":"2607.08639","title":"Native Video-Action Pretraining for Generalizable Robot Control","created":"2026-07-09","cited_by_count":36},{"id":"2602.14979","title":"RynnBrain: Open Embodied Foundation Models","created":"2026-02-13","cited_by_count":35},{"id":"2602.20309","title":"QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models","created":"2026-02-23","cited_by_count":30},{"id":"2607.00678","title":"ABot-M0.5: Unified Mobility-and-Manipulation World Action Model","created":"2026-07-01","cited_by_count":30},{"id":"2607.15330","title":"Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories","created":"2026-07-16","cited_by_count":29},{"id":"2607.06403","title":"From Foundation to Application: Improving VLA Models in Practice","created":"2026-07-07","cited_by_count":26},{"id":"2509.15212","title":"RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation","created":"2025-09-18","cited_by_count":25},{"id":"2603.24517","title":"AVO: Agentic Variation Operators for Autonomous Evolutionary Search","created":"2026-03-25","cited_by_count":24},{"id":"2606.14409","title":"Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stack","created":"2026-06-12","cited_by_count":22},{"id":"2604.07430","title":"HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents","created":"2026-04-08","cited_by_count":18},{"id":"2511.16449","title":"Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference","created":"2025-11-20","cited_by_count":17},{"id":"2512.22219","title":"MPK: A Compiler and Runtime for Mega-Kernelizing Tensor Programs","created":"2025-12-22","cited_by_count":15},{"id":"2604.05656","title":"SnapFlow: One-Step Action Generation for Flow-Matching VLAs via Progressive Self-Distillation","created":"2026-04-07","cited_by_count":14},{"id":"2605.30877","title":"Wall-OSS-0.5 Technical Report","created":"2026-05-29","cited_by_count":12},{"id":"2607.13960","title":"GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch","created":"2026-07-15","cited_by_count":11},{"id":"2606.09215","title":"MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulation","created":"2026-06-08","cited_by_count":10},{"id":"2605.24011","title":"ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models","created":"2026-05-19","cited_by_count":8},{"id":"2606.08962","title":"C$^3$ache: Accelerating World Action Models with Cross Inference Chunk Cache","created":"2026-06-08","cited_by_count":8},{"id":"2607.17977","title":"RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model","created":"2026-07-20","cited_by_count":8},{"id":"2606.20537","title":"Execution-State Capsules: Graph-Bound Execution-State Checkpoint and Restore for Low-Latency, Small-Batch, On-Device Physical-AI Serving","created":"2026-06-18","cited_by_count":7},{"id":"2603.14371","title":"OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelism","created":"2026-03-15","cited_by_count":4},{"id":"2604.13327","title":"Event Tensor: A Unified Abstraction for Compiling Dynamic Megakernel","created":"2026-04-14","cited_by_count":4},{"id":"2607.02501","title":"Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots","created":"2026-07-02","cited_by_count":2},{"id":"2607.06370","title":"ActionCache: Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement","created":"2026-07-07","cited_by_count":2}],"next_cursor":null}