fariver

摘要： 目录RT-1: ROBOTICS TRANSFORMER FOR REAL-WORLD CONTROL AT SCALETL;DRMethodinstructions与images模态特征处理TokenLearnerAction预测DataExperiment在新任务上Zero-shot泛化能力仿真 阅读全文

摘要： 目录Helix: A Vision-Language-Action Model for Generalist Humanoid ControlTL;DRMethodMotivationSystem 2 (S2，慢系统)System 1 (S1, 快系统)DataExperiment效果可视化总结与思 阅读全文

摘要： 目录RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic ControlTL;DRMethod模型Action表示Co-Fine-TuneReal-Time Inference如何实现连续运动控制训练数据Exper 阅读全文

摘要： 目录π0: A Vision-Language-Action Flow Model for General Robot ControlTL;DRMethodPaliGemma VLM基座模型VLA多模态的对齐机制与Transfusion的联系Flow Matching生成如何在本文所介绍的VLA模型 阅读全文

摘要： 目录UNLEASHING LARGE-SCALE VIDEO GENERATIVE PRE-TRAINING FOR VISUAL ROBOT MANIPULATIONTL;DRMethodPretrainRobot Data FinetuningExperiment总结与思考相关链接 UNLEAS 阅读全文

摘要： 目录OpenVLA: An Open-Source Vision-Language-Action ModelTL;DRMethodaction表示Training DataImplementationInfrastructureExperiment效果可视化总结与思考相关链接Related work 阅读全文

摘要： 目录Qwen3 Technical ReportTL;DRArchitectureMethodPre-trainingPost-trainingLong-CoT Cold StartThinking Mode FusionStage2的Reasoning RL 与 Stage4的General RL 阅读全文

摘要： 目录KIMI K2: OPEN AGENTIC INTELLIGENCETL;DRMethodQK-Clip在Transformer Attention中，什么是attention logits爆炸问题？QKClip为什么能解决attention logits爆炸的问题？AlgorithmPre-t 阅读全文

摘要： 目录Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large DatasetsTL; DR;DataStage I: Image PretrainingStage II: Curating a Video Pretr 阅读全文

摘要： 目录Flamingo: a Visual Language Model for Few-Shot LearningTL;DRMethodVisual processing and Perceiver ResamplerGATED XATTN-DENSE layersMixture of Vision 阅读全文