Success Rate

Paper notes on improving success rates in robotic physical AI tasks

• WEAVER, Better, Faster, Longer: An Effective World Model for Robotic Manipulation 2026-06-12
  multi-view RGB + proprioception + action chunk를 입력으로 미래 latent rollout과 reward/value를 빠르게 예측해, π0.5 같은 VLA policy의 offline evaluation, synthetic-data policy improvement, test-time best-of-N planning을 가능하게 만든 action-conditioned latent world model
  Korean inference-time success-rate WAM VLA fine-tuning auxiliary-module-training training-data
• DAM-VLA: Decoupled Asynchronous Multimodal Vision Language Action model 2026-06-11
  VLA의 synchronous clock 가정이 contact-rich manipulation의 multi-rate sensor structure와 맞지 않는다고 보고, modality별 asynchronous latent buffer + gated cross-attention으로 X-VLA를 100 Hz controller 기반 closed-loop execution에 맞춘다
  Korean VLA fine-tuning component-scratch-training
• Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments 2026-06-01
  Qwen3.5 VLM + DiT flow-matching action decoder / embodiment-aware prompt / joint pretraining → generalist VLA (manipulation, navigation, human egocentric motion, trajectory prediction)
  Korean VLA foundation-Model
• A Factory-Floor Deployment Case Study of VLA Pipelines for Industrial Packaging Task: Workflow, Failures, and Lessons 2026-05-28
  데이터 수집·teleoperation·runtime·failure analysis 루프를 설계해서 pretrained π0.5를 실제 공장 포장 작업에 배포하는 시도, 그리고 거기서 얻은 교훈들
  Korean real-world VLA fine-tuning
• HyperSim: A Holistic Sim-To-Real Framework For Robust Robotic Manipulation 2026-05-27
  더 현실적인 시뮬레이션 + 더 다양한 recovery trajectory + 소량 real data co-training → zero-shot/few-shot sim-to-real 성능 향상
  Korean sim2real VLA fine-tuning
• SMoDP: Semantically Structured Mixture-of-Experts for Compositional Robotic Manipulation 2026-05-25
  Diffusion policy의 MoE router를 skill-aware하게 만들어 multi-task manipulation에서 expert를 의미 있는 skill 단위로 재사용하게 만든다
  Korean MoE multi-task diffusion-policy scratch-training