🧰 Vision-Language-Action models

The items that name it 14

• Quantize by Doing: Task-Guided Mixed-Precision Quantization of Vision-Language-Action Models
  paperas classification.technologies2026-10-28It is written here as vision-language-action model.
• Build specialized multimodal models with LFM3
  articleas classification.technologies2026-10-27It is written here as vision-language-action model.
• Introducing LFM3: Every Modality for Specialized Intelligence
  articleas classification.technologies2026-10-27It is written here as vision-language-action model.
• Test-time training in robotics shows no clear gains in demo response
  articleas classification.technologies2026-10-26It is written here as vision-language-action model.
• When to Stop Penalizing Actions? Martingale GRPO for VLA Reinforcement Learning
  paperas classification.technologies2026-10-23It is written here as vision-language-action model.
• MAST-VLA: Skill-Conditioned Adaptation with Trajectory-Affordance Priors for Multi-Skill Robot Manipulation
  paperas classification.technologies2026-10-23It is written here as vision-language-action model.
• Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success
  paperas classification.technologies2026-10-22It is written here as vision-language-action model.
• Progress Probes $P^2$: Lightweight Runtime Monitoring for Vision-Language-Action Models
  paperas classification.technologies2026-10-22It is written here as vision-language-action model.
• AgenticRoboRL: Bringing Coding-Agent Post-Training to Agentic Robotics
  paperas classification.technologies2026-10-20It is written here as vision-language-action model.
• ChunkAct: Action Chunking for Agentic Robotics
  paperas classification.technologies2026-10-13It is written here as vision-language-action model.
• RARA: Robust Policy Fine-Tuning through Retrieval-Anchored Representation Alignment for Robotic Manipulation
  paperas models2026-10-09It is written here as Vision-Language-Action (VLA) models.

  VLA

• Recursive Video In-Context Learning for Agentic Robot
  paperas classification.technologies2026-10-05It is written here as vision-language-action model.
• DuoMind: Enabling Distributed Multi-Robot Coordination with Semantic Communication
  paperas classification.technologies2026-10-01It is written here as vision-language-action model.
• A Brain Too Big to Carry — On-Device vs Datacenter Inference
  articleas classification.technologies2026-09-14It is written here as vision-language-action model.