FlowDAgger: Human-in-the-Loop Adaptation of Generative Robot Policies in Latent Space
FlowDAgger is a new method for adapting frozen generative robot policies using human interventions in latent space. It enables sample- and compute-efficient correction of failure modes outside the pretraining distribution without large-scale data collection or online RL.
Entities
Related
PAC-ACT: Post-training Actor-Critic for Action Chunking Transformers
PAC-ACT is a reinforcement-learning post-training framework for pretrained Action Chunking Transformer policies, designed to improve reliability in precision industrial contact manipulation under pose perturbations and contact-force constraints. It addresses distribution shift in contact-rich tasks that behavior-cloned policies suffer from.
ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation
Researchers introduced ARDY, a streaming generation framework that enables real-time synthesis of 3D human motions with text and kinematic control, bridging the gap between offline precision and online speed. The method addresses limitations in existing online approaches regarding controllability and complex text semantics.
CLAP paper proposes direct VLM-to-VLA adaptation to isolate semantic transfer
A new arXiv paper introduces CLAP, a method that converts pretrained vision-language models (VLMs) into vision-language-action models (VLAs) with minimal architectural changes, avoiding the distribution mismatch caused by predicting actions as bare numeric tokens. The approach aims to clarify how VLM capabilities transfer across model scales for robot control.
LLM/VLA models enable prompt-driven exploration in RL
A new research paper proposes using large language models (LLMs) and vision-language-action (VLA) models to drive exploration in reinforcement learning by modifying natural language prompts, which induce global behavioral changes beyond standard action noise. This approach could help policies escape weak local optima more effectively.
LeRobot v0.6.0 adds world model policies, new VLAs, and unified evaluation
LeRobot v0.6.0 introduces world model policies (VLA-JEPA, FastWAM, LingBot-VA) that learn to imagine future states, along with new VLAs (GR00T N1.7, MolmoAct2, EO-1, EVO1, Multitask DiT). It ships six new simulation benchmarks unified under lerobot-eval, a lerobot-rollout CLI with DAgger-style human-in-the-loop corrections, FSDP training, and cloud training on HF Jobs. Datasets gain depth support, automatic language annotation, custom video encoding, and up to 2x faster data loading.