arXiv AI
Don't Throw Away the Tail: Action Upcycling for Policy Acceleration
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
1d ago
Staircase Policy: Streaming Inference for World-Action Models with Large Action Chunks
arXiv:2609.36471v1 Announce Type: cross Abstract: World-Action Models (WAMs) improve robotic manipulation by conditioning action generation on predicted future observations, but future prediction add...
arXiv AI
Jun 6
TempoVLA: Learning Speed-Controllable Vision-Language-Action Policies
arXiv:2606. 06491v1 Announce Type: cross Abstract: Robot manipulation alternates between low-risk transit phases that call for fast execution and high-risk contact stages that demand slow, precise motion.
arXiv AI
Sep 1
PAVE: Predictive Alignment and Value-Guided Evolution for World-Action Policies
arXiv:2608.30378v1 Announce Type: cross Abstract: Direct vision-language-action policies generate continuous robot actions efficiently, but standard behavior cloning leaves two complementary gaps: th...
arXiv Machine Learning
Sep 17
Reinforcement Learning for Real-Time Vision-Language-Action Policies
The paper presents Real‑Time EXPO‑FT, a reinforcement learning framework that fine‑tunes large Vision‑Language‑Action models for real‑time robotic control. It separates slow, expressive action generation from fast, reactive edits, allowing a lightweight policy to adjust actions based on the latest observation. Experiments on the Kinetix benchmark and four dynamic real‑world tasks show that Real‑Time EXPO‑FT achieves superior performance, improving policy success rates from 42% to 97% with only ten minutes of online data and no human intervention.
Hugging Face Trending Papers
Jun 4
TempoVLA: Learning Speed-Controllable Vision-Language-Action Policies
Robot manipulation alternates between low-risk transit phases that call for fast execution and high-risk contact stages that demand slow, precise motion. Yet existing Vision-Language-Action models (VLAs) only inherit a single fixed speed from training demonstrations.
arXiv AI
Aug 5
Continue or Replan? Bernoulli-Continuation Policy Learning for Adaptive Horizon Execution
arXiv:2608. 03483v1 Announce Type: cross Abstract: Existing chunk-based Vision-Language-Action (VLA) models execute a fixed number of actions (i.