arXiv AI

Don't Throw Away the Tail: Action Upcycling for Policy Acceleration

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.

By Perry Dong, Kuo-Han Hung, Dorsa Sadigh, Chelsea Finn
arXiv Machine Learning
Jun 9

C$^3$ache: Accelerating World Action Models with Cross Inference Chunk Cache

arXiv:2606. 08962v1 Announce Type: new Abstract: World Action Models (WAMs) generalize better than standard Vision-Language-Action (VLA) policies to novel motions and environments, because a video-modeling objective lets them learn from abundant unlabeled video rather than scarce labeled robot demonstrations.

By Weisen Zhao, Lam Nguyen, Zhicong Lu, Yuzhang Shang
arXiv AI
Oct 2

Measuring the Stability Assumption Behind Action Chunking

The paper investigates how small action errors evolve when using action chunking in behavioural cloning. By injecting errors at each state and observing their growth under open‑loop (no replanning) and closed‑loop (replanning) regimes, the authors classify states as contracting, expanding, or unresolved. Across twelve manipulation tasks, they find that stable states are rare, error amplification is common, and that short‑horizon fitting can overestimate long‑horizon propagation. Predictors trained on camera and proprioceptive data can recover open‑loop stability but only partially capture closed‑loop dynamics, indicating that standard imitation learning does not reliably produce policies that contract errors when perturbed.

By Aryan Goyal
arXiv AI
Oct 23

PaceVLA: Adaptive Temporal Action Quantization in Vision-Language-Action Models

PaceVLA introduces adaptive temporal action quantization for Vision‑Language‑Action models, enabling faster robot execution by aggregating low‑level actions into coarser steps when appropriate. The framework combines mode‑specific action decoders with a quantizability‑guided mode selection and a context‑conditioned router to decide execution granularity at each inference step. Experiments on simulation benchmarks and real‑world tasks demonstrate that PaceVLA improves execution efficiency while preserving task success rates across diverse embodiments.

By Hojin Jeon, Jimin Lee, Taekwan Kim, Nayoung Oh, Taeyoung Kim, Myungkyu Koo, Jinmo Koo, Joonwoo Ahn, Jinwoo Shin
arXiv Machine Learning
Oct 9

WAM-Cache: Staleness-Bounded KV Reuse for Efficient World Action Models

WAM-Cache is a training‑free framework that reuses layerwise key‑value (KV) representations from a pretrained video Diffusion Transformer (DiT) across control chunks, recomputing only a sparse set of refreshed tokens. By selecting refresh tokens based on the action expert’s cross‑attention, visual latent surprise, and a strict age bound, it reduces DiT prefill FLOPs by 32‑42% on datasets such as RoboTwin 2.0 and LIBERO while maintaining action accuracy within 0.7‑1.8 percentage points of the dense baseline in simulation and 2.5 points on a real robot.

By Kai Ding, Yang He, Ruijie Quan, Yi Yang
arXiv Computer Vision
Sep 30

EVO-WAM: Evolving World Action Models through Video-Action Verification

arXiv:2609.38057v1 Announce Type: new Abstract: Improving robot policies on new tasks without collecting additional expert demonstrations remains a central challenge in robot learning. World action m...

By Shiyang Zhou, Xionghao Wu, Wenbo Li, Shenghe Zheng, Jiyao Zhang, Songsong Yu, Yijun Yang, Jianhui Liu, Haoze Sun, Senqiao Yang, Li Jiang, Jingyong Su, Haoyang Huang, Zhuotao Tian