arXiv AI
Jul 28
VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference
arXiv:2512. 01031v2 Announce Type: replace-cross Abstract: Vision-Language-Action models (VLAs) are becoming increasingly capable across diverse robotic tasks.
Learning to Act While Waiting: RL Finetuning of Generalist Robot Policies Under Inference Latency
The paper introduces ARLI, a latency‑aware framework that enables reinforcement learning fine‑tuning of large generalist robot policies despite inference delays. ARLI combines asynchronous inference with state augmentations—incorporating committed actions and mid‑inference observations—to restore near‑Markovian dynamics and maintain reactivity. Experiments on simulated and real‑world manipulation tasks show that ARLI allows effective policy improvement under latency, outperforming standard RL even in no‑latency scenarios.
Related stories
arXiv Machine Learning
1d ago
Reinforcement Learning for Real-Time Vision-Language-Action Policies
arXiv:2609.18207v1 Announce Type: cross Abstract: Reinforcement learning fine-tuning on top of large, pretrained Vision-Language-Action (VLA) models offers promise for highly reliable robot deploymen...
arXiv AI
Jun 4
DEFLECT: Temporal Counterfactual Preference Learning for Delay-Robust Asynchronous VLAs
arXiv:2605. 19294v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) policies increasingly rely on asynchronous inference to hide large-model latency behind ongoing robot motion.
arXiv Computer Vision
Aug 21
RoMAN-Flow: Taming Autoregressive Normalizing Flows for Offline Reinforcement Learning in Robotic Manipulation
arXiv:2608. 20208v1 Announce Type: new Abstract: Offline reinforcement learning improves robotic policies using previously collected data without further environment interaction.
Hugging Face Trending Papers
Aug 20
RoMAN-Flow: Taming Autoregressive Normalizing Flows for Offline Reinforcement Learning in Robotic Manipulation
Offline reinforcement learning improves robotic policies using previously collected data without further environment interaction. Yet prevalent diffusion- and flow-matching robot policies lack tractable likelihoods, limiting their use in likelihood-based offline RL post-training.
arXiv AI
Aug 17
AtomBridge: Agentic VLA Inference Plugin for Long-Horizon Tasks in Scientific Experiments
arXiv:2602. 09430v2 Announce Type: replace-cross Abstract: Robotic laboratories play a critical role in autonomous scientific discovery by enabling scalable, continuous experimental execution.
arXiv AI
Jun 15
Elastic Queries Reinforcement Learning: Self-Aware Policy Execution for VLA Models
arXiv:2606. 14375v1 Announce Type: cross Abstract: Vision-language-action (VLA) models are powerful action generators for robot manipulation, but they are typically executed with fixed inference and replanning schedules.
arXiv AI
Jul 20
SLAC: Safe and Efficient Real-Robot Reinforcement Learning via Unsupervised Simulation Pre-Training
arXiv:2506. 04147v5 Announce Type: replace-cross Abstract: Building capable household and industrial robots requires mastering the control of versatile, high-degree-of-freedom (DoF) systems such as mobile manipulators.
arXiv AI
Jun 2
SpeedAug: Policy Acceleration via Tempo-Enriched Policy and RL Fine-Tuning
arXiv:2512. 00062v2 Announce Type: replace-cross Abstract: Robotic policy learning for complex real-world manipulation tasks has seen rapid recent progress, enabled in large part by the ability to collect demonstrations through human operation.
arXiv AI
Aug 18
Algorithm-Architecture Co-Design for Efficient VLA Inference via Speculative Inference and Verification
arXiv:2608. 15636v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in the field of embodied AI, but their high computational cost and limited predicted action length hinder real-time deployment.
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
6d ago
2AM: Grounding Agent-Side Memory as Guidance for Steerable Action Models in Long-Horizon Manipulation
The paper introduces 2AM, a system that separates memory and action execution in long‑horizon robot manipulation. 2AM stores task memory exclusively in a multimodal Agent, while a single RGB‑based, stateless Action Model performs motion based on language and optional 2D hints. On the LIBERO‑Mem benchmark, 2AM achieves 76.3% average completion—over 61 points higher than the best baseline—demonstrating that agent‑side memory and precise steering of the Action Model can substantially improve performance.