Related papers: Learning Native Continuation for Action Chunking F…

While Vision-Language-Action (VLA) models have revolutionized autonomous driving by unifying perception and planning, their reliance on explicit textual Chain-of-Thought (CoT) leads to semantic-perceptual decoupling and perceptual-symbolic…

We describe a recurrent neural network (RNN) based architecture to learn the flow function of a causal, time-invariant and continuous-time control system from trajectory data. By restricting the class of control inputs to piecewise constant…

MEGA is a recent transformer-based architecture, which utilizes a linear recurrent operator whose parallel computation, based on the FFT, scales as $O(LlogL)$, with $L$ being the sequence length. We build upon their approach by replacing…

Although pre-trained Vision-Language-Action (VLA) models exhibit impressive generalization in robotic manipulation, post-training remains crucial to ensure reliable performance during deployment. However, standard offline Supervised…

Recent Vision-Language-Action (VLA) models equipped with Flow Matching (FM) action heads achieve state-of-the-art performance in complex robot manipulation. However, the multi-step iterative ODE solving required by FM introduces inference…

Vision-Language-Action (VLA) tasks require reasoning over complex visual scenes and executing adaptive actions in dynamic environments. While recent studies on reasoning VLAs show that explicit chain-of-thought (CoT) can improve…

Vision-Language-Action (VLA) models map visual observations and language instructions directly to robotic actions. While effective for simple tasks, standard VLA models often struggle with complex, multi-step tasks requiring logical…

Recent work has begun to equip vision-language-action (VLA) policies with explicit intermediate reasoning. In embodied control, however, textual chain-of-thought is a poor fit: irrelevant or weakly textual information can interfere with…

Vision-Language-Action (VLA) models are a powerful paradigm for generalist robotic control. However, their high computational cost and limited control frequency hinder real-time robotic manipulation, especially when large vision-language…

Robotic manipulation with Vision-Language-Action models requires efficient inference over long-horizon multi-modal context, where attention to dense visual tokens dominates computational cost. Existing methods optimize inference speed by…

Recently, some studies have integrated Multimodal Large Language Models into robotic manipulation, constructing vision-language-action models (VLAs) to interpret multimodal information and predict SE(3) poses. While VLAs have shown…

Recent advances in Vision-Language-Action (VLA) models have enabled robots to execute increasingly complex tasks. However, VLA models trained through imitation learning struggle to operate reliably in dynamic environments and often fail…

Generalist robot policies increasingly benefit from large-scale pretraining, but offline data alone is insufficient for robust real-world deployment. Deployed robots encounter distribution shifts, long-tail failures, task variations, and…

We propose ReinFlow, a simple yet effective online reinforcement learning (RL) framework that fine-tunes a family of flow matching policies for continuous robotic control. Derived from rigorous RL theory, ReinFlow injects learnable noise…

Vision-language-action (VLA) models provide a promising foundation for general-purpose robotics. However, their successful deployment in real-world scenarios requires the ability to continually acquire new skills while retaining previously…

Controlled generation imposes sequence-level constraints (syntax, style, safety) that depend on future tokens, making exact conditioning of an autoregressive LM intractable. Tractable surrogates such as HMMs can approximate continuation…

Vision-Language-Action (VLA) models offer a unified framework for robotic perception and control, but their ability to scale to real-world, long-horizon tasks is limited by the high computational cost of attention and the large memory…

Long-horizon robotic manipulation tasks require executing multiple interdependent subtasks in strict sequence, where errors in detecting subtask completion can cascade into downstream failures. Existing Vision-Language-Action (VLA) models…

A fundamental objective of manipulation policy design is to endow robots to comprehend human instructions, reason about scene cues, and execute generalized actions in dynamic environments. Recent autoregressive vision-language-action (VLA)…

While vision-language models have advanced significantly, their application in language-conditioned robotic manipulation is still underexplored, especially for contact-rich tasks that extend beyond visually dominant pick-and-place…