Related papers: Decoupled Action Expert: Confining Task Knowledge …

Vision-Language-Action (VLA) models have advanced rapidly with stronger backbones, broader pre-training, and larger demonstration datasets, yet their action heads remain largely homogeneous: most directly predict action commands in a fixed…

Large-scale AI model training divides work across thousands of GPUs, then synchronizes gradients across them at each step. This incurs a significant network burden that only centralized, monolithic clusters can support, driving up…

Vision-Language-Action (VLA) models are emerging as a promising paradigm for end-to-end autonomous driving, valued for their potential to leverage world knowledge and reason about complex driving scenes. However, existing methods suffer…

Interactive multimodal agents must convert raw visual observations into coherent sequences of language-conditioned actions -- a capability that current vision-language models (VLMs) still lack. Earlier reinforcement-learning (RL) efforts…

Diffusion Policy has shown great performance in robotic manipulation tasks under stochastic perturbations, due to its ability to model multimodal action distributions. Nonetheless, its reliance on a computationally expensive reverse-time…

Diffusion large language models (dLLMs) generate text via iterative denoising but consistently underperform on multi-step reasoning. We hypothesize this gap stems from a coordination problem: AR models build coherence token-by-token, while…

The training of diffusion-based models for image generation is predominantly controlled by a select few Big Tech companies, raising concerns about privacy, copyright, and data authority due to their lack of transparency regarding training…

Developing robust and general-purpose manipulation policies represents a fundamental objective in robotics research. While Vision-Language-Action (VLA) models have demonstrated promising capabilities for end-to-end robot control, existing…

Vision--Language--Action (VLA) models that encode actions using a discrete tokenization scheme are increasingly adopted for robotic manipulation, but existing decoding paradigms remain fundamentally limited. Whether actions are decoded…

Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing methods are largely limited to single-task optimization. Extending RL to multiple tasks is challenging: joint…

Generating instructional images of human daily actions from an egocentric viewpoint serves as a key step towards efficient skill transfer. In this paper, we introduce a novel problem -- egocentric action frame generation. The goal is to…

Sim-to-real transfer remains a fundamental challenge in robot manipulation due to the entanglement of perception and control in end-to-end learning. We present a decoupled framework that learns each component where it is most reliable:…

Current reinforcement learning (RL) methods can successfully learn single tasks but often generalize poorly to modest perturbations in task domain or training procedure. In this work, we present a decoupled learning strategy for RL that…

Vision--language--action (VLA) policies are trained to imitate actions; their loss never asks them to estimate reward, progress, or future success. Their frozen representations nevertheless carry such information, and it can be read out and…

Diffusion models are trained by learning a sequence of models that reverse each step of noise corruption. Typically, the model parameters are fully shared across multiple timesteps to enhance training efficiency. However, since the…

Leveraging vast amounts of unlabeled internet video data for embodied AI is currently bottlenecked by the lack of action labels and the presence of action-correlated visual distractors. Although recent latent action policy optimization…

Typical reinforcement learning (RL) agents learn to complete tasks specified by reward functions tailored to their domain. As such, the policies they learn do not generalize even to similar domains. To address this issue, we develop a…

Recent advances in multimodal large language models (MLLMs) have enabled image-based question-answering capabilities. However, a key limitation is the use of CLIP as the visual encoder; while it can capture coarse global information, it…

Reinforcement learning (RL) has demonstrated remarkable capability in acquiring robot skills, but learning each new skill still requires substantial data collection for training. The pretrain-and-finetune paradigm offers a promising…

Vision Foundation Models (VFMs) pretrained on massive datasets exhibit impressive performance on various downstream tasks, especially with limited labeled target data. However, due to their high inference compute cost, these models cannot…