Related papers: VLM-TDP: VLM-guided Trajectory-conditioned Diffusi…

Active multi-target tracking requires a mobile robot to balance exploration for undetected targets with exploitation of uncertain tracked ones. Diffusion policies have emerged as a powerful approach for capturing diverse behavioral…

We observe that several existing policy gradient methods (such as vanilla policy gradient, PPO, A2C) may suffer from overly large gradients when the current policy is close to deterministic (even in some very simple environments), leading…

Temporal sequential tasks challenge humanoid robots, as existing Diffusion Policy (DP) and Action Chunking with Transformers (ACT) methods often lack temporal context, resulting in local optima traps and excessive repetitive actions. To…

Enabling robots to perform diverse tasks across varied environments is a central challenge in robot learning. While vision-language-action (VLA) models have shown promise for generalizable robot skills, realizing their full potential…

Latent Diffusion Models (LDMs) enable high-quality image synthesis while avoiding excessive compute demands by training a diffusion model in a compressed lower-dimensional latent space. Here, we apply the LDM paradigm to high-resolution…

Vision-Language Navigation in Continuous Environments (VLN-CE) requires agents to follow natural language instructions through free-form 3D spaces. Existing VLN-CE approaches typically use a two-stage waypoint planning framework, where a…

Reinforcement learning (RL) has shown extraordinary potential in aligning diffusion models to downstream tasks, yet most of them still suffer from significant reward hacking, which degrades generative diversity and quality by inducing…

Long-horizon robotic manipulation requires dense feedback that reflects how a task advances through its procedural stages, not merely whether the final outcome is successful. Existing reward models often rely on trajectory-level success…

Recent Speech Large Language Models~(LLMs) have achieved impressive capabilities in end-to-end speech interaction. However, the prevailing autoregressive paradigm imposes strict serial constraints, limiting generation efficiency and…

Vision-language-action (VLA) models are effective robot action executors, but they remain limited on long-horizon tasks due to the dual burden of extended closed-loop planning and diverse physical operations. We therefore propose…

Diffusion and flow matching models have achieved remarkable success in text-to-image generation. However, these models typically rely on the predetermined denoising schedules for all prompts. The multi-step reverse diffusion process can be…

In this work, we focus on addressing the long-horizon manipulation tasks in densely cluttered scenes. Such tasks require policies to effectively manage severe occlusions among objects and continually produce actions based on visual…

This work introduces Video Diffusion Transformer (VDT), which pioneers the use of transformers in diffusion-based video generation. It features transformer blocks with modularized temporal and spatial attention modules to leverage the rich…

Imitation learning has emerged as a crucial ap proach for acquiring visuomotor skills from demonstrations, where designing effective observation encoders is essential for policy generalization. However, existing methods often struggle to…

Conditional diffusion models have exhibited superior performance in high-fidelity text-guided visual generation and editing. Nevertheless, prevailing text-guided visual diffusion models primarily focus on incorporating text-visual…

Large Language Model (LLM)-based agents have shown promise in procedural tasks, but the potential of multimodal instructions augmented by texts and videos to assist users remains under-explored. To address this gap, we propose the Visually…

Reinforcement learning has emerged as a principled post-training paradigm for Temporal Video Grounding (TVG) due to its on-policy optimization, yet existing GRPO-based methods remain fundamentally constrained by sparse reward signals and…

As a robot senses and selects actions, the world keeps changing. This inference delay creates a gap of tens to hundreds of milliseconds between the observed state and the state at execution. In this work, we take the natural generalization…

Diffusion models have recently emerged as powerful tools for robot motion planning by capturing the multi-modal distribution of feasible trajectories. However, their extension to multi-robot settings with flexible, language-conditioned task…

Reasoning over long sequences of observations and actions is essential for many robotic tasks. Yet, learning effective long-context policies from demonstrations remains challenging. As context length increases, training becomes increasingly…