Related papers: PPGuide: Steering Diffusion Policies with Performa…

Autonomous driving technology has seen significant advancements, but existing models often fail to fully capture the complexity of multi-agent environments, where interactions between dynamic agents are critical. To address this, we propose…

Imitation learning has emerged as a promising approach for addressing sequential decision-making problems, with the assumption that expert demonstrations are optimal. However, in real-world scenarios, most demonstrations are often…

We present Readout Guidance, a method for controlling text-to-image diffusion models with learned signals. Readout Guidance uses readout heads, lightweight networks trained to extract signals from the features of a pre-trained, frozen…

In recent years, generative models have shown remarkable capabilities across diverse fields, including images, videos, language, and decision-making. By applying powerful generative models such as flow-based models to reinforcement…

Generative policies based on expressive model classes, such as diffusion and flow matching, are well-suited to complex control problems with highly multimodal action distributions. Their expressivity, however, comes at a significant…

Learning robust visuomotor policies that generalize across diverse objects and interaction dynamics remains a central challenge in robotic manipulation. Most existing approaches rely on direct observation-to-action mappings or compress…

Guidance is a crucial technique for extracting the best performance out of image-generating diffusion models. Traditionally, a constant guidance weight has been applied throughout the sampling chain of an image. We show that guidance is…

Recent advances in reinforcement learning (RL) have achieved great successes by leveraging the multimodality and exploration capability of diffusion policies. Among these approaches, one representative branch focuses on the sampling-based…

Offline reinforcement learning (RL) recovers the optimal policy $\pi$ given historical observations of an agent. In practice, $\pi$ is modeled as a weighted version of the agent's behavior policy $\mu$, using a weight function $w$ working…

Diffusion policies have recently emerged as a powerful class of visuomotor controllers for robot manipulation, offering stable training and expressive multi-modal action modeling. However, existing approaches typically treat action…

Interactive decision-making is essential in applications such as autonomous driving, where the agent must infer the behavior of nearby human drivers while planning in real-time. Traditional predict-then-act frameworks are often insufficient…

Diffusion policies have achieved great success in online reinforcement learning (RL) due to their strong expressive capacity. However, the inference of diffusion policy models relies on a slow iterative sampling process, which limits their…

Many real-world machine learning tasks require outputs that satisfy hard constraints, such as physical conservation laws, structured dependencies in graphs, or column-level relationships in tabular data. Existing approaches rely either on…

We present a diffusion-based approach to quadrupedal locomotion that simultaneously addresses the limitations of learning and interpolating between multiple skills and of (modes) offline adapting to new locomotion behaviours after training.…

Prompt learning has demonstrated promising results in fine-tuning pre-trained multimodal models. However, the performance improvement is limited when applied to more complex and fine-grained tasks. The reason is that most existing methods…

Training general robotic policies from heterogeneous data for different tasks is a significant challenge. Existing robotic datasets vary in different modalities such as color, depth, tactile, and proprioceptive information, and collected in…

Diffusion guidance is a powerful technique that enables controllable and high-fidelity sample generation with diffusion models. At a high level, it modifies the score function by incorporating a guidance term that steers the generative…

Simultaneously grasping and delivering multiple objects can significantly enhance robotic work efficiency and has been a key research focus for decades. The primary challenge lies in determining how to push objects, group them, and execute…

Robotic manipulation policies are commonly initialized through imitation learning, but their performance is limited by the scarcity and narrow coverage of expert data. Reinforcement learning can refine polices to alleviate this limitation,…

Solving goal-oriented tasks is an important but challenging problem in reinforcement learning (RL). For such tasks, the rewards are often sparse, making it difficult to learn a policy effectively. To tackle this difficulty, we propose a new…