Related papers: Uni-Skill: Building Self-Evolving Skill Repository…

Learning diverse skills is one of the main challenges in robotics. To this end, imitation learning approaches have achieved impressive results. These methods require explicitly labeled datasets or assume consistent skill execution to enable…

Shared-autonomy imitation learning lets a human correct a robot in real time, mitigating covariate-shift errors. Yet existing approaches ignore two critical factors: (i) the operator's cognitive load and (ii) the risk created by delayed or…

We present Unified Latent Dynamics (ULD), a novel reinforcement learning algorithm that unifies the efficiency of model-free methods with the representational strengths of model-based approaches, without incurring planning overhead. By…

Generalizing from individual skill executions to solving long-horizon tasks remains a core challenge in building autonomous agents. A promising direction is learning high-level, symbolic abstractions of the low-level skills of the agents,…

Biological intelligence systems of animals perceive the world by integrating information in different modalities and processing simultaneously for various tasks. In contrast, current machine learning research follows a task-specific…

Federated Learning (FL) often suffers from severe performance degradation when faced with non-IID data, largely due to local classifier bias. Traditional remedies such as global model regularization or layer freezing either incur high…

Robots deployed in many real-world settings need to be able to acquire new skills and solve new tasks over time. Prior works on planning with skills often make assumptions on the structure of skills and tasks, such as subgoal skills, shared…

Zero-shot reinforcement learning (RL) has emerged as a setting for developing general agents, capable of solving downstream tasks without additional training or planning at test-time. While conventional RL optimizes policies for fixed…

Unified multimodal models aim to jointly enable visual understanding and generation, yet current benchmarks rarely examine their true integration. Existing evaluations either treat the two abilities in isolation or overlook tasks that…

Generating natural and physically plausible character motion remains challenging, particularly for long-horizon control with diverse guidance signals. While prior work combines high-level diffusion-based motion planners with low-level…

In AI-facilitated teaching, leveraging various query styles to interpret abstract text descriptions is crucial for ensuring high-quality teaching. However, current retrieval models primarily focus on natural text-image retrieval, making…

Long-horizon tasks, usually characterized by complex subtask dependencies, present a significant challenge in manipulation planning. Skill chaining is a practical approach to solving unseen tasks by combining learned skill priors. However,…

Modern LLMs show mastery over an ever-growing range of skills, as well as the ability to compose them flexibly. However, extending model capabilities to new skills in a scalable manner is an open problem: fine-tuning and parameter-efficient…

In-context Learning enables training-free adaptation via demonstrations but remains highly sensitive to example selection and formatting. In unified multimodal models spanning understanding and generation, this sensitivity is exacerbated by…

Reinforcement learning necessitates meticulous reward shaping by specialists to elicit target behaviors, while imitation learning relies on costly task-specific data. In contrast, unsupervised skill discovery can potentially reduce these…

List-wise reranking arranges a request-specific pool of candidate items into an ordered slate that maximizes user satisfaction. Existing generative rerankers fall into two paradigms: Autoregressive (AR) rerankers construct the slate left to…

Significant advancements has recently been achieved in the field of multi-modal large language models (MLLMs), demonstrating their remarkable capabilities in understanding and reasoning across diverse tasks. However, these models are often…

Recent advancements in whole-body control through deep reinforcement learning have enabled humanoid robots to achieve remarkable progress in real-world chal lenging locomotion skills. However, existing approaches often struggle with…

Most existing vision-language pre-training methods focus on understanding tasks and use BERT-like objectives (masked language modeling and image-text matching) during pretraining. Although they perform well in many understanding downstream…

This paper develops a hierarchical learning and optimization framework that can learn and achieve well-coordinated multi-skill locomotion. The learned multi-skill policy can switch between skills automatically and naturally in tracking…