6 accepted papers
Guidance methods, e.g., classifier-free guidance (CFG) and auto-guidance (AG), have distinctively improved noise-to-data diffusion generation results. Recently, bridge models have been proposed, which present a data-to-data sampling process to exploit instructive information from clean prior represe…
Mean Field Games (MFGs) provide a principled framework for modeling interactions in large populations models: at scale, population dynamics become deterministic, with uncertainty entering only through aggregate shocks, or *common noise*. However, algorithmic progress has been limited since model-fre…
Practical reinforcement learning (RL) usually requires agents to be optimized for multiple potentially conflicting criteria, e.g. speed vs. safety. Although Multi-Objective RL (MORL) algorithms have been studied in previous works, their trained agents often cover limited Pareto optimal solutions an…
Unsupervised reinforcement learning (URL) aims to learn general skills for unseen downstream tasks. Mutual Information Skill Learning (MISL) addresses URL by maximizing the mutual information between states and skills but lacks sufficient theoretical analysis, e.g., how well its learned skills can i…
Universal domain adaptation (UniDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain without requiring the same label sets of both domains. The existence of domain and category shift makes the task challenging and requires us to distinguish “known” samples (i.e.,…
Existing Optimal Transport (OT) methods mainly derive the optimal transport plan/matching under the criterion of transport cost/distance minimization, which may cause incorrect matching in some cases. In many applications, annotating a few matched keypoints across domains is reasonable or even effor…