13 papers
Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization
Yuchen Zhu, Wei Guo, Jaemoo Choi +4
Diffusion large language models (dLLMs) are promising alternatives to autoregressive large language models (AR-LLMs), as they potentially allow higher inference throughput. Reinfor…
Generalized Schrödinger Bridge on Graphs
Panagiotis Theodoropoulos, Juno Nam, Evangelos Theodorou +1
Transportation on graphs is a fundamental challenge across many domains, where decisions must respect topological and operational constraints. Despite the need for actionable polic…
Coarse-to-Fine Compositional Diffusion for Long-Horizon Planning
Byoungwoo Park, Utkarsh A. Mishra, Jaemoo Choi +2
Diffusion models provide strong priors for generating structured data, but many tasks require outputs beyond the scale on which these models are typically trained. Compositional ge…
RMA: an Agentic System for Research-Level Mathematical Problems
Zelin Zhao, Bo Yuan, Jaemoo Choi +1
We present , an agentic framework for automated reasoning on research-level mathematical problems. Unlike prior studies centered on competition…
MetaDNS: Enhancing Exploration in Discrete Neural Samplers via Well-Tempered Metadynamics
Xiaochen Du, Juno Nam, Jaemoo Choi +7
Sampling from discrete distributions with multiple modes and energy barriers is fundamental to machine learning and computational physics. Recent discrete neural samplers like MDNS…
Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design
Jaemoo Choi, Yuchen Zhu, Wei Guo +6
Reinforcement learning has been widely applied to diffusion and flow models for visual tasks such as text-to-image generation. However, these tasks remain challenging because diffu…