12 papers · 1 filter
Reflected Proximal Dynamics for Accelerated High-Accuracy Log-Concave Sampling
Bo Yuan, Wei Guo, Yongxin Chen
We study sampling from on , where is -strongly convex and -smooth with condition number . For this problem, the proxi…
LongTake: Learning to Sustain Dynamics in Long-Horizon Video Generation
Byoungwoo Park, Jaemoo Choi, Juho Lee +1
World models, game simulators, and long-take video creation require coherent scene evolution and sustained dynamics over extended durations. Autoregressive (AR) video diffusion pro…
Scaling Reinforcement Learning for Diffusion Models via Velocity Matching
Jaemoo Choi, Wei Guo, Yuchen Zhu +4
Reward-based fine-tuning of diffusion models has largely inherited likelihood-based policy optimization developed for autoregressive large language models (LLMs). Diffusion models,…
FLARE: Diffusion for Hybrid Language Model
Yuchen Zhu, Jing Shi, Chongjian Ge +9
Autoregressive (AR) large language models (LLMs) have achieved broad practical success, but sequential decoding remains a key bottleneck for low-latency deployment. Recent efficien…
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: Context-Orchestrated Research Math Agents
Zelin Zhao, Bo Yuan, Yuchen Zhu +2
Long-horizon mathematical reasoning fails less often because a model cannot produce a valid next step than because an agent fails to maintain and expose the right semantic state ac…
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…
Efficient Adjoint Matching for Fine-tuning Diffusion Models
Jeongwoo Shin, Dongsoo Shin, Yuchen Zhu +5
Reward fine-tuning has become a common approach for aligning pretrained diffusion and flow models with human preferences in text-to-image generation. Among reward-gradient-based me…
Continuous Diffusion Scales Competitively with Discrete Diffusion for Language
Zhihan Yang, Wei Guo, Shuibai Zhang +5
While diffusion has drawn considerable recent attention from the language modeling community, continuous diffusion has appeared less scalable than discrete approaches. To challenge…
Discrete Adjoint Schrödinger Bridge Sampler
Wei Guo, Yuchen Zhu, Xiaochen Du +6
Learning discrete neural samplers is challenging due to the lack of gradients and combinatorial complexity. While stochastic optimal control (SOC) and Schrödinger bridge (SB) provi…
LaViDa-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Models
Shufan Li, Yuchen Zhu, Jiuxiang Gu +6
Diffusion language models (dLLMs) recently emerged as a promising alternative to auto-regressive LLMs. The latest works further extended it to multimodal understanding and generati…
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…