activity
20222026
most citedMaximum Likelihood Training for Score-Based Diffusion ODEs by High-Order Denoising Score Matching

11 citations · 27 across the 32 of their papers we have counts for

collaborators
Showing cs.LGShow all

12 papers · 1 filter

cs.LG2026

SLA2: Sparse-Linear Attention with Learnable Routing and QAT

Jintao Zhang, Haoxu Wang, Kai Jiang +6

Sparse-Linear Attention (SLA) combines sparse and linear attention to accelerate diffusion models and has shown strong performance in video generation. However, (i) SLA relies on a…

cs.LG2025

Data-regularized Reinforcement Learning for Diffusion Models at Scale

Haotian Ye, Kaiwen Zheng, Jiashu Xu +15

Aligning generative diffusion models with human preferences via reinforcement learning (RL) is critical yet challenging. Most existing algorithms are often vulnerable to reward hac…

cs.LG2025

SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention

Jintao Zhang, Haoxu Wang, Kai Jiang +10

In Diffusion Transformer (DiT) models, particularly for video generation, attention latency is a major bottleneck due to the long sequence length and the quadratic complexity. We f…

cs.LG2025

DiffusionNFT: Online Diffusion Reinforcement with Forward Process

Kaiwen Zheng, Huayu Chen, Haotian Ye +7

Online reinforcement learning (RL) has been central to post-training language models, but its extension to diffusion models remains challenging due to intractable likelihoods. Rece…

cs.LG2025

NFT: Bridging Supervised Learning and Reinforcement Learning in Math Reasoning

Huayu Chen, Kaiwen Zheng, Qinsheng Zhang +8

Reinforcement Learning (RL) has played a central role in the recent surge of LLMs' math abilities by enabling self-improvement through binary verifier signals. In contrast, Supervi…

cs.LG2025

Elucidating the Preconditioning in Consistency Distillation

Kaiwen Zheng, Guande He, Jianfei Chen +2

Consistency distillation is a prevalent way for accelerating diffusion models adopted in consistency (trajectory) models, in which a student model is trained to traverse backward o…