5 citations · 11 across the 17 of their papers we have counts for
9 papers · 1 filter
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…
InfoTok: Adaptive Discrete Video Tokenizer via Information-Theoretic Compression
Haotian Ye, Qiyuan He, Jiaqi Han +12
Accurate and efficient discrete video tokenization is essential for long video sequences processing. Yet, the inherent complexity and variable information density of videos present…
Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency
Kaiwen Zheng, Yuji Wang, Qianli Ma +7
Although continuous-time consistency models (e.g., sCM, MeanFlow) are theoretically principled and empirically powerful for fast academic-scale diffusion, its applicability to larg…
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…
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…
Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning
NVIDIA, :, Alisson Azzolini +51
Physical AI systems need to perceive, understand, and perform complex actions in the physical world. In this paper, we present the Cosmos-Reason1 models that can understand the phy…
Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator
Kaiwen Zheng, Yongxin Chen, Huayu Chen +4
While likelihood-based generative models, particularly diffusion and autoregressive models, have achieved remarkable fidelity in visual generation, the maximum likelihood estimatio…
Exploratory Diffusion Model for Unsupervised Reinforcement Learning
Chengyang Ying, Huayu Chen, Xinning Zhou +3
Unsupervised reinforcement learning (URL) aims to pre-train agents by exploring diverse states or skills in reward-free environments, facilitating efficient adaptation to downstrea…
Visual Generation Without Guidance
Huayu Chen, Kai Jiang, Kaiwen Zheng +3
Classifier-Free Guidance (CFG) has been a default technique in various visual generative models, yet it requires inference from both conditional and unconditional models during sam…