1 citations · 1 across the 14 of their papers we have counts for
13 papers · 1 filter
Scaling Muon for Diffusion Transformers
Chenghao Li, Xiao Han, Xinxin Huang +22
The matrix-aware optimizer Muon improves large model training by balancing updates across singular directions, yet its scaling behavior and end-to-end efficiency on large Diffusion…
On-Policy Self-Distillation in Diffusion Models
Wei Zhou, Xiongwei Zhu, Lingdong Kong +14
Reinforcement learning can align diffusion models with human preferences and task-specific objectives, but endpoint rewards do not specify how an intermediate denoising prediction…
UNIFUSION: Adapting Autoregressive Language Models into Discrete Diffusion under a Unified Reverse-Rate Objective
Xiaoyi Jiang, Jingyuan Li, Yixuan Jiang +4
Existing methods mainly adapt pretrained autoregressive (AR) language models to masked diffusion, whereas we directly adapt them to uniform-noise diffusion, where every token remai…
Mean-to-Score Discrete Diffusion: Posterior-Mean Denoisers for Score Entropy
Jingyuan Li, Xiaoyi Jiang, Yixuan Jiang +4
Score Entropy Discrete Diffusion (SEDD) parameterizes discrete reverse processes with unconstrained positive score ratios. While positivity guarantees nonnegative reverse jump rate…
Through the PRISM: Preference Representation in Intermediate States of Video Diffusion Models
Haoxuan Wu, Lai Man Po, Mengyang Liu +3
Video reward models are central to aligning video diffusion models with human preferences, yet existing ones are external vision-language models that score clean, decoded pixels. S…
DanceOPD: On-Policy Generative Field Distillation
Wei Zhou, Xiongwei Zhu, Zelin Xu +8
Modern image generation demands a single model that unifies diverse capabilities, including text-to-image (T2I), local editing, and global editing. However, these capabilities are…
Neural Continuous-Time Markov Chain: Discrete Diffusion via Decoupled Jump Timing and Direction
Jingyuan Li, Xiaoyi Jiang, Fukang Wen +5
Discrete diffusion models based on continuous-time Markov chains (CTMCs) have shown strong performance on language and discrete data generation, yet existing approaches typically p…
Seedance 2.0: Advancing Video Generation for World Complexity
Team Seedance, De Chen, Liyang Chen +168
Seedance 2.0 is a new native multi-modal audio-video generation model, officially released in China in early February 2026. Compared with its predecessors, Seedance 1.0 and 1.5 Pro…
SEED: A Large-Scale Benchmark for Provenance Tracing in Sequential Deepfake Facial Edits
Mengieong Hoi, Zhedong Zheng, Ping Liu +1
Deepfake content on social networks is increasingly produced through multiple \emph{sequential} edits to biometric data such as facial imagery. Consequently, the final appearance o…
LoDAdaC: a unified local training-based decentralized framework with adaptive gradients and compressed communication
Wei Liu, Anweshit Panda, Ujwal Pandey +5
In the decentralized distributed learning, achieving fast convergence and low communication cost is essential for scalability and high efficiency. Adaptive gradient methods, such a…
JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency
Aichen Cai, Anmeng Zhang, Anyu Li +66
We introduce JoyAI-LLM Flash, an efficient Mixture-of-Experts (MoE) language model designed to redefine the trade-off between strong performance and token efficiency in the sub-50B…
Vision-Guided Iterative Refinement for Frontend Code Generation
Hannah Sansford, Derek H. C. Law, Wei Liu +3
Code generation with large language models often relies on multi-stage human-in-the-loop refinement, which is effective but very costly - particularly in domains such as frontend w…
Draft-and-Target Sampling for Video Generation Policy
Qikang Zhang, Yingjie Lei, Wei Liu +1
Video generation models have been used as a robot policy to predict the future states of executing a task conditioned on task description and observation. Previous works ignore the…