6 papers
LLaDA MoE v2: Scaling Mixture-of-Experts Diffusion Language Models
Fengqi Zhu, Shaoxuan Xu, Jingyang Ou +11
Diffusion language models (dLLMs) offer an alternative to autoregressive (AR) language modeling, yet the scaling behavior of Mixture-of-Experts (MoE) dLLMs remains poorly understoo…
Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data
Jingyang Ou, Shen Nie, Kaiwen Xue +4
Discrete diffusion models with absorbing processes have shown promise in language modeling. The key quantities to be estimated are the ratios between the marginal probabilities of…
Effective and Efficient Masked Image Generation Models
Zebin You, Jingyang Ou, Xiaolu Zhang +3
Although masked image generation models and masked diffusion models are designed with different motivations and objectives, we observe that they can be unified within a single fram…
DLLM-Searcher: Adapting Diffusion Large Language Model for Search Agents
Jiahao Zhao, Shaoxuan Xu, Zhongxiang Sun +6
Recently, Diffusion Large Language Models (dLLMs) have demonstrated unique efficiency advantages, enabled by their inherently parallel decoding mechanism and flexible generation pa…
Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective
Jingyang Ou, Jiaqi Han, Minkai Xu +5
Reinforcement Learning (RL) has proven highly effective for autoregressive language models, but adapting these methods to diffusion large language models (dLLMs) presents fundament…
Large Language Diffusion Models
Shen Nie, Fengqi Zhu, Zebin You +7
The capabilities of large language models (LLMs) are widely regarded as relying on autoregressive models (ARMs). We challenge this notion by introducing LLaDA, a diffusion model tr…