Keyue Jiang
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1AI×1
Frequent co-authors
Research Timeline
2026
GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models
The paper proposes Guided Denoiser Self-Distillation (GDSD), a novel method that bypasses the use of likelihood surrogates (like ELBO) in RL for diffusion language models, achieving state-of-the-art performance on complex benchmarks.
Highlighted terms show continued research focus across papers
Papers
cs.LGcs.AIRecentMay 28, 2026
GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models
Xiaohang Tang, Keyue Jiang, Che Liu, Qifang Zhao +3 more
The paper proposes Guided Denoiser Self-Distillation (GDSD), a novel method that bypasses the use of likelihood surrogates (like ELBO) in RL for diffusion language models, achieving state-of-the-art p…
View →