Adapters and trajectory artifacts for matched-compute PRM guidance and ORM reranking in discrete diffusion reasoning.
🔄 In a Training Loop
Yan Zhan
YanZhanPKU
·
AI & ML interests
LLM
Recent Activity
liked a dataset about 9 hours ago
YanZhanPKU/dLLM-PRM-Gap-Datasets liked a model about 9 hours ago
YanZhanPKU/dLLM-PRM-Gap-c3a-causal-lasttoken-dream7b-s42 liked a model about 9 hours ago
YanZhanPKU/dLLM-PRM-Gap-c3a-causal-lasttoken-dream7b-s43Organizations
None yet
Training-free length selection for masked diffusion MT (EMNLP 2026). Code: github.com/Entropy-Valley/Entropy-Valley
-
Length-Adaptive Decoding for Masked Diffusion Machine Translation
Paper • 2608.22274 • Published • 4 -
YanZhanPKU/Entropy-Valley-LLaDA-8B-En2Zh
Translation • Updated • 13 • 2 -
YanZhanPKU/Entropy-Valley-LLaDA-8B-Zh2En
Translation • Updated • 11 • 1 -
YanZhanPKU/Entropy-Valley-LLaDA-8B-En2De
Translation • Updated • 11 • 1
Adapters and trajectory artifacts for matched-compute PRM guidance and ORM reranking in discrete diffusion reasoning.
Segment-Locked Credit Assignment for tool-calling RL — processed data splits and the reference implementation.
Training-free length selection for masked diffusion MT (EMNLP 2026). Code: github.com/Entropy-Valley/Entropy-Valley
-
Length-Adaptive Decoding for Masked Diffusion Machine Translation
Paper • 2608.22274 • Published • 4 -
YanZhanPKU/Entropy-Valley-LLaDA-8B-En2Zh
Translation • Updated • 13 • 2 -
YanZhanPKU/Entropy-Valley-LLaDA-8B-Zh2En
Translation • Updated • 11 • 1 -
YanZhanPKU/Entropy-Valley-LLaDA-8B-En2De
Translation • Updated • 11 • 1