Residual Context Diffusion (RCD): Repurposing discarded signals as structured priors for high-performance reasoning in dLLMs.
Yuezhou Hu
yuezhouhu
AI & ML interests
My research interests include efficient machine learning, particularly efficient training and inference.
Recent Activity
upvoted a paper 1 day ago
FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution upvoted a collection 3 months ago
Residual Context Diffusion upvoted a paper 4 months ago
Speculative Decoding for Autoregressive Video GenerationOrganizations
models 12
yuezhouhu/RCD-LLaDA-8B-Instruct
1B • Updated • 9
yuezhouhu/SeqD-LLaDA-8B-Instruct
1B • Updated • 10
yuezhouhu/RCD-SDAR-8B-b64-Thinking
8B • Updated • 8
yuezhouhu/RCD-SDAR-8B-b32-Thinking
8B • Updated • 12
yuezhouhu/RCD-SDAR-4B-b64-Thinking
4B • Updated • 17
yuezhouhu/RCD-SDAR-4B-b32-Thinking
4B • Updated • 7
yuezhouhu/SeqD-SDAR-8B-b64-Thinking
8B • Updated • 9
yuezhouhu/SeqD-SDAR-8B-b32-Thinking
8B • Updated • 7
yuezhouhu/SeqD-SDAR-4B-b64-Thinking
4B • Updated • 5
yuezhouhu/SeqD-SDAR-4B-b32-Thinking
4B • Updated • 7
datasets 0
None public yet