Residual Context Diffusion
Collection
Residual Context Diffusion (RCD): Repurposing discarded signals as structured priors for high-performance reasoning in dLLMs. • 12 items • Updated • 2
Yuezhou Hu
yuezhouhu
AI & ML interests
My research interests include efficient machine learning, particularly efficient training and inference.
Recent Activity
upvoted a collection 19 days ago
Residual Context Diffusion upvoted a paper 2 months ago
Speculative Decoding for Autoregressive Video Generation submitted a paper 2 months ago
Speculative Decoding for Autoregressive Video GenerationOrganizations
upvoted a collection 19 days ago
upvoted a paper 2 months ago
upvoted 3
papers 4 months ago
V_1: Unifying Generation and Self-Verification for Parallel Reasoners
Paper • 2603.04304 • Published • 14
SLA2: Sparse-Linear Attention with Learnable Routing and QAT
Paper • 2602.12675 • Published • 59
SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
Paper • 2602.13515 • Published • 45
upvoted 3
papers 5 months ago
Residual Context Diffusion Language Models
Paper • 2601.22954 • Published • 36
Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization
Paper • 2602.02958 • Published • 34
Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow
Paper • 2601.14243 • Published • 24
upvoted 2
papers 7 months ago
upvoted a paper 8 months ago
upvoted a paper 9 months ago