arxiv:2508.05731
Congkai Xie
congkai
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 days ago
Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation upvoted a paper 14 days ago
OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond upvoted a paper 18 days ago
DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM InferenceOrganizations
