ginda307
- Karma
- 0
- Created
- ()
- Submissions
- 36,551
- CAD: Disaggregating Core Attention for Efficient Long-Context LLM Training (hao-ai-lab.github.io)
- Disaggregated Inference: 18 Months Later (hao-ai-lab.github.io)
- Reasoning Without Hesitating: Efficient Cot Through Certainty Probing (hao-ai-lab.github.io)