-
InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU
Paper • 2502.08910 • Published • 148 -
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
Paper • 2502.06703 • Published • 153 -
The Curse of Depth in Large Language Models
Paper • 2502.05795 • Published • 40
Shenxin Li
Adinosaur
·
AI & ML interests
None yet
Organizations
-
InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU
Paper • 2502.08910 • Published • 148 -
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
Paper • 2502.06703 • Published • 153 -
The Curse of Depth in Large Language Models
Paper • 2502.05795 • Published • 40