works on
gpu acceleration 1hardware-software co-design 1n:m sparsity 1sparse inference 1vision transformers 1

From the 1 of 8 linked papers with an AI index.

activity
20242026
collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

Crystal-KV: Efficient KV Cache Management for Chain-of-Thought LLMs via Answer-First Principle

Zihan Wang, Cheng Tang, Lei Gong +5

Chain-of-Thought (CoT) reasoning in large language models (LLMs) significantly improves accuracy on complex tasks, yet incurs excessive memory overhead due to the long think-stage…