Search Results for author:
Found 2 papers, 1 papers with code
R-KV: Redundancy-aware KV Cache Compression for Training-Free Reasoning Models Acceleration
To address this, we propose Redundancy-aware KV Cache Compression for Reasoning models (R-KV), a novel method specifically targeting redundant tokens in reasoning models.
Entropy-based Exploration Conduction for Multi-step Reasoning
In large language model (LLM) reasoning, multi-step processes have proven effective for solving complex tasks.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
