3 papers
stat.ML2026
AIS: Adaptive Importance Sampling for Quantized RL
Jiajun Zhou, Wei Shao, Lingchao Zheng +2
Reinforcement learning (RL) for large language models (LLMs) is dominated by the cost of rollout generation, which has motivated the use of low-precision rollouts (e.g., FP8) paire…
cs.AR2025
A Time- and Energy-Efficient CNN with Dense Connections on Memristor-Based Chips
Wenyong Zhou, Yuan Ren, Jiajun Zhou +2
Designing lightweight convolutional neural network (CNN) models is an active research area in edge AI. Compute-in-memory (CIM) provides a new computing paradigm to alleviate time a…
cs.LG2025
QuZO: Quantized Zeroth-Order Fine-Tuning for Large Language Models
Jiajun Zhou, Yifan Yang, Kai Zhen +6
Language Models (LLMs) are often quantized to lower precision to reduce the memory cost and latency in inference. However, quantization often degrades model performance, thus fine-…