1 citations · 1 across the 7 of their papers we have counts for
7 papers
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…
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…
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-…
LoRETTA: Low-Rank Economic Tensor-Train Adaptation for Ultra-Low-Parameter Fine-Tuning of Large Language Models
Yifan Yang, Jiajun Zhou, Ngai Wong +1
Various parameter-efficient fine-tuning (PEFT) techniques have been proposed to enable computationally efficient fine-tuning while maintaining model performance. However, existing…
A Unifying Tensor View for Lightweight CNNs
Jason Chun Lok Li, Rui Lin, Jiajun Zhou +2
Despite the decomposition of convolutional kernels for lightweight CNNs being well studied, existing works that rely on tensor network diagrams or hyperdimensional abstraction lack…
Hundred-Kilobyte Lookup Tables for Efficient Single-Image Super-Resolution
Binxiao Huang, Jason Chun Lok Li, Jie Ran +4
Conventional super-resolution (SR) schemes make heavy use of convolutional neural networks (CNNs), which involve intensive multiply-accumulate (MAC) operations, and require special…
Lite it fly: An All-Deformable-Butterfly Network
Rui Lin, Jason Chun Lok Li, Jiajun Zhou +3
Most deep neural networks (DNNs) consist fundamentally of convolutional and/or fully connected layers, wherein the linear transform can be cast as the product between a filter matr…