activity
20222024
most citedRPTQ: Reorder-based Post-training Quantization for Large Language Models

20 citations · 41 across the 9 of their papers we have counts for

collaborators

9 papers

cs.CL20244 cited

Enhancing Retrieval and Managing Retrieval: A Four-Module Synergy for Improved Quality and Efficiency in RAG Systems

Yunxiao Shi, Xing Zi, Zijing Shi +3

Retrieval-augmented generation (RAG) techniques leverage the in-context learning capabilities of large language models (LLMs) to produce more accurate and relevant responses. Origi…

physics.optics2024

All-optical polarization scrambler based on polarization beam splitting with amplified fiber ring

Yuanjie Yu, Shiyun Dai, Qiang Wu +6

Optical-fiber-based polarization scramblers can reduce the impact of polarization sensitive performance of various optical fiber systems. Here, we propose a simple and efficient po…

cs.LG20237 cited

PB-LLM: Partially Binarized Large Language Models

Yuzhang Shang, Zhihang Yuan, Qiang Wu +1

This paper explores network binarization, a radical form of quantization, compressing model weights to a single bit, specifically for Large Language Models (LLMs) compression. Due…

gr-qc20233 cited

Accretion disk around Reissner-Nordström black hole coupled with a nonlinear electrodynamics field

G. Abbas, H. Rehman, Tao Zhu +2

The phenomenon by which matter accumulates in the vicinity of a huge celestial object is known as accretion. The gravitational energy is excreted as a consequence of infalling matt…

physics.optics20231 cited

Robust Super-Resolution Imaging Based on a Ring Core Fiber with Orbital Angular Momentum

Zheyu Wu, Ran Gao, Sitong Zhou +8

Single fiber imaging technology offers unique insights for research and inspection in difficult to reach and narrow spaces. In particular, ultra-compact multimode fiber (MMF) imagi…

cs.CL202320 cited

RPTQ: Reorder-based Post-training Quantization for Large Language Models

Zhihang Yuan, Lin Niu, Jiawei Liu +7

Large-scale language models (LLMs) have demonstrated impressive performance, but their deployment presents challenges due to their significant memory usage. This issue can be allev…