activity
20222024
most citedMiniGPT-v2: large language model as a unified interface for vision-language multi-task learning

67 citations · 95 across the 7 of their papers we have counts for

collaborators

7 papers

cs.CL2024

RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization

Xijie Huang, Zechun Liu, Shih-Yang Liu +1

Low-Rank Adaptation (LoRA), as a representative Parameter-Efficient Fine-Tuning (PEFT)method, significantly enhances the training efficiency by updating only a small portion of the…

cs.CV202367 cited

MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning

Jun Chen, Deyao Zhu, Xiaoqian Shen +7

Large language models have shown their remarkable capabilities as a general interface for various language-related applications. Motivated by this, we target to build a unified int…

cs.SD20231 cited

On The Open Prompt Challenge In Conditional Audio Generation

Ernie Chang, Sidd Srinivasan, Mahi Luthra +8

Text-to-audio generation (TTA) produces audio from a text description, learning from pairs of audio samples and hand-annotated text. However, commercializing audio generation is ch…

cs.CL20231 cited

Binary and Ternary Natural Language Generation

Zechun Liu, Barlas Oguz, Aasish Pappu +2

Ternary and binary neural networks enable multiplication-free computation and promise multiple orders of magnitude efficiency gains over full-precision networks if implemented on s…

cs.CL202315 cited

LLM-QAT: Data-Free Quantization Aware Training for Large Language Models

Zechun Liu, Barlas Oguz, Changsheng Zhao +6

Several post-training quantization methods have been applied to large language models (LLMs), and have been shown to perform well down to 8-bits. We find that these methods break d…

cs.LG20228 cited

SDQ: Stochastic Differentiable Quantization with Mixed Precision

Xijie Huang, Zhiqiang Shen, Shichao Li +5

In order to deploy deep models in a computationally efficient manner, model quantization approaches have been frequently used. In addition, as new hardware that supports mixed bitw…