activity
20232026
collaborators

10 papers

cs.CL2026

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

Shih-Yang Liu, Xin Dong, Ximing Lu +10

As language models become increasingly capable, users expect them to provide not only accurate responses but also behaviors aligned with diverse human preferences across a variety…

cs.LG2025

DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning

Shih-Yang Liu, Xin Dong, Ximing Lu +9

Reasoning language models such as OpenAI-o1, DeepSeek-R1, and Qwen achieve strong performance via extended chains of thought but often generate unnecessarily long outputs. Maximizi…

cs.CV2024

SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training

Dongting Hu, Jierun Chen, Xijie Huang +16

Existing text-to-image (T2I) diffusion models face several limitations, including large model sizes, slow runtime, and low-quality generation on mobile devices. This paper aims to…

cs.CL2024

EoRA: Fine-tuning-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation

Shih-Yang Liu, Maksim Khadkevich, Nai Chit Fung +10

While post-training compression techniques effectively reduce the memory footprint, latency, and power consumption of Large Language Models (LLMs), they often result in noticeable…

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.LG2024

Genetic Quantization-Aware Approximation for Non-Linear Operations in Transformers

Pingcheng Dong, Yonghao Tan, Dong Zhang +11

Non-linear functions are prevalent in Transformers and their lightweight variants, incurring substantial and frequently underestimated hardware costs. Previous state-of-the-art wor…