activity
20232026
most citedWhat Makes Quantization for Large Language Models Hard? An Empirical Study from the Lens of Perturbation

2 citations · 2 across the 17 of their papers we have counts for

collaborators
Showing cs.CLShow all

14 papers · 1 filter

cs.CL2026

Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models

Zihao Wei, Wenjie Shi, Liang Pang +8

Long-form chain-of-thought reasoning can improve LLM performance on complex tasks, but models often continue generating unnecessary reasoning after a correct answer has emerged. We…

cs.CL2025

The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis

Zihao Wei, Liang Pang, Jiahao Liu +7

Test-time scaling via explicit reasoning trajectories significantly boosts large language model (LLM) performance but often triggers overthinking. To explore this, we analyze reaso…

cs.CL2025

Libra: Assessing and Improving Reward Model by Learning to Think

Meng Zhou, Bei Li, Jiahao Liu +5

Reinforcement learning (RL) has significantly improved the reasoning ability of large language models. However, current reward models underperform in challenging reasoning scenario…

cs.CL2025

Dynamic Fisher-weighted Model Merging via Bayesian Optimization

Sanwoo Lee, Jiahao Liu, Qifan Wang +3

The fine-tuning of pre-trained language models has resulted in the widespread availability of task-specific models. Model merging offers an efficient way to create multi-task model…

cs.CL2024

Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning

Bei Li, Tong Zheng, Rui Wang +8

Residual networks, as discrete approximations of Ordinary Differential Equations (ODEs), have inspired significant advancements in neural network design, including multistep method…

cs.CL2024

FIRP: Faster LLM inference via future intermediate representation prediction

Pengfei Wu, Jiahao Liu, Zhuocheng Gong +5

Recent advancements in Large Language Models (LLMs) have shown remarkable performance across a wide range of tasks. Despite this, the auto-regressive nature of LLM decoding, which…