Posts by Collection

Yaoyuan Liang*, Zhuojun Cai*, Xu Jian, Guanbo Huang, Yiran Wang, Xiao Liang, Jiahao Liu, Ziran Li, Jingang Wang, Jingang Wang, Shao-Lun Huang†

This work proposes a training-free framework, named as ``unleash-then-eliminate’’, which first elicits the latent information in the intermediate layers, and then adopts a cycle-consistency-based decoding method to alleviate the production of hallucinations.

Qingyue Zhang*, Haohao Fu*, Guanbo Huang*, Yaoyuan Liang, Chang Chu, Tianren Peng, Yanru Wu, Qi Li, Yang Li†, Shao-Lun Huang†

This work calculates the optimal training data quantity to sample from various source tasks into target task under transfer learning, based on Fisher Information theory.

Fanding Huang*, Guanbo Huang*, Xiao Fan, Yi He, Xiao Liang, Xiao Chen, Qinting Jiang, Faisal Nadeem Khan, Jingyan Jiang†, Zhi Wang†

This work is the first to analyze the hidden state dynamics for Reinforcement Learning in LLM reasoning.

Guanbo Huang*, Jingjia Mao*, Fanding Huang*, Fengkai Liu, Xiangyang Luo, Yaoyuan Liang, Jiasheng Lu, Xiaoe Wang, Pei Liu, Ruiliu Fu†, Shao-Lun Huang†

This work proposes a learning target for Anti-Drift Rectification and a dynamic reweighting loss for Frequency Compensation to alleviate exposure bias.