4 papers
UCPO: Uncertainty-Aware Policy Optimization
Xianzhou Zeng, Jing Huang, Chunmei Xie +9
The key to building trustworthy large language models (LLMs) lies in endowing them with inherent uncertainty expression capabilities, thereby mitigating overconfident errors in hig…
HiFloat4 Format for Language Model Inference
Yuanyong Luo, Jing Huang, Yu Cheng +19
This paper introduces HiFloat4 (HiF4), a block floating-point data format tailored for deep learning. Each HiF4 unit packs 64 4-bit elements with 32 bits of shared scaling metadata…
Diffusion Epistemic Uncertainty with Asymmetric Learning for Diffusion-Generated Image Detection
Yingsong Huang, Hui Guo, Jing Huang +2
The rapid progress of diffusion models highlights the growing need for detecting generated images. Previous research demonstrates that incorporating diffusion-based measurements, s…
NGRPO: Negative-enhanced Group Relative Policy Optimization
Gongrui Nan, Siye Chen, Jing Huang +8
RLVR has enhanced the reasoning capabilities of Large Language Models (LLMs) across various tasks. However, GRPO, a representative RLVR algorithm, suffers from a critical limitatio…