collaborators

9 papers

cs.LG2026

Margin-Adaptive Confidence Ranking for Reliable LLM Judgement

Gaojie Jin, Yong Tao, Lijia Yu +1

Jung et al. (2025) introduce a hypothesis testing framework for guaranteeing agreement between large language models (LLMs) and human judgments, relying on the assumption that the…

cs.LG2026

OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents

Xinyu Li, Ronghui Mu, Lin Li +2

Large Language Models (LLMs) are increasingly deployed as autonomous agents that execute tool-augmented, multi-step tasks, where latency is a critical factor for real-world applica…

cs.LG2026

GradientStabilizer:Fix the Norm, Not the Gradient

Tianjin Huang, Zhangyang Wang, Haotian Hu +10

Training instability in modern deep learning systems is frequently triggered by rare but extreme gradient-norm spikes, which can induce oversized parameter updates, corrupt optimiz…

cs.LG2025

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization

Xinyu Li, Tianjin Huang, Ronghui Mu +2

Recent advances in Chain-of-Thought (CoT) prompting have substantially enhanced the reasoning capabilities of large language models (LLMs), enabling sophisticated problem-solving t…

cs.LG2025

LOST: Low-rank and Sparse Pre-training for Large Language Models

Jiaxi Li, Lu Yin, Li Shen +6

While large language models (LLMs) have achieved remarkable performance across a wide range of tasks, their massive scale incurs prohibitive computational and memory costs for pre-…

cs.LG2025

Principal Eigenvalue Regularization for Improved Worst-Class Certified Robustness of Smoothed Classifiers

Gaojie Jin, Tianjin Huang, Ronghui Mu +1

Recent studies have identified a critical challenge in deep neural networks (DNNs) known as ``robust fairness", where models exhibit significant disparities in robust accuracy acro…