14 papers
Interpretable but Fragile? Robustness of Concept Bottlenecks under Geometric-Semantic Perturbations
Hanwei Zhang, Tianma Hu, Gaojie Jin +2
Concept Bottleneck Models (CBMs) are designed to provide interpretable intermediate representations, yet how such bottlenecks affect robustness remains unclear, with existing studi…
Localize-Then-Decide Guarantees for LLM Judgments
Xinyu Li, Yi Zhou, Guanqun Cao +3
Large language models (LLMs) are increasingly used as evaluators to assess output quality and preference alignment, yet providing reliable guarantees of agreement with human judgme…
CPR: Chained Perceptual Refinement for Coarse-to-Fine Medical Image Classification
Si-Yuan Lu, Hanruo Zhu, Ziquan Zhu +6
High resolution medical images contain fine grained, spatially sparse cues that are critical for diagnosis, yet preserving full resolution incurs substantial computational and memo…
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…
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…
Confusion-Aware Spectral Regularizer for Long-Tailed Recognition
Ziquan Zhu, Gaojie Jin, Hanruo Zhu +11
Long-tailed image classification remains a long-standing challenge, as real-world data typically follow highly imbalanced distributions where a few head classes dominate and many t…
Dual-Kernel Adapter: Expanding Spatial Horizons for Data-Constrained Medical Image Analysis
Ziquan Zhu, Hanruo Zhu, Siyuan Lu +8
Adapters have become a widely adopted strategy for efficient fine-tuning of large pretrained models, particularly in resource-constrained settings. However, their performance under…
StealthMark: Harmless and Stealthy Ownership Verification for Medical Segmentation via Uncertainty-Guided Backdoors
Qinkai Yu, Chong Zhang, Gaojie Jin +11
Annotating medical data for training AI models is often costly and limited due to the shortage of specialists with relevant clinical expertise. This challenge is further compounded…
CluCERT: Certifying LLM Robustness via Clustering-Guided Denoising Smoothing
Zixia Wang, Gaojie Jin, Jia Hu +1
Recent advancements in Large Language Models (LLMs) have led to their widespread adoption in daily applications. Despite their impressive capabilities, they remain vulnerable to ad…
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…
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…
SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training
Tianjin Huang, Ziquan Zhu, Gaojie Jin +3
Large Language Models (LLMs) have demonstrated exceptional performance across diverse tasks, yet their training remains highly resource-intensive and susceptible to critical challe…
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…
Enhancing Robust Fairness via Confusional Spectral Regularization
Gaojie Jin, Sihao Wu, Jiaxu Liu +2
Recent research has highlighted a critical issue known as ``robust fairness", where robust accuracy varies significantly across different classes, undermining the reliability of de…