8 papers
MSSR: Memory-Aware Adaptive Replay for Continual LLM Fine-Tuning
Yiyang Lu, Yu He, Jianlong Chen +1
Continual fine-tuning of large language models (LLMs) is becoming increasingly crucial as these models are deployed in dynamic environments where tasks and data distributions evolv…
Calibrating Tabular Anomaly Detection via Optimal Transport
Hangting Ye, He Zhao, Wei Fan +4
Tabular anomaly detection (TAD) remains challenging due to the heterogeneity of tabular data: features lack natural relationships, vary widely in distribution and scale, and exhibi…
Safeguarding LLM Fine-tuning via Push-Pull Distributional Alignment
Haozhong Wang, Zhuo Li, Yibo Yang +3
The inherent safety alignment of Large Language Models (LLMs) is prone to erosion during fine-tuning, even when using seemingly innocuous datasets. While existing defenses attempt…
Milestones over Outcome: Unlocking Geometric Reasoning with Sub-Goal Verifiable Reward
Jianlong Chen, Daocheng Fu, Shengze Xu +6
Multimodal Large Language Models (MLLMs) struggle with complex geometric reasoning, largely because "black box" outcome-based supervision fails to distinguish between lucky guesses…
LLM as an Algorithmist: Enhancing Anomaly Detectors via Programmatic Synthesis
Hangting Ye, Jinmeng Li, He Zhao +4
Existing anomaly detection (AD) methods for tabular data usually rely on some assumptions about anomaly patterns, leading to inconsistent performance in real-world scenarios. While…
Balancing Two Classifiers via A Simplex ETF Structure for Model Calibration
Jiani Ni, He Zhao, Jintong Gao +2
In recent years, deep neural networks (DNNs) have demonstrated state-of-the-art performance across various domains. However, despite their success, they often face calibration issu…