9 papers
Se-DPO: Self-Evolving Token Credit for Direct Preference Optimization
Wenxiao Zhao, Shu Wang, Ying Nian Wu
Direct Preference Optimization (DPO) aggregates token-level log-probability ratios via uniform summation, implicitly treating all tokens as contributing equally to the preference s…
A-SR: Self-Evolving Agentic LLMs for Symbolic Regression via Hierarchical Coordination
Wenxiao Zhao, Dong Liu, Kaiyi Xu +10
Symbolic regression aims to discover closed-form equations from data, but existing LLM-guided methods often rely on a unified proposal loop that compresses heterogeneous search fai…
RUBRIC: Realism--Utility Balanced Ranking for Imbalanced Classification
Yanxuan Yu, Dong Liu, Dong liu +11
Class imbalance poses a fundamental challenge in risk-sensitive applications such as fraud detection and medical diagnosis, where minority-class samples are scarce yet critical for…
MemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agents
Shu Wang, Edwin Yu, Oscar Love +4
Large Language Model (LLM) agents require persistent memory to maintain personalization, factual continuity, and long-horizon reasoning, yet standard context-window and retrieval-a…
TS-PEFT: Unveiling Token-Level Redundancy in Parameter-Efficient Fine-Tuning
Dabiao Ma, Ziming Dai, Zhimin Xin +3
Current Parameter-Efficient Fine-Tuning (PEFT) methods typically operate under an implicit assumption: Once a target module is selected, every token passing through it contributes…
Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing
Han Jiang, Xiaoyuan Yi, Zhihua Wei +3
Warning: Contains harmful model outputs. Despite significant advancements, the propensity of Large Language Models (LLMs) to generate harmful and unethical content poses critical c…