Yuan Wu

BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models

Decomposing Prompts: Discovering Reusable Scaffolds and Task-Specific Residuals

THINK-Bench: Evaluating Thinking Efficiency and Chain-of-Thought Quality of Large Reasoning Models

Align, Don’t Divide: Revisiting the LoRA Architecture in Multi-Task Learning

MeTA-LoRA: Data-Efficient Multi-Task Fine-Tuning for Large Language Models

Beyond Accuracy: Measuring Reward Variance as a Predictive Benchmark for RLHF

Mixup Model Merge: Enhancing Model Merging Performance through Randomized Linear Interpolation

ConfProBench: A Confidence Evaluation Benchmark for MLLM-based Process Judges

SegRet: An Efficient Design for Semantic Segmentation with Retentive Network

ProDA: Profile-Decomposed Adaptation for Capturing the Structured Residual in Low-Rank Updates

BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models

Large Language Model Evaluation via Matrix Nuclear-Norm

Rethinking Data Selection at Scale: Random Selection is Almost All You Need