Yu Wang

Overthinking Reduction with Decoupled Rewards and Curriculum Data Scheduling

Selecting Auxiliary Data via Neural Tangent Kernels for Low-Resource Domains

Truly Assessing Fluid Intelligence of Large Language Models through Dynamic Reasoning Evaluation

Fine-tuning with Reserved Majority for Noise Reduction

Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language Bootstrapping

Drawing the Line: Enhancing Trustworthiness of MLLMs Through the Power of Refusal