activity
20242026
collaborators

5 papers

cs.AI2026

Risk Awareness Injection: Calibrating Vision-Language Models for Safety without Compromising Utility

Mengxuan Wang, Yuxin Chen, Gang Xu +3

Vision language models (VLMs) extend the reasoning capabilities of large language models (LLMs) to cross-modal settings, yet remain highly vulnerable to multimodal jailbreak attack…

cs.LG2026

Scaling Laws Revisited: Modeling the Role of Data Quality in Language Model Pretraining

Anirudh Subramanyam, Yuxin Chen, Robert L. Grossman

Scaling laws for language model training traditionally characterize how performance scales with model size and dataset volume. Prior work has explored architecture variants and dat…

cs.CV2025

EditInfinity: Image Editing with Binary-Quantized Generative Models

Jiahuan Wang, Yuxin Chen, Jun Yu +2

Adapting pretrained diffusion-based generative models for text-driven image editing with negligible tuning overhead has demonstrated remarkable potential. A classical adaptation pa…

cs.CL2025

Knowing or Guessing? Robust Medical Visual Question Answering via Joint Consistency and Contrastive Learning

Songtao Jiang, Yuxi Chen, Sibo Song +5

In high-stakes medical applications, consistent answering across diverse question phrasings is essential for reliable diagnosis. However, we reveal that current Medical Vision-Lang…

cs.CV2024

Advancing Cross-domain Discriminability in Continual Learning of Vision-Language Models

Yicheng Xu, Yuxin Chen, Jiahao Nie +3

Continual learning (CL) with Vision-Language Models (VLMs) has overcome the constraints of traditional CL, which only focuses on previously encountered classes. During the CL of VL…