activity
20242026
collaborators

6 papers

cs.CV2026

Cosine Misleads: Auxiliary Losses Reshape Vision Language Models, Not Their Latents

XiuYu Zhang, Junfeng Fang, Zhenkai Liang

Latent visual reasoning (LVR) inserts supervised latent tokens between perception and answer generation in vision-language models (VLMs). The field uses alignment between these lat…

cs.CL2026

Self-Evaluation Is Already There: Eliciting Latent Judge Calibration in Base LLMs with Minimal Data

XiuYu Zhang, Yi Shan, Junfeng Fang +1

Large language models are increasingly evaluated by other models, raising a natural question: can a model predict how a judge will score its own output? We find that the ability is…

cs.AI2025

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning

Yi Zhang, An Zhang, XiuYu Zhang +4

Large language models (LLMs), despite possessing latent safety understanding from their vast pretraining data, remain vulnerable to generating harmful content and exhibit issues su…

cs.CV2024

CLAS: A Machine Learning Enhanced Framework for Exploring Large 3D Design Datasets

XiuYu Zhang, Xiaolei Ye, Jui-Che Chang +1

Three-dimensional (3D) objects have wide applications. Despite the growing interest in 3D modeling in academia and industries, designing and/or creating 3D objects from scratch rem…

cs.CL2024

Advancing Conversational Psychotherapy: Integrating Privacy, Dual-Memory, and Domain Expertise with Large Language Models

XiuYu Zhang, Zening Luo

Mental health has increasingly become a global issue that reveals the limitations of traditional conversational psychotherapy, constrained by location, time, expense, and privacy c…

cs.CV2024

Partially Conditioned Patch Parallelism for Accelerated Diffusion Model Inference

XiuYu Zhang, Zening Luo, Michelle E. Lu

Diffusion models have exhibited exciting capabilities in generating images and are also very promising for video creation. However, the inference speed of diffusion models is limit…