9 papers
Reward Auditor: Inference on Reward Modeling Suitability in Real-World Perturbed Scenarios
Jianxiang Zang, Yongda Wei, Ruxue Bai +5
Reliable reward models (RMs) are critical for ensuring the safe alignment of large language models (LLMs). However, current RM evaluation methods focus solely on preference percept…
Why Self-Training Helps and Hurts: Denoising vs. Signal Forgetting
Mingqi Wu, Archer Y. Yang, Qiang Sun
Iterative self-training (self-distillation) repeatedly refits a model on pseudo-labels generated by its own predictions. We study this procedure in overparameterized linear regress…
Training-Free Self-Correction for Multimodal Masked Diffusion Models
Yidong Ouyang, Panwen Hu, Zhengyan Wan +7
Masked diffusion models have emerged as a powerful framework for text and multimodal generation. However, their sampling procedure updates multiple tokens simultaneously and treats…
EIR: Enhanced Image Representations for Medical Report Generation
Qiang Sun, Zongcheng Ji, Yinlong Xiao +2
Generating medical reports from chest X-ray images is a critical and time-consuming task for radiologists, especially in emergencies. To alleviate the stress on radiologists and re…
C3-OWD: A Curriculum Cross-modal Contrastive Learning Framework for Open-World Detection
Siheng Wang, Zhengdao Li, Yanshu Li +12
Object detection has advanced significantly in the closed-set setting, but real-world deployment remains limited by two challenges: poor generalization to unseen categories and ins…
PCA++: How Uniformity Induces Robustness to Background Noise in Contrastive Learning
Mingqi Wu, Qiang Sun, Yi Yang
High-dimensional data often contain low-dimensional signals obscured by structured background noise, which limits the effectiveness of standard PCA. Motivated by contrastive learni…