Continual SFT Matches Multimodal RLHF with Negative Supervisionby Ke Zhu, Yu Wang, Yanpeng Sun, Qiang…
Non-Linear Outlier Synthesis for Out-of-Distribution Detectionby Lars Doorenbos, Raphael Sznitman, Pablo Márquez-NeilaFirst submitted to arxiv…
Omnipredicting Single-Index Models with Multi-Index Modelsby Lunjia Hu, Kevin Tian, Chutong YangFirst submitted to arxiv…
Learning from Label Proportions and Covariate-shifted Instancesby Sagalpreet Singh, Navodita Sharma, Shreyas Havaldar, Rishi Saket,…
A Multimodal Approach Combining Structural and Cross-domain Textual Guidance for Weakly Supervised OCT Segmentationby Jiaqi…
Contrast Similarity-Aware Dual-Pathway Mamba for Multivariate Time Series Node Classificationby Mingsen Du, Meng Chen, Yongjian…
libcll: an Extendable Python Toolkit for Complementary-Label Learningby Nai-Xuan Ye, Tan-Ha Mai, Hsiu-Hsuan Wang, Wei-I…
Learning Differentiable Surrogate Losses for Structured Predictionby Junjie Yang, Matthieu Labeau, Florence d'Alché-BucFirst submitted to…
Upside-Down Reinforcement Learning for More Interpretable Optimal Controlby Juan Cardenas-Cartagena, Massimiliano Falzari, Marco Zullich, Matthia…
Enhancing Decision Transformer with Diffusion-Based Trajectory Branch Generationby Zhihong Liu, Long Qian, Zeyang Liu, Lipeng…