Reducing self-supervised learning complexity improves weakly-supervised classification performance in computational pathologyby Tim Lenz, Omar S.…
Teaching Large Language Models to Reason with Reinforcement Learningby Alex Havrilla, Yuqing Du, Sharath Chandra…
Stop Regressing: Training Value Functions via Classification for Scalable Deep RLby Jesse Farebrother, Jordi Orbay,…
Knockoff-Guided Feature Selection via A Single Pre-trained Reinforced Agentby Xinyuan Wang, Dongjie Wang, Wangyang Ying,…
On the Effectiveness of Distillation in Mitigating Backdoors in Pre-trained Encoderby Tingxu Han, Shenghan Huang,…
Public-data Assisted Private Stochastic Optimization: Power and Limitationsby Enayat Ullah, Michael Menart, Raef Bassily, Cristóbal…
Performance Evaluation of Semi-supervised Learning Frameworks for Multi-Class Weed Detectionby Jiajia Li, Dong Chen, Xunyuan…
Rehabilitation Exercise Quality Assessment through Supervised Contrastive Learning with Hard and Soft Negativesby Mark Karlov,…
Learning without Exact Guidance: Updating Large-scale High-resolution Land Cover Maps from Low-resolution Historical Labelsby Zhuohong…
Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Modelsby…