Efficient Multi-task Uncertainties for Joint Semantic Segmentation and Monocular Depth Estimationby Steven Landgraf, Markus Hillemann,…
Rethinking Self-Distillation: Label Averaging and Enhanced Soft Label Refinement with Partial Labelsby Hyeonsu Jeong, Hye…
DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflowsby Ajay Patel, Colin Raffel,…
Model Compression and Efficient Inference for Large Language Models: A Surveyby Wenxiao Wang, Wei Chen,…
Physics-Informed Neural Networks with Hard Linear Equality Constraintsby Hao Chen, Gonzalo E. Constante Flores, Can…
In-Context Data Distillation with TabPFNby Junwei Ma, Valentin Thomas, Guangwei Yu, Anthony CateriniFirst submitted to…
Distilling Morphology-Conditioned Hypernetworks for Efficient Universal Morphology Controlby Zheng Xiong, Risto Vuorio, Jacob Beck, Matthieu…
Classifying Nodes in Graphs without GNNsby Daniel Winter, Niv Cohen, Yedid HoshenFirst submitted to arxiv…
Cooperative Knowledge Distillation: A Learner Agnostic Approachby Michael Livanos, Ian Davidson, Stephen WongFirst submitted to…
Flashback: Understanding and Mitigating Forgetting in Federated Learningby Mohammed Aljahdali, Ahmed M. Abdelmoniem, Marco Canini,…