60 citations
- Tsinghua UniversityCN14 papers
- Peking UniversityCN9 papers
- Shanghai Jiao Tong UniversityCN8 papers
- Huawei Technologies (China)CN7 papers
- Peng Cheng LaboratoryCN6 papers
- Chinese University of Hong KongHK5 papers
- South China University of TechnologyCN5 papers
- The University of SydneyAU5 papers
- University of Chinese Academy of SciencesCN5 papers
- Huawei Technologies (United Kingdom)GB4 papers
- Huazhong University of Science and TechnologyCN4 papers
- LMU KlinikumDE4 papers
4 papers · 2 filters
VIL: Learning to Leverage Auxiliary Tasks for Multitask Learning
Rafael Kourdis, Gabriel Gordon-Hall, Philip John Gorinski
Multitask Learning is a Machine Learning paradigm that aims to train a range of (usually related) tasks with the help of a shared model. While the goal is often to improve the join…
OAC: Output-adaptive Calibration for Accurate Post-training Quantization
Ali Edalati, Alireza Ghaffari, Mahsa Ghazvini Nejad +4
Deployment of Large Language Models (LLMs) has major computational costs, due to their rapidly expanding size. Compression of LLMs reduces the memory footprint, latency, and energy…
Enhancing Reinforcement Learning Agents with Local Guides
Paul Daoudi, Bogdan Robu, Christophe Prieur +2
This paper addresses the problem of integrating local guide policies into a Reinforcement Learning agent. For this, we show how to adapt existing algorithms to this setting before…
Leveraging Gradients for Unsupervised Accuracy Estimation under Distribution Shift
Renchunzi Xie, Ambroise Odonnat, Vasilii Feofanov +3
Estimating the test performance of a model, possibly under distribution shift, without having access to the ground-truth labels is a challenging, yet very important problem for the…