Summary of Keeping Llms Aligned After Fine-tuning: the Crucial Role Of Prompt Templates, by Kaifeng Lyu et al.
Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templatesby Kaifeng Lyu, Haoyu Zhao,…
Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templatesby Kaifeng Lyu, Haoyu Zhao,…
Generalizability Under Sensor Failure: Tokenization + Transformers Enable More Robust Latent Spacesby Geeling Chau, Yujin…
Diffusion Language Models Are Versatile Protein Learnersby Xinyou Wang, Zaixiang Zheng, Fei Ye, Dongyu Xue,…
Approaching Human-Level Forecasting with Language Modelsby Danny Halawi, Fred Zhang, Chen Yueh-Han, Jacob SteinhardtFirst submitted…
Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewardsby Haoxiang…
Stochastic contextual bandits with graph feedback: from independence number to MAS numberby Yuxiao Wen, Yanjun…
Meta-Task: A Method-Agnostic Framework for Learning to Regularize in Few-Shot Learningby Mohammad Rostami, Atik Faysal,…
MMSR: Symbolic Regression is a Multi-Modal Information Fusion Taskby Yanjie Li, Jingyi Liu, Weijun Li,…
Impact of network topology on the performance of Decentralized Federated Learningby Luigi Palmieri, Chiara Boldrini,…
FORML: A Riemannian Hessian-free Method for Meta-learning on Stiefel Manifoldsby Hadi Tabealhojeh, Soumava Kumar Roy,…