Advancing Super-Resolution in Neural Radiance Fields via Variational Diffusion Strategiesby Shrey Vishen, Jatin Sarabu, Saurav…
TabDPT: Scaling Tabular Foundation Modelsby Junwei Ma, Valentin Thomas, Rasa Hosseinzadeh, Hamidreza Kamkari, Alex Labach,…
Learning Versatile Skills with Curriculum Maskingby Yao Tang, Zhihui Xie, Zichuan Lin, Deheng Ye, Shuai…
AdaRankGrad: Adaptive Gradient-Rank and Moments for Memory-Efficient LLMs Training and Fine-Tuningby Yehonathan Refael, Jonathan Svirsky,…
LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Mergingby Ke Wang, Nikolaos Dimitriadis, Alessandro…
Fine-Tuning Large Language Models to Appropriately Abstain with Semantic Entropyby Benedict Aaron Tjandra, Muhammed Razzak,…
Understanding Transfer Learning via Mean-field Analysisby Gholamali Aminian, Łukasz Szpruch, Samuel N. CohenFirst submitted to…
SoftSRV: Learn to Generate Targeted Synthetic Databy Giulia DeSalvo, Jean-Fracois Kagy, Lazaros Karydas, Afshin Rostamizadeh,…
How Can We Diagnose and Treat Bias in Large Language Models for Clinical Decision-Making?by Kenza…
In Search of the Successful Interpolation: On the Role of Sharpness in CLIP Generalizationby Alireza…