Unveiling Molecular Secrets: An LLM-Augmented Linear Model for Explainable and Calibratable Molecular Property Predictionby Zhuoran…
Transformers Provably Solve Parity Efficiently with Chain of Thoughtby Juno Kim, Taiji SuzukiFirst submitted to…
QEFT: Quantization for Efficient Fine-Tuning of LLMsby Changhun Lee, Jun-gyu Jin, Younghyun Cho, Eunhyeok ParkFirst…
Why pre-training is beneficial for downstream classification tasks?by Xin Jiang, Xu Cheng, Zechao LiFirst submitted…
MUSO: Achieving Exact Machine Unlearning in Over-Parameterized Regimesby Ruikai Yang, Mingzhen He, Zhengbao He, Youmei…
Metalic: Meta-Learning In-Context with Protein Language Modelsby Jacob Beck, Shikha Surana, Manus McAuliffe, Oliver Bent,…
Merging in a Bottle: Differentiable Adaptive Merging (DAM) and the Path from Averaging to Automationby…
Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?by Khashayar Gatmiry, Nikunj…
Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptationby Grigory Malinovsky,…
HyperDPO: Conditioned One-Shot Multi-Objective Fine-Tuning Frameworkby Yinuo Ren, Tesi Xiao, Michael Shavlovsky, Lexing Ying, Holakou…