Language Adaptation on a Tight Academic Compute Budget: Tokenizer Swapping Works and Pure bfloat16 Is…
Boosting Lossless Speculative Decoding via Feature Sampling and Partial Alignment Distillationby Lujun Gui, Bin Xiao,…
LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yetby Nathaniel Li, Ziwen Han, Ian…
MLR-Copilot: Autonomous Machine Learning Research based on Large Language Models Agentsby Ruochen Li, Teerth Patel,…
Question answering system of bridge design specification based on large language modelby Leye Zhang, Xiangxiang…
Memory-Efficient LLM Training with Online Subspace Descentby Kaizhao Liang, Bo Liu, Lizhang Chen, Qiang LiuFirst…
Vintern-1B: An Efficient Multimodal Large Language Model for Vietnameseby Khang T. Doan, Bao G. Huynh,…
Critique-out-Loud Reward Modelsby Zachary Ankner, Mansheej Paul, Brandon Cui, Jonathan D. Chang, Prithviraj AmmanabroluFirst submitted…
Memorization in In-Context Learningby Shahriar Golchin, Mihai Surdeanu, Steven Bethard, Eduardo Blanco, Ellen RiloffFirst submitted…
Design Principle Transfer in Neural Architecture Search via Large Language Modelsby Xun Zhou, Xingyu Wu,…