Summary of Reflect-rl: Two-player Online Rl Fine-tuning For Lms, by Runlong Zhou et al.
Reflect-RL: Two-Player Online RL Fine-Tuning for LMsby Runlong Zhou, Simon S. Du, Beibin LiFirst submitted…
Reflect-RL: Two-Player Online RL Fine-Tuning for LMsby Runlong Zhou, Simon S. Du, Beibin LiFirst submitted…
EBFT: Effective and Block-Wise Fine-Tuning for Sparse LLMsby Song Guo, Fan Wu, Lei Zhang, Xiawu…
Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Modelsby Christian Schlarmann,…
A Critical Evaluation of AI Feedback for Aligning Large Language Modelsby Archit Sharma, Sedrick Keh,…
Mafin: Enhancing Black-Box Embeddings with Model Augmented Fine-Tuningby Mingtian Zhang, Shawn Lan, Peter Hayes, David…
Uncertainty quantification in fine-tuned LLMs using LoRA ensemblesby Oleksandr Balabanov, Hampus LinanderFirst submitted to arxiv…
Remember This Event That Year? Assessing Temporal Information and Reasoning in Large Language Modelsby Himanshu…
Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decodingby Hanling Yi,…
LoRA Training in the NTK Regime has No Spurious Local Minimaby Uijeong Jang, Jason D.…
Invertible Fourier Neural Operators for Tackling Both Forward and Inverse Problemsby Da Long, Shandian ZheFirst…