The N-Grammys: Accelerating Autoregressive Inference with Learning-Free Batched Speculationby Lawrence Stewart, Matthew Trager, Sujan Kumar…
Beyond The Rainbow: High Performance Deep Reinforcement Learning On A Desktop PCby Tyler Clark, Mark…
Overcoming label shift in targeted federated learningby Edvin Listo Zec, Adam Breitholtz, Fredrik D. JohanssonFirst…
Flexible task abstractions emerge in linear networks with fast and bounded unitsby Kai Sandbrink, Jan…
Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Databy Chengrui Qu, Laixi Shi, Kishan…
Reconsidering the Performance of GAE in Link Predictionby Weishuo Ma, Yanbo Wang, Xiyuan Wang, Muhan…
EXPLORA: Efficient Exemplar Subset Selection for Complex Reasoningby Kiran Purohit, Venktesh V, Raghuram Devalla, Krishna…
MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mambaby Masakazu Yoshimura, Teruaki Hayashi, Yota MaedaFirst submitted to arxiv…
MEG: Medical Knowledge-Augmented Large Language Models for Question Answeringby Laura Cabello, Carmen Martin-Turrero, Uchenna Akujuobi,…
Polynomial Composition Activations: Unleashing the Dynamics of Large Language Modelsby Zhijian Zhuo, Ya Wang, Yutao…