TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selectionby…
Fair In-Context Learning via Latent Concept Variablesby Karuna Bhaila, Minh-Hao Van, Kennedy Edemacu, Chen Zhao,…
Point processes with event time uncertaintyby Xiuyuan Cheng, Tingnan Gong, Yao XieFirst submitted to arxiv…
Compositional simulation-based inference for time seriesby Manuel Gloeckler, Shoji Toyota, Kenji Fukumizu, Jakob H. MackeFirst…
Energy-Aware Dynamic Neural Inferenceby Marcello Bullo, Seifallah Jardak, Pietro Carnelli, Deniz GündüzFirst submitted to arxiv…
A Comprehensive Study on Quantization Techniques for Large Language Modelsby Jiedong Lang, Zhehao Guo, Shuyu…
TeleOracle: Fine-Tuned Retrieval-Augmented Generation with Long-Context Support for Networkby Nouf Alabbasi, Omar Erak, Omar Alhussein,…
“Give Me BF16 or Give Me Death”? Accuracy-Performance Trade-Offs in LLM Quantizationby Eldar Kurtic, Alexandre…
MADOD: Generalizing OOD Detection to Unseen Domains via G-Invariance Meta-Learningby Haoliang Wang, Chen Zhao, Feng…
SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Modelsby Linglan Zhao, Xuerui…