Summary of Pushing the Envelope Of Low-bit Llm Via Dynamic Error Compensation, by Yeonhong Park et al.
Pushing the Envelope of Low-Bit LLM via Dynamic Error Compensationby Yeonhong Park, Jake Hyun, Hojoon…
Pushing the Envelope of Low-Bit LLM via Dynamic Error Compensationby Yeonhong Park, Jake Hyun, Hojoon…
Sequence Generation Modeling for Continuous Value Predictionby Hongxu Ma, Kai Tian, Tao Zhang, Xuefeng Zhang,…
Data-Free Group-Wise Fully Quantized Winograd Convolution via Learnable Scalesby Shuokai Pan, Gerti Tuzi, Sudarshan Sreeram,…
Goal-oriented Communications based on Recursive Early Exit Neural Networksby Jary Pomponi, Mattia Merluzzi, Alessio Devoto,…
InfAlign: Inference-aware language model alignmentby Ananth Balashankar, Ziteng Sun, Jonathan Berant, Jacob Eisenstein, Michael Collins,…
Revisiting PCA for time series reduction in temporal dimensionby Jiaxin Gao, Wenbo Hu, Yuntian ChenFirst…
Latenrgy: Model Agnostic Latency and Energy Consumption Prediction for Binary Classifiersby Jason M. PittmanFirst submitted…
Adaptive Conformal Inference by Bettingby Aleksandr Podkopaev, Darren Xu, Kuang-Chih LeeFirst submitted to arxiv on:…
Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller…
Evaluating deep learning models for fault diagnosis of a rotating machinery with epistemic and aleatoric…