Post-Hoc Robustness Enhancement in Graph Neural Networks with Conditional Random Fieldsby Yassine Abbahaddou, Sofiane Ennadir,…
Bridging the Gap between Learning and Inference for Diffusion-Based Molecule Generationby Peidong Liu, Wenbo Zhang,…
Hardware and Software Platform Inferenceby Cheng Zhang, Hanna Foerster, Robert D. Mullins, Yiren Zhao, Ilia…
Don’t Look Twice: Faster Video Transformers with Run-Length Tokenizationby Rohan Choudhury, Guanglei Zhu, Sihan Liu,…
ZipNN: Lossless Compression for AI Modelsby Moshik Hershcovitch, Andrew Wood, Leshem Choshen, Guy Girmonsky, Roy…
SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Modelsby Muyang Li, Yujun Lin, Zhekai…
VTechAGP: An Academic-to-General-Audience Text Paraphrase Dataset and Benchmark Modelsby Ming Cheng, Jiaying Gong, Chenhan Yuan,…
BitNet a4.8: 4-bit Activations for 1-bit LLMsby Hongyu Wang, Shuming Ma, Furu WeiFirst submitted to…
SuffixDecoding: A Model-Free Approach to Speeding Up Large Language Model Inferenceby Gabriele Oliaro, Zhihao Jia,…
Neuromorphic Wireless Split Computing with Multi-Level Spikesby Dengyu Wu, Jiechen Chen, Bipin Rajendran, H. Vincent…