Energy-Efficient and Dequantization-Free Quantization of LLMs: A Spiking Neural Network Approach to Salient Value Mitigation.

@inproceedings{wang-2026-energyefficient, author = {Chenyu Wang and Zhanglu Yan and Zhi Zhou and Xu Chen and Weng-Fai Wong}, editor = {Hakim Hacid and Yoelle Maarek and Francesco Bonchi and Ido Guy and Emine Yilmaz}, title = {{Energy-Efficient and Dequantization-Free Quantization of LLMs: A Spiking Neural Network Approach to Salient Value Mitigation}}, booktitle = {{Proceedings of the ACM Web Conference 2026, WWW 2026, Dubai, United Arab Emirates, originally scheduled for April 13-17, 2026, rescheduled for June 29 - July 3, 2026}}, pages = {5334--5345}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3774904.3792337}, doi = {https://doi.org/10.1145/3774904.3792337} }