method · first seen 13 Oct 2026
activation-aware weight quantization
Also: AWQ quantization
A 4-bit weight quantization method that protects salient weight channels using activation statistics.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Lightweight but Linguistically Fair? Quantisation Robustness across Bavarian, German, and EnglishPapers · 13 Oct 2026 · Jophin John, Michael Hoffmann, Piroska Lendvai, Florent Dufour
- Leonccaa/ReVoltaCode · 20 Oct 2026 · Leonccaa · 61 stars
- Compressing Onboard Language Models for Space Robots under a Behavioral-Fidelity RequirementPapers · 21 Oct 2026 · Jia Deng, Zizhe Wang, Xin Lu, Yi Huang, Zehao Jia
- PlantVLM-Edge: Quantized Vision-Language Models for On-Device Crop Health DiagnosisPapers · 2 Nov 2026 · Gaurab Wagle, Bishal Adhikari, Jiajia Li, Xiaolei Huang, Dong Chen
- LoopQ: Fair, Closed-Loop Evaluation of Quantized Vision-Language-Action ModelsPapers · 3 Nov 2026 · Syed Umer Bukhari, Magnus Almgren, Ahmed Ali-Eldin
Latest sources
- LoopQ: Fair, Closed-Loop Evaluation of Quantized Vision-Language-Action ModelsPapers · 3 Nov 2026 · Syed Umer Bukhari, Magnus Almgren, Ahmed Ali-Eldin
- PlantVLM-Edge: Quantized Vision-Language Models for On-Device Crop Health DiagnosisPapers · 2 Nov 2026 · Gaurab Wagle, Bishal Adhikari, Jiajia Li, Xiaolei Huang, Dong Chen
- Compressing Onboard Language Models for Space Robots under a Behavioral-Fidelity RequirementPapers · 21 Oct 2026 · Jia Deng, Zizhe Wang, Xin Lu, Yi Huang, Zehao Jia
- Leonccaa/ReVoltaCode · 20 Oct 2026 · Leonccaa · 61 stars
- Lightweight but Linguistically Fair? Quantisation Robustness across Bavarian, German, and EnglishPapers · 13 Oct 2026 · Jophin John, Michael Hoffmann, Piroska Lendvai, Florent Dufour