Natalia Frumkin

4 papers · 2023–2025 · 4 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (4) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (15)

Conferences

AAAI (1) ICCV (1) ICLR (1) ICML (1)

Top co-authors

Diana Marculescu (4) Hung-Yueh Chiang (3) Chi-Chih Chang (2) Kai-Chiang Wu (2) Dibakar Gope (1) Mohamed S. Abdelfattah (1) Feng Liang (1)

Keywords

neural network quantization (1) model compression (1) vision transformer (1) transfer learning (1) loss landscape (1) memory efficiency (1) evolutionary algorithm (1) edge computing (1) weight quantization (1) mobile computing (1) inverted residual block (1)

Papers

Quamba: A Post-Training Quantization Recipe for Selective State Space Models ICLR 2025

Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models ICML 2025

MobileTL: On-Device Transfer Learning with Inverted Residual Blocks AAAI 2023

Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers ICCV 2023