Poster · Atlanta

Differentiable Bit-Widths: Co-optimizing Pruning and Quantization via SVD for Ultra-Efficient LLM Compression

Name: Differentiable Bit-Widths: Co-optimizing Pruning and Quantization via SVD for Ultra-Efficient LLM Compression
Start: 2026-12-11T10:00:00-05:00
End: 2026-12-11T13:00:00-05:00
Location: Hall C1, Georgia World Congress Center

When: Fri 11 Dec 2026, 10:00–13:00 EST
Where: Hall C1, Georgia World Congress Center
Session: Atlanta Poster Session 5
Authors: Hankyul Kang, Jongbin Ryu
Organisations: Ajou University
QRS classification: Language models, Efficient and distributed ML systems

Open in schedule Official page