Poster · Atlanta
SemanticDialect: Semantic-Aware Mixed-Format Quantization for Video Diffusion Transformers
- When
- Thu 10 Dec 2026, 16:30–19:30 EST
- Where
- Hall C1, Georgia World Congress Center
- Session
- Atlanta Poster Session 4
- Authors
- Wonsuk Jang, Thierry Tambe
- Organisations
- Stanford University
- QRS classification
- Attention and transformers, Generative models, Computer vision, Efficient and distributed ML systems