QuantWM: Temporally Consistent 2-Bit KV Cache Quantization for Video World Models
QuantWM applies training-free 2-bit KV cache quantization to video world models while preserving temporal consistency.
42
AI model
Causal-Forcing
- Mentions · 7d0
- Mentions · 30d0
- All mentions1
- First seenSep 27, 2026
- Last mentionedSep 27, 2026
Timeline
1 articles · newest firstAppears with
- Longcat-Videoai model · 1
- Matrix-Game-2ai model · 1
- HY-World 1.5ai model · 1
- LingBot-World-v2ai model · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.