SOURCE-LINKED INTELLIGENCE

QuantWM: Temporally Consistent 2-Bit KV Cache Quantization for World Models and Video Generation

arXiv · AI, language, vision and robotics · article · Sep 22, 2026 · UTC

KV cache memory has become a major deployment bottleneck for video generation and world models, which motivates low-bit quantization study for efficiency. Existing 2-bit KV cache quantization methods can achieve nearly lossless performance on video benchmarks such as VBench, however, we find that they still cause severe temporal flickering and visual degradation. Meanwhile, deeper investigates show that Key quantization produces smaller reconstruction errors than Value, but surprisingly leads to much larger output degradation. We trace this discrepancy to attention: small Key perturbations can

Read original source ↗ Open in workspace

recordType

paper

region

Global