Sparse VideoGen 2 | PSNR = 25.808 | Latency = 16 min Dense Attention | Latency = 30 min Wan 2.1 720P, Text-to-Video
–Neural Information Processing Systems
Dif significant fusion T latenc ransformers y due to (DiTs) the quadratic are essential comple for xity video of attention.
Neural Information Processing Systems
Jun-19-2026, 13:41:17 GMT
- Country:
- North America > United States (0.28)
- Genre:
- Research Report > Experimental Study (1.00)
- Industry:
- Information Technology (0.46)
- Technology: