Haocheng Xi
@HaochengXiUCB
Second-year PhD in @berkeley_ai. Prev: Yao Class, @Tsinghua_Uni |
Efficient Machine Learning & ML sys
502 Following 2.3K Followers
Open-source video generation is now faster than playback without compromising quality.
Introducing Video Delta Net (VDN): hybrid attention for live text-to-video with near-lossless quality.
VDN accelerates Minimax-H3 by 75 - 90 x, generating 14 seconds of 768p video in 11 seconds on 8× NVIDIA B200 GPUs.
Checkpoints + training/inference code + Technical Blog ⬇️
(1/6)
Show more
🎬 Long video generation is bottlenecked by KV-cache memory. We fixed it.
Presenting QuantVideoGen @ #ICML2026#:
⚡ ~7× smaller KV cache @ INT2
💾 ~85% less memory
🔧 No fine-tuning, no weight changes
📍 Poster: Thu Jul 9, 2026. 5:00 PM -6:45 PM KST · Hall A #4603#
My wonderful co-author Xingyang Li will be presenting our papers. Come say hi!
🔗
Show more
New blog post: The Forgetting Wall in Video and World Models
Long-horizon video generation is not just limited by compute. It is limited by how much of its own past the model can afford to remember.
I wrote about why long videos drift, why KV cache becomes the memory bottleneck, and why compression is a key direction for future video/world models.
Show more
Really exciting to see KV-cache compression getting attention.
A similar bottleneck shows up beyond LLMs: for world models and autoregressive long-video generation, KV cache can quickly dominate memory and limit long-horizon consistency.
Our recent work, Quant VideoGen, explores training-free 2-bit KV-cache quantization for video diffusion models, achieving up to 7.0× KV memory reduction with <4% latency overhead.
Link:
Show more
