Arash Vahdat

@ArashVahdat

Research Director, leading fundamental generative AI research (GenAIR) @nvidia research, volunteer at California Search & Rescue, views are my own.

San Francisco Bay Area

research.nvidia.com/labs/genair

Replies Reposts Media

Pinned
Arash Vahdat
@ArashVahdat
Jul 29
⚡ Video diffusion is slow. PDD changes that. 🚀 Introducing Parallel Decoding Distillation, our latest work on accelerating video diffusion models. Paper: arxiv.org/abs/2607.26004 Page: research.nvidia.com/labs/genair/pd… By @shaulneta, @julberner, and Chao Liu. Below PDD on LTX-2.3 🔊
00:00
11
Arash Vahdat
@ArashVahdat
Sep 3
Can you be ANYMORE committed to open AI models? 📢 Exciting news on @huggingface joining @nvidia 💚🤗💚
Jensen Huang
@JensenHuang
Sep 3
Exciting day for NVIDIA and @huggingface. Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enable sovereignty. They allow every developer, startup, university, industry and country to build with, customize and benefit from AI. Thank you
2
Arash Vahdat
@ArashVahdat
Sep 3
Congratulations to @RekaAILabs! 🎉 🚀 It's exciting to see how our partners are using NVIDIA FastGen library for building their real-time video generation infrastructure.
Reka
@RekaAILabs
Sep 3
Together with @nvidia , we've built a real-time version of our video generation model: 30B parameters, steerable mid-stream in natural language, 720p at 24fps. 11.8x faster on a single H100, no major quality drop in our blind eval. We're one step closer to World Language Action
00:00
Arash Vahdat
@ArashVahdat
Aug 28
FastGen 💚 FastVideo
Hao AI Lab
@haoailab
Aug 28
(1/6) Open Weight @MiniMax_AI FastH3 v1: Generate 15s 768p video in 13s 🚀 - FastVideo collab w/ @nuvalab + FastGen - Up to 14x speedup on @NVIDIAAI Blackwell GPU - Fully open so community can run and improve the acceleration recipe. The era of open weight video models just
00:00
1
Arash Vahdat
@ArashVahdat
Aug 28
Love seeing ideas travel this fast. 🚀 We haven’t released the code or even submitted the paper yet, but our Parallel Decoding Distillation (PDD) has already been independently implemented and used to accelerate MiniMax-H3. ⚡ More on FastGen-PDD: research.nvidia.com/labs/genair/pd…
Wildminder
@wildmindai
Aug 26
Another cool stuff from Alibaba! MiniMax-H3 Acc LoRAs. Parallel Decoding Distillation for efficient video gen in a few steps. FL2VA + Ref2VA huggingface.co/alibaba-pai/Mi…
00:00
1