Arash Vahdat ✓

@ArashVahdat · San Francisco Bay Area · joined 24 Jan 2010

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

11 391Followers

926Following

1 874Posts total

40.2KViews on collected posts

Latest posts

Arash Vahdat ✓@ArashVahdat3 Sep

Can you be ANYMORE committed to open AI models? 📢 Exciting news on @huggingface joining @nvidia 💚🤗💚 https://t.co/c8fVIoU5OV 1.6K views · 14 likes · 0 reposts · 1 replies Open on X →

Arash Vahdat ✓@ArashVahdat3 Sep

Congratulations to @RekaAILabs! 🎉 🚀 It's exciting to see how our partners are using NVIDIA FastGen library for building their real-time video generation infrastructure. 4.7K views · 38 likes · 1 reposts · 0 replies Open on X →

Arash Vahdat ✓@ArashVahdat28 Aug

FastGen 💚 FastVideo 3.8K views · 38 likes · 3 reposts · 1 replies Open on X →

Arash Vahdat ✓@ArashVahdat28 Aug

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: https://t.co/EVQSHE3oEf 9K views · 68 likes · 11 reposts · 1 replies Open on X →

Arash Vahdat ✓@ArashVahdat29 Jul

⚡ Video diffusion is slow. PDD changes that. 🚀 Introducing Parallel Decoding Distillation, our latest work on accelerating video diffusion models. Paper: https://t.co/WWHgZvc0hu Page: https://t.co/EVQSHE3oEf By @shaulneta, @julberner, and Chao Liu. Below PDD on LTX-2.3 🔊 http 21.1K views · 298 likes · 40 reposts · 11 replies Open on X →

Against accounts of the same size

5 posts from the last 90 days, next to the 10K–100K follower range. shown widely, but few of those viewers react.

Median views4 675this account883median for 10K–100K

Reach, %41.04%this account3.35%median for 10K–100K

Engagement, %0.92%this account1.97%median for 10K–100K

Metric	This account	Median for 10K–100K	Ratio
Median views per post	4 675	883	5.29×
Reach (views ÷ followers)	41.04%	3.35%	12.2×
Engagement rate	0.92%	1.97%	0.47×

Others in this range → Compare with another account → How these benchmarks are built →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

21.1K29 Jul

9K28 Aug

3.8K

4.7K3 Sep

1.6K

Last 5 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

1.65%29 Jul

0.89%28 Aug

1.10%

0.83%3 Sep

0.92%

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.97%.

What the audience does

Likes57.0%456 in total

Reposts6.9%55 in total

Replies1.8%14 in total

Bookmarks34.4%275 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.