Bidhan Roy ✓

@bidhan

ceo @bageldotcom. building a general world-action model for physical AI.

4 245Followers

963Following

3 380Posts total

482.4KViews on collected posts

Latest posts

Bidhan Roy ✓@bidhan28 May

@bidhan Congrats Bidhan :). Amazing work!!!!! Can’t wait to try this out 617 views · 8 likes · 0 reposts · 1 replies Open on X →

Bidhan Roy ✓@bidhan28 May

We're selectively releasing the Paris 2.0 weights and partnering with researchers and teams interested in diffusion-based video models, world models, and embodied agents. The model is on Hugging Face: https://t.co/HjoeeQ1vbN 12.1K views · 67 likes · 6 reposts · 2 replies Open on X →

Bidhan Roy ✓@bidhan28 May

Video diffusion backbones increasingly anchor the world models behind physical AI. Our early internal results show the Paris 2.0 recipe carries over to them very well. We will share more on that in future work. 2.3K views · 21 likes · 0 reposts · 1 replies Open on X →

Bidhan Roy ✓@bidhan28 May

With Paris 2.0, our goal was only to match a monolithic model's benchmarks while training on a distributed, heterogeneous pool of GPUs. It beat them instead. FVD dropped from 561.04 to 279.01, and CLIP text-video alignment and aesthetic score increased. To our knowledge, the DDM

2.4K views · 21 likes · 0 reposts · 1 replies Open on X →

Bidhan Roy ✓@bidhan28 May

Paris 2.0 is a Decentralized Diffusion Model (DDM). A DDM is an ensemble of independent diffusion models trained in isolation, each on its own slice of the data, and exchanges no gradients, parameters, or activations between them. During inference, a lightweight router selects a

2.9K views · 31 likes · 1 reposts · 1 replies Open on X →

Bidhan Roy ✓@bidhan28 May

Paris 2.0 builds on Paris 1.0, which proved that image generation can be trained on a geographically distributed, heterogeneous pool of GPUs. Temporally coherent video under the same settings remained an open question. Paris 2.0 closes it. Read the technical report on arxiv: htt

4.6K views · 36 likes · 2 reposts · 1 replies Open on X →

Bidhan Roy ✓@bidhan28 May

We're releasing Paris 2.0, which, to our knowledge, is the world's first decentralized trained video generation model. We benchmarked it against a monolithic model trained on the same data and compute budget, and Paris 2.0 outperformed the monolithic by ~2x on FVD benchmark. htt

0:42

457.5K views · 660 likes · 112 reposts · 88 replies Open on X →

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

457.5K28 May

4.6K

2.9K

2.4K

2.3K

12.1K

617

Last 7 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.21%28 May

0.89%

1.18%

0.91%

0.97%

0.62%

1.46%

Reactions — likes, reposts, replies and quotes — divided by views.

What the audience does

Likes49.5%844 in total

Reposts7.1%121 in total

Replies5.6%95 in total

Quotes4.9%84 in total

Bookmarks32.9%562 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.

Latest posts

Growth & engagement

Views per post

Engagement rate per post

What the audience does

Similar accounts