Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

trained my own with trl + openenv blog with open artifacts (code, models, dataset, rl env...) soon!

Sergio Paniego

7,031 subscribers

90,257 views • 2 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

13 Comments

Saad2 months ago

I’m trying something similar too

Gajesh2 months ago

how much did this process cost and how many TFLOPs / GPUs went in this? (would like to try smth like this)

Sergio Paniego2 months ago

i'll add all the details about it on the final blog, i'm releasing it tomorrow

Akash Mahajan2 months ago

@adithya_s_k Awesome looking forward to it!

Kevin Hu2 months ago

looking forward!

Sagar2 months ago

Open artifacts is the part that matters. Waiting on that blog!

tani2 months ago

nice work - how much did it end up costing?

Sergio Paniego2 months ago

i'll add details about it on the blog! dropping tomorrow

Gon2 months ago

Eres un crack Sergio. La verdad es que la charla que diste en seLIA sobre TRL y Openenv estuvo muy interesante (yo soy el chaval que se acercó a darte la lata al final)

Sergio Paniego2 months ago

gracias, me acuerdo! jaja

Gon2 months ago

El año que viene volveré a darte la lata

Starling2 months ago

What beauty 💙

Nelson Chu2 months ago

Interested in controlling a watercolor app to paint?

Related Videos

You can literally RL a 4B VLM to ace GeoGuesser 🌍 > Open-source code, RL environment, dataset, training setup, evals, and everything you need to reproduce it end-to-end > dropping soon!!

You can literally RL a 4B VLM to ace GeoGuesser 🌍 > Open-source code, RL environment, dataset, training setup, evals, and everything you need to reproduce it end-to-end > dropping soon!!

Adithya S K

117,964 views • 2 months ago

Introducing the Open Deep Research app! Generate detailed reports on any topic with open source LLMs. Free & fully open source. We’re releasing everything: evaluation dataset, code, app, and blog.🔥

Introducing the Open Deep Research app! Generate detailed reports on any topic with open source LLMs. Free & fully open source. We’re releasing everything: evaluation dataset, code, app, and blog.🔥

Together AI

28,338 views • 1 year ago

Multi-harness RL training is coming to OpenEnv > pick a model. pick a harness. pick a sandbox. train > Claude Code. Codex. Gemini CLI. OpenCode. Pi. Kimi. OpenHands. and many more. > Async RL loop. fully open-source. end-to-end, harbor compatible dropping soon 👀

Multi-harness RL training is coming to OpenEnv > pick a model. pick a harness. pick a sandbox. train > Claude Code. Codex. Gemini CLI. OpenCode. Pi. Kimi. OpenHands. and many more. > Async RL loop. fully open-source. end-to-end, harbor compatible dropping soon 👀

Adithya S K

26,931 views • 1 month ago

A composite agent harness composed of system1 (multi-agent jevs) + system2 (astra) out-micros an insane computer in my WC3FT RL env (will open-source soon)

A composite agent harness composed of system1 (multi-agent jevs) + system2 (astra) out-micros an insane computer in my WC3FT RL env (will open-source soon)

Peter Wang

188,012 views • 1 month ago

I had 14 tabs open just to keep up with AI. arXiv, Papers With Code, every leaderboard, HuggingFace, half a dozen RL-env hubs... So I built one screen for all of it. The Bloomberg terminal for AI research. It's called Sophon 🧵

I had 14 tabs open just to keep up with AI. arXiv, Papers With Code, every leaderboard, HuggingFace, half a dozen RL-env hubs... So I built one screen for all of it. The Bloomberg terminal for AI research. It's called Sophon 🧵

serafim

48,633 views • 5 months ago

We used RL to train models that create curated context from long documents for downstream use by agents. The models sometimes learn to invent their own abbreviations and shorthand. Optimizing with RL for downstream use produces very different artifacts from ordinary summaries: shorter, denser, creatively concise. We call these neural cheat-sheets.

We used RL to train models that create curated context from long documents for downstream use by agents. The models sometimes learn to invent their own abbreviations and shorthand. Optimizing with RL for downstream use produces very different artifacts from ordinary summaries: shorter, denser, creatively concise. We call these neural cheat-sheets.

Applied Compute

37,368 views • 4 months ago

One of the first policies successfully trained with obstacles. Am I the first person to train models in RL with this many rigid bodies?

One of the first policies successfully trained with obstacles. Am I the first person to train models in RL with this many rigid bodies?

kache

31,437 views • 2 months ago

we RL trained a 4B VLM to play GeoGuesser > environment, dataset, training recipe, evals, and code are all open-source. > runs on a single A100 > beat gpt 5.4 mini, haiku, qwen 3.5 122B and came close to sonnet on evals

we RL trained a 4B VLM to play GeoGuesser > environment, dataset, training recipe, evals, and code are all open-source. > runs on a single A100 > beat gpt 5.4 mini, haiku, qwen 3.5 122B and came close to sonnet on evals

Adithya S K

68,926 views • 1 month ago

Video understanding isn't just recognizing —it demands reasoning across thousands of frames. Meet Long-RL🚀 Highlights: 🧠 Dataset: LongVideo-Reason — 52K QAs with reasoning. ⚡ System: MR-SP - 2.1× faster RL for long videos. 📈 Scalability: Hour-long videos (3,600 frames) RL on a single node (8×A100s). 🖼️📝🎵 RL training for video, text, audio — works with VILA, Qwen series, and image/video generation models 🎨🎬 📄 Paper: 🎥 Demo: 💻 Code:

Video understanding isn't just recognizing —it demands reasoning across thousands of frames. Meet Long-RL🚀 Highlights: 🧠 Dataset: LongVideo-Reason — 52K QAs with reasoning. ⚡ System: MR-SP - 2.1× faster RL for long videos. 📈 Scalability: Hour-long videos (3,600 frames) RL on a single node (8×A100s). 🖼️📝🎵 RL training for video, text, audio — works with VILA, Qwen series, and image/video generation models 🎨🎬 📄 Paper: 🎥 Demo: 💻 Code:

Yukang Chen

31,876 views • 1 year ago

excited to announce that Cloudflare Artifacts is now in open beta! with Artifacts, you can give every application and agent its own repo that you can manage programmatically plus you can use it to store and deploy your Workers code (and ofc it integrates with Workers Previews)

excited to announce that Cloudflare Artifacts is now in open beta! with Artifacts, you can give every application and agent its own repo that you can manage programmatically plus you can use it to store and deploy your Workers code (and ofc it integrates with Workers Previews)

dina kozlov 🐀

166,435 views • 1 month ago

train YOLOv9 on your dataset tutorial - run inference with a pre-trained COCO model - fine-tune model on custom dataset - evaluate the trained model - run inference with a fine-tuned model blogpost: ↓ read more

train YOLOv9 on your dataset tutorial - run inference with a pre-trained COCO model - fine-tune model on custom dataset - evaluate the trained model - run inference with a fine-tuned model blogpost: ↓ read more

SkalskiP

111,876 views • 2 years ago

OpenEnv has a new home: starting today, it's coordinated by a committee that includes Meta-PyTorch, Reflection, Unsloth, Modal, Prime Intellect, Nvidia, Mercor, Fleet AI, and Hugging Face frontier labs train their models and their harnesses together. Claude knows Claude Code. GPT-5.5 knows Codex. that's not an accident, it's training. open-source models deserve the same magic, but pulling that off requires infrastructure that belongs to everyone, not one lab OpenEnv is that layer. one api, any harness, any trainer, any environment rewards and training loops stay in TRL, Unsloth, wherever you already work. OpenEnv is the socket they all plug into get involved!

OpenEnv has a new home: starting today, it's coordinated by a committee that includes Meta-PyTorch, Reflection, Unsloth, Modal, Prime Intellect, Nvidia, Mercor, Fleet AI, and Hugging Face frontier labs train their models and their harnesses together. Claude knows Claude Code. GPT-5.5 knows Codex. that's not an accident, it's training. open-source models deserve the same magic, but pulling that off requires infrastructure that belongs to everyone, not one lab OpenEnv is that layer. one api, any harness, any trainer, any environment rewards and training loops stay in TRL, Unsloth, wherever you already work. OpenEnv is the socket they all plug into get involved!

Sergio Paniego

32,760 views • 5 months ago

Building good RL environments is hard. We're introducing a way to turn anything into RL-environments with REA using the open source AgentEnv framework from Scale Labs Any site, app, or game can now easily be turned into an env 😉

Building good RL environments is hard. We're introducing a way to turn anything into RL-environments with REA using the open source AgentEnv framework from Scale Labs Any site, app, or game can now easily be turned into an env 😉

reatools

54,812 views • 17 days ago

None of the video gen models do a real CRT terminal animation look. So I trained my own with fal. CRT-anim : open-source LoRA for LTX-2.3 22B. Runs on fal + ComfyUI.

None of the video gen models do a real CRT terminal animation look. So I trained my own with fal. CRT-anim : open-source LoRA for LTX-2.3 22B. Runs on fal + ComfyUI.

Lovis Odin

42,051 views • 6 months ago

We just released the world's first open-source humanoid physical strike AI! The AI is trained with large-scale self-play RL with a pre-trained ASE model from Jason Peng. Thank ZiyiBird for this amazing work.

We just released the world's first open-source humanoid physical strike AI! The AI is trained with large-scale self-play RL with a pre-trained ASE model from Jason Peng. Thank ZiyiBird for this amazing work.

Flood Sung

101,796 views • 3 years ago

📈 Scale open models with Hugging Face Text Generation Inference! 🚀 Customize with LoRA adapters ⚙️ Optimize with PEFT and TRL ☁️ Deploy on Google Cloud Platform with ease 🤖 Watch the demo from #GemmaDeveloperDay Tokyo →

📈 Scale open models with Hugging Face Text Generation Inference! 🚀 Customize with LoRA adapters ⚙️ Optimize with PEFT and TRL ☁️ Deploy on Google Cloud Platform with ease 🤖 Watch the demo from #GemmaDeveloperDay Tokyo →

Google for Developers

23,085 views • 1 year ago

Together Post-Training is live Turn open models into custom models you own, with SFT or RL. You define the data, rewards, environments and the training loop itself. We run the hard infrastructure underneath it, tuned for quality and speed.

Together Post-Training is live Turn open models into custom models you own, with SFT or RL. You define the data, rewards, environments and the training loop itself. We run the hard infrastructure underneath it, tuned for quality and speed.

Together AI

36,915 views • 18 days ago

Today we presented our work on Action Recognition with 3D pose and tracking at #CVPR. We also released our code, models, and dataset of 1.5 million human trajectories. Code: Project Page:

Today we presented our work on Action Recognition with 3D pose and tracking at #CVPR. We also released our code, models, and dataset of 1.5 million human trajectories. Code: Project Page:

Jathushan Rajasegaran

132,016 views • 3 years ago

Turned Scott Wu’s pub card game into a Math RL environment Simple rules and rewards, and plenty of headroom for small models to hillclimb on and built on OpenEnv 👀

Turned Scott Wu’s pub card game into a Math RL environment Simple rules and rewards, and plenty of headroom for small models to hillclimb on and built on OpenEnv 👀

Adithya S K

17,833 views • 15 days ago