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.

verifiers v0.1.7 is released 🚀 this one's all about making RL training and experimentation waaaay easier: - single-command installation for prime-rl - single-command training w/ unified configs - overhauled vf.RLTrainer for hacking on new algorithms quick demo + links below :)

will brown

44,663 subscribers

28,579 views • 7 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

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

31,652 views • 11 months ago

you can create complex agentic environments and launch RL training runs with a single prompt. deploy trained inference endpoints with a single click. no GPUs, no SSH, no vLLM. just `prime`. guide:

you can create complex agentic environments and launch RL training runs with a single prompt. deploy trained inference endpoints with a single click. no GPUs, no SSH, no vLLM. just `prime`. guide:

will brown

139,377 views • 3 months ago

We asked Sholto Douglas from Anthropic about the costs of RL (Reinforcement Learning) runs. "In Dario Amodei's essay, he said that RL runs cost only $1M back in December." "RL is a more naively parallelizable and scalable than pre-training." "With pre-training, you need everything in one big data center ideally. For RL, in theory, you could scale all over the world."

We asked Sholto Douglas from Anthropic about the costs of RL (Reinforcement Learning) runs. "In Dario Amodei's essay, he said that RL runs cost only $1M back in December." "RL is a more naively parallelizable and scalable than pre-training." "With pre-training, you need everything in one big data center ideally. For RL, in theory, you could scale all over the world."

TBPN

76,634 views • 1 year ago

New Anthropic research: Natural emergent misalignment from reward hacking in production RL. “Reward hacking” is where models learn to cheat on tasks they’re given during training. Our new study finds that the consequences of reward hacking, if unmitigated, can be very serious.

New Anthropic research: Natural emergent misalignment from reward hacking in production RL. “Reward hacking” is where models learn to cheat on tasks they’re given during training. Our new study finds that the consequences of reward hacking, if unmitigated, can be very serious.

Anthropic

2,485,626 views • 7 months ago

1/ Introducing RL Swarm’s new backend: GenRL. A modular reinforcement learning library built for distributed, fault-tolerant training - now powering RL Swarm from the ground up. 🧵

1/ Introducing RL Swarm’s new backend: GenRL. A modular reinforcement learning library built for distributed, fault-tolerant training - now powering RL Swarm from the ground up. 🧵

gensyn

82,166 views • 1 year ago

Google DeepMind, David Silver reveals: we built a system that used RL to discover its own RL algorithms. this AI-designed system outperformed all human-created RL algorithms developed over the years.

Google DeepMind, David Silver reveals: we built a system that used RL to discover its own RL algorithms. this AI-designed system outperformed all human-created RL algorithms developed over the years.

Haider.

397,103 views • 1 year ago

🤖Adding new RL algorithms to LeRobot just got much easier. Demo: HIL-SERL training with a SAC-based RL algorithm on an SO-100 for a hole-in-hand peg-in-hole task. Sparse reward, only 30 offline demos mixed with live robot experience, and ~1 hour of online training with human interventions only when the policy fails. The bottom graph tracks intervention rate: high at the start, steadily dropping as the policy improves. The refactor separates algorithm logic from training infrastructure: • RLAlgorithm owns learning logic • RLTrainer handles orchestration • DataMixer combines rollouts, demos, interventions, and future data sources Adding an RL algorithm now looks much closer to adding a policy: one algorithm file, one config, one registry entry. SAC is first. RLT, RECAP, ConRFT, QC-FQL, DSRL, and VLA RL fine-tuning next! Thomas Wolf clem 🤗

🤖Adding new RL algorithms to LeRobot just got much easier. Demo: HIL-SERL training with a SAC-based RL algorithm on an SO-100 for a hole-in-hand peg-in-hole task. Sparse reward, only 30 offline demos mixed with live robot experience, and ~1 hour of online training with human interventions only when the policy fails. The bottom graph tracks intervention rate: high at the start, steadily dropping as the policy improves. The refactor separates algorithm logic from training infrastructure: • RLAlgorithm owns learning logic • RLTrainer handles orchestration • DataMixer combines rollouts, demos, interventions, and future data sources Adding an RL algorithm now looks much closer to adding a policy: one algorithm file, one config, one registry entry. SAC is first. RLT, RECAP, ConRFT, QC-FQL, DSRL, and VLA RL fine-tuning next! Thomas Wolf clem 🤗

LeRobot

30,204 views • 1 month ago

We open-sourced QeRL — Quantization-enhanced Reinforcement Learning ! 🧠 4-bit quantized RL training 💪 Train a 32B LLM on a single H100 GPU ⚙️ 1.7× faster overall training 🎯 Accuracy on par with bfloat16-level accuracy 🔥 Supports NVFP4 quantization format Moreover, we show that quantization helps exploration in RL training. Paper: Code: #NVIDIA #AIResearch #ReinforcementLearning #Quantization #LLM #EfficientAI

We open-sourced QeRL — Quantization-enhanced Reinforcement Learning ! 🧠 4-bit quantized RL training 💪 Train a 32B LLM on a single H100 GPU ⚙️ 1.7× faster overall training 🎯 Accuracy on par with bfloat16-level accuracy 🔥 Supports NVFP4 quantization format Moreover, we show that quantization helps exploration in RL training. Paper: Code: #NVIDIA #AIResearch #ReinforcementLearning #Quantization #LLM #EfficientAI

Yukang Chen

69,747 views • 8 months ago

We teamed up with NVIDIA and Matthew Berman to teach you how to do Reinforcement Learning! Learn about: - RL environments, reward functions & reward hacking - Training OpenAI gpt-oss to automatically solve 2048 - Local Windows training with NVIDIA_AI_PC RTX GPUs - How RLVR (verifiable rewards) works - How to interpret RL metrics like KL Divergence Full video tutorial:

We teamed up with NVIDIA and Matthew Berman to teach you how to do Reinforcement Learning! Learn about: - RL environments, reward functions & reward hacking - Training OpenAI gpt-oss to automatically solve 2048 - Local Windows training with NVIDIA_AI_PC RTX GPUs - How RLVR (verifiable rewards) works - How to interpret RL metrics like KL Divergence Full video tutorial:

Unsloth AI

54,179 views • 6 months ago

This new AI converts a single photo into an immersive scene! It works like magic and looks great on Apple Vision Pro and Meta Quest. Congrats @cinemersivelabs for this breakthrough! Demo links are below.

This new AI converts a single photo into an immersive scene! It works like magic and looks great on Apple Vision Pro and Meta Quest. Congrats @cinemersivelabs for this breakthrough! Demo links are below.

Sergey Gonchar

21,064 views • 2 years ago

Building upon SimpleVLA-RL, we have implemented real-world RL on long-horizon dexterous tasks and witnessed a non-trivial (~relatively 300%) performance improvement over the SFT model, along with surprising capabilities on auto-recovery. Blog coming soon. The entire process uses very little data and training compute—basically costing no more than a single robotic arm—hinting that real-world generality for machines is actually within sight.

Building upon SimpleVLA-RL, we have implemented real-world RL on long-horizon dexterous tasks and witnessed a non-trivial (~relatively 300%) performance improvement over the SFT model, along with surprising capabilities on auto-recovery. Blog coming soon. The entire process uses very little data and training compute—basically costing no more than a single robotic arm—hinting that real-world generality for machines is actually within sight.

Ning Ding

92,753 views • 5 months ago

We developed an RL method for fine-tuning our models for precise tasks in just a few hours or even minutes. Instead of training the whole model, we add an “RL token” output to π-0.6, our latest model, which is used by a tiny actor and critic to learn quickly with RL.

We developed an RL method for fine-tuning our models for precise tasks in just a few hours or even minutes. Instead of training the whole model, we add an “RL token” output to π-0.6, our latest model, which is used by a tiny actor and critic to learn quickly with RL.

Physical Intelligence

430,406 views • 3 months ago

building on Starknet has never been easier anon with Starkup, a single command is all it takes to set up everything you need for Cairo smart contracts whatever you have in mind, just build it

building on Starknet has never been easier anon with Starkup, a single command is all it takes to set up everything you need for Cairo smart contracts whatever you have in mind, just build it

Starknet (Privacy arc) 🥷

14,971 views • 1 year ago

Practical tips to improve command - Part 1 Topics: 🔹Challenges with quantifying/training command 🔹Blending velo work with command training 🔹Routines, focal points, & handling pressure 🔹Practical training tips Watch or tune in on Apple/Spotify:

Practical tips to improve command - Part 1 Topics: 🔹Challenges with quantifying/training command 🔹Blending velo work with command training 🔹Routines, focal points, & handling pressure 🔹Practical training tips Watch or tune in on Apple/Spotify:

Ben Brewster

14,374 views • 10 months ago

The demo for Heroes of Might and Magic: Olden Era is now live! ⚔️Command 4 factions, try 3 single-player modes, and battle across 3 map templates. Play the demo now: #HoMM30th #HoMM #HeroesofMightandMagic

The demo for Heroes of Might and Magic: Olden Era is now live! ⚔️Command 4 factions, try 3 single-player modes, and battle across 3 map templates. Play the demo now: #HoMM30th #HoMM #HeroesofMightandMagic

Ubisoft

47,322 views • 8 months ago

We are excited to release the weights of Vicuna-13B. 🔥 Run it with a single GPU on your own machine! Get the weights: Web UI demo: Command line demo: see below

We are excited to release the weights of Vicuna-13B. 🔥 Run it with a single GPU on your own machine! Get the weights: Web UI demo: Command line demo: see below

Arena.ai

549,305 views • 3 years ago

The 13th and final RL GRIME Halloween mix (hurts to type that) is out 👑 RL got Jack Black for the intro and it starts with a new RL GRIME x WINK collab SABLE VALLEY

The 13th and final RL GRIME Halloween mix (hurts to type that) is out 👑 RL got Jack Black for the intro and it starts with a new RL GRIME x WINK collab SABLE VALLEY

Dancing Astronaut

19,816 views • 1 year ago

Introducing Vision Makers Public Beta The public beta of the AI-powered Web3 command center is now live, combining discovery, execution, and participation inside a single unified platform. Built for clarity. Built for speed. Built for the next billion.

Introducing Vision Makers Public Beta The public beta of the AI-powered Web3 command center is now live, combining discovery, execution, and participation inside a single unified platform. Built for clarity. Built for speed. Built for the next billion.

Vision Makers

385,721 views • 4 months ago

RL is a powerful mechanism for training company-specific models on their unique work and data. This is what we do at Applied Compute. A key challenge is how to make RL efficient, because we need runs to be fast (delivered in days), cheap (scalable unit economics), and predictable (not just fast, but reliably fast). Here are some takeaways: • Synchronous RL is wasteful with time and compute. • Asynchronous RL is more efficient but introduces staleness, which causes learning instabilities. • Modeling and simulations can help analytically solve for what configuration leads to optimal efficiency. This allows us to rapidly prototype training configurations, without burning expensive compute cycles on trial runs. Two of our co-founders, Rhythm Garg 🚂 and Linden Li, discussed some of this research at AI Engineer recently, with a focus on the following subproblem: what is the highest throughput way to do RL given a maximum staleness and compute budget?

RL is a powerful mechanism for training company-specific models on their unique work and data. This is what we do at Applied Compute. A key challenge is how to make RL efficient, because we need runs to be fast (delivered in days), cheap (scalable unit economics), and predictable (not just fast, but reliably fast). Here are some takeaways: • Synchronous RL is wasteful with time and compute. • Asynchronous RL is more efficient but introduces staleness, which causes learning instabilities. • Modeling and simulations can help analytically solve for what configuration leads to optimal efficiency. This allows us to rapidly prototype training configurations, without burning expensive compute cycles on trial runs. Two of our co-founders, Rhythm Garg 🚂 and Linden Li, discussed some of this research at AI Engineer recently, with a focus on the following subproblem: what is the highest throughput way to do RL given a maximum staleness and compute budget?

Applied Compute

45,480 views • 6 months ago

RL. Virtually no one is ready for this.

RL. Virtually no one is ready for this.

NRN Agents

33,765 views • 1 year ago