Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

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 :)

willccbb's profile picture

will brown

44,663 subscribers

28,579 görüntüleme • 1 yıl önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

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:
1:19

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

31,994 görüntüleme • 1 yıl önce

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:
9:59

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

139,747 görüntüleme • 8 ay önce

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."
0:37

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

76,696 görüntüleme • 1 yıl önce

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.
51:56

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

2,623,747 görüntüleme • 11 ay önce

Introducing RL Environment Explorer 🧭 There are now 12M+ RL task entries across RL environments on the Hugging Face Hub. You can now explore, visualize, and run RL environments across: OpenEnv • Harbor • MiMo • Verifiers • NeMo Gym All in one place
0:29

Introducing RL Environment Explorer 🧭 There are now 12M+ RL task entries across RL environments on the Hugging Face Hub. You can now explore, visualize, and run RL environments across: OpenEnv • Harbor • MiMo • Verifiers • NeMo Gym All in one place

Adithya S K

27,777 görüntüleme • 1 ay önce

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. 🧵
0:50

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

82,215 görüntüleme • 1 yıl önce

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.
0:37

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.

397,296 görüntüleme • 1 yıl önce

Introducing Prime Sandboxes: MicroVM sandboxes purpose-built for RL training. Model training requires running tens of thousands of concurrent sandboxes, leading to complex and costly configuration. We built Prime Sandboxes for our own team. Today we're releasing them publicly.
0:26

Introducing Prime Sandboxes: MicroVM sandboxes purpose-built for RL training. Model training requires running tens of thousands of concurrent sandboxes, leading to complex and costly configuration. We built Prime Sandboxes for our own team. Today we're releasing them publicly.

Prime Intellect

120,791 görüntüleme • 1 ay önce

Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve them without rebuilding them.:
0:20

Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve them without rebuilding them.:

Microsoft Research

18,815 görüntüleme • 1 ay önce

🤖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 🤗
0:57

🤖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

31,237 görüntüleme • 6 ay önce

RL post-training on Macs 14 Macs across 4 countries generate every rollout for the run. Everything's running over the internet. No wire between any of them. As far as we can tell, this is the first RL post-training run with its whole rollout fleet on consumer Macs.
0:26

RL post-training on Macs 14 Macs across 4 countries generate every rollout for the run. Everything's running over the internet. No wire between any of them. As far as we can tell, this is the first RL post-training run with its whole rollout fleet on consumer Macs.

Pluralis Research

35,721 görüntüleme • 3 ay önce

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
1:45

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

69,896 görüntüleme • 1 yıl önce

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:
5:13

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

54,307 görüntüleme • 10 ay önce

In my understanding - a big part of why frontier models are becoming smarter and adaptive is that they are learning to mimic an RL process. Fascinating new research showing a link between increased RL training and reward-seeking behaviour just dropped from in collaboration with OpenAI. They investigated a checkpoint from a capabilities-focused OpenAI o3 RL run (without safety training) and found that RL grader preferences often overruled OpenAI leadership preferences.
2:13

In my understanding - a big part of why frontier models are becoming smarter and adaptive is that they are learning to mimic an RL process. Fascinating new research showing a link between increased RL training and reward-seeking behaviour just dropped from in collaboration with OpenAI. They investigated a checkpoint from a capabilities-focused OpenAI o3 RL run (without safety training) and found that RL grader preferences often overruled OpenAI leadership preferences.

Machine Learning Street Talk

12,409 görüntüleme • 3 ay önce

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.
0:56

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

21,245 görüntüleme • 2 yıl önce

It's time to rethink RL. Translating real world use into model improvements requires redesigning post-training algorithms for non-verifiable, per token rewards. At AI Engineer 🔜 NYC 🗽 's World Fair, we share our insights into scaling algorithms like SDPO for continual learning.
23:02

It's time to rethink RL. Translating real world use into model improvements requires redesigning post-training algorithms for non-verifiable, per token rewards. At AI Engineer 🔜 NYC 🗽 's World Fair, we share our insights into scaling algorithms like SDPO for continual learning.

Trajectory

69,205 görüntüleme • 2 ay önce

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
0:20

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 görüntüleme • 2 ay önce

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.
0:20

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

93,483 görüntüleme • 10 ay önce

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.
2:15

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

454,790 görüntüleme • 7 ay önce

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
1:11

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

14,987 görüntüleme • 1 yıl önce