Загрузка видео...

Не удалось загрузить видео

На главную

🤔Want a principled way to RL your diffusion model? Check Data-regularized Reinforcement Learning (DDRL)! Post-train NVIDIA #Cosmos World Foundation models with a million GPU hours! 🤯 Novel formulation ➡️ Theoretically integrates SFT into RL ➡️ Robust to Reward Hacking 🛑 Details: #DDRL #Diffusion #RL #NVIDIA #Cosmos

haotian_yeee's profile picture

Haotian Ye

1,075 subscribers

77,657 просмотров • 7 месяцев назад •via X (Twitter)

#Cosmos
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

NEWS: Nvidia has just introduced "Cosmos," a world foundation model created to understand the physical world. The model can generate synthetic data to train robotics.
2:34

NEWS: Nvidia has just introduced "Cosmos," a world foundation model created to understand the physical world. The model can generate synthetic data to train robotics.

Sawyer Merritt

254,296 просмотров • 1 год назад

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

54,179 просмотров • 6 месяцев назад

The best way to get robust, high-quality robot performance is through reinforcement learning; but RL in either the real world or a traditional simulation has lots of limitations. Instead, Jiazhi Yang in RISE does RL in a compositional world model. Learn more ->
1:15

The best way to get robust, high-quality robot performance is through reinforcement learning; but RL in either the real world or a traditional simulation has lots of limitations. Instead, Jiazhi Yang in RISE does RL in a compositional world model. Learn more ->

Chris Paxton

33,766 просмотров • 27 дней назад

NVIDIA just introduced Cosmos, a platform for world foundation models designed for robotics. ⦿ It features advanced tokenizers, an AI-accelerated data pipeline, and integration with NVIDIA Omniverse. Humanoid makers 1X, Figure, and Agility are among the first to adopt Cosmos. ⦿ Cosmos generates synthetic, physics-based data, accelerating model training and customization. ⦿ It also features a CUDA-accelerated data processing pipeline that enables developers to process, curate, and label 20 million hours of videos in 14 days using the NVIDIA Blackwell platform.
8:02

NVIDIA just introduced Cosmos, a platform for world foundation models designed for robotics. ⦿ It features advanced tokenizers, an AI-accelerated data pipeline, and integration with NVIDIA Omniverse. Humanoid makers 1X, Figure, and Agility are among the first to adopt Cosmos. ⦿ Cosmos generates synthetic, physics-based data, accelerating model training and customization. ⦿ It also features a CUDA-accelerated data processing pipeline that enables developers to process, curate, and label 20 million hours of videos in 14 days using the NVIDIA Blackwell platform.

The Humanoid Hub

129,383 просмотров • 1 год назад

RL-100 Performant Robotic Manipulation with Real-World Reinforcement Learning
1:37

RL-100 Performant Robotic Manipulation with Real-World Reinforcement Learning

AK

15,364 просмотров • 8 месяцев назад

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

69,747 просмотров • 8 месяцев назад

NVIDIA Cosmos 3 launches with a full model family — Cosmos Super for highest-accuracy robotics and AV post-training, Cosmos Nano for high-speed video and action reasoning, and Cosmos Edge for real-time edge inference. Read the release ➡️
0:35

NVIDIA Cosmos 3 launches with a full model family — Cosmos Super for highest-accuracy robotics and AV post-training, Cosmos Nano for high-speed video and action reasoning, and Cosmos Edge for real-time edge inference. Read the release ➡️

NVIDIA Newsroom

46,581 просмотров • 1 месяц назад

If you have a policy that uses diffusion/flow (e.g. diffusion VLA), you can run RL where the actor chooses the noise, which is then denoised by the policy to produce an action. This method, which we call diffusion steering (DSRL), leads to a remarkably efficient RL method! 🧵👇
0:39

If you have a policy that uses diffusion/flow (e.g. diffusion VLA), you can run RL where the actor chooses the noise, which is then denoised by the policy to produce an action. This method, which we call diffusion steering (DSRL), leads to a remarkably efficient RL method! 🧵👇

Sergey Levine

152,824 просмотров • 1 год назад

Hiring RL Engineer! Started off as a curious project at Lossfunk to push the boundaries of LLMs in social reasoning - we are now building RL environments, data, and benchmarks to simulate more real-world scenarios. If you want to train SoTA RL models over multi-GPUs (H200s/B200s) to unlock next AI frontier, this is for you.
1:21

Hiring RL Engineer! Started off as a curious project at Lossfunk to push the boundaries of LLMs in social reasoning - we are now building RL environments, data, and benchmarks to simulate more real-world scenarios. If you want to train SoTA RL models over multi-GPUs (H200s/B200s) to unlock next AI frontier, this is for you.

Satpal Singh Rathore

45,915 просмотров • 11 месяцев назад

RobotMDM, by Disney Research, combines diffusion-based motion generation with RL to produce physics-aware humanoid motions from text prompts. Trained on human motion data with a reward surrogate for physical feasibility, it ensures realistic motions.
0:56

RobotMDM, by Disney Research, combines diffusion-based motion generation with RL to produce physics-aware humanoid motions from text prompts. Trained on human motion data with a reward surrogate for physical feasibility, it ensures realistic motions.

The Humanoid Hub

22,943 просмотров • 1 год назад

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

76,634 просмотров • 1 год назад

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

431,973 просмотров • 3 месяцев назад

Nvidia just announced Align Your Gaussians Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models
0:22

Nvidia just announced Align Your Gaussians Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models

AK

131,322 просмотров • 2 лет назад

Our course recommendation of the day is “Post-training of LLMs, ” where you’ll learn how to customize pre-trained language models using Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL). You'll learn when to use each method, how to curate training data, and implement them in code to shape model behavior effectively. Enroll here:
1:05

Our course recommendation of the day is “Post-training of LLMs, ” where you’ll learn how to customize pre-trained language models using Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL). You'll learn when to use each method, how to curate training data, and implement them in code to shape model behavior effectively. Enroll here:

DeepLearning.AI

29,369 просмотров • 9 месяцев назад

Using our brain simulator, we’ve trained a reinforcement learning agent to maximize bits per second. Here is the RL policy converting brain data to cursor control in simulation:
0:29

Using our brain simulator, we’ve trained a reinforcement learning agent to maximize bits per second. Here is the RL policy converting brain data to cursor control in simulation:

Neuralink

18,410 просмотров • 1 год назад

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

82,174 просмотров • 1 год назад

Presenting DemoDiffusion: An extremely simple approach enabling a pre-trained 'generalist' diffusion policy to follow a human-demonstration for a novel task during inference One-shot human imitation *without* requiring any paired human-robot data or online RL 🙂 1/n
0:30

Presenting DemoDiffusion: An extremely simple approach enabling a pre-trained 'generalist' diffusion policy to follow a human-demonstration for a novel task during inference One-shot human imitation *without* requiring any paired human-robot data or online RL 🙂 1/n

Homanga Bharadhwaj

32,830 просмотров • 1 год назад

Want to scale RL with your shiny new GPU? 🚀 In our ICML24 Oral we find that RL algorithms hit a barrier when data is scaled up. Our new algorithm, SAPG, proposes a simple fix. It scales to 25k envs and solves hard tasks where PPO makes no progress. 1/n
1:24

Want to scale RL with your shiny new GPU? 🚀 In our ICML24 Oral we find that RL algorithms hit a barrier when data is scaled up. Our new algorithm, SAPG, proposes a simple fix. It scales to 25k envs and solves hard tasks where PPO makes no progress. 1/n

Ananye Agarwal

64,403 просмотров • 1 год назад