Загрузка видео...

Не удалось загрузить видео

На главную

Our embodied reasoning models are getting even better.

ArmenAgha's profile picture

Armen Aghajanyan

16,157 subscribers

14,465 просмотров • 25 дней назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Models are getting good with CAD Playing around with geometric reasoning for assembly sequences.
0:34

Models are getting good with CAD Playing around with geometric reasoning for assembly sequences.

Mikameel ᯅ

75,587 просмотров • 17 дней назад

We teamed up with Boston Dynamics to power their robot Spot with Gemini Robotics embodied reasoning models. This means it can better understand its surroundings, identify objects and follow simple commands - like tidying up a room.
0:37

We teamed up with Boston Dynamics to power their robot Spot with Gemini Robotics embodied reasoning models. This means it can better understand its surroundings, identify objects and follow simple commands - like tidying up a room.

Google DeepMind

153,265 просмотров • 4 месяцев назад

Today we're releasing Perceptron Mk1: frontier video and embodied reasoning.
0:49

Today we're releasing Perceptron Mk1: frontier video and embodied reasoning.

Perceptron AI

1,303,629 просмотров • 3 месяцев назад

Fursuits are Getting and Looking EVEN BETTER! #fursuit #furries #furryfandom
0:35

Sensitive content

Fursuits are Getting and Looking EVEN BETTER! #fursuit #furries #furryfandom

BetaEtaDelota

62,280 просмотров • 1 год назад

We are releasing Star Elastic - turn ONE reasoning LLM into MANY sizes with a single post-training run. 360× cheaper than pretraining a family of models. 7× better than SOTA compression. Split reasoning capability. Plus elastic budget control that beats the accuracy-latency frontier. Paper: HF models: Thread 👇
0:42

We are releasing Star Elastic - turn ONE reasoning LLM into MANY sizes with a single post-training run. 360× cheaper than pretraining a family of models. 7× better than SOTA compression. Split reasoning capability. Plus elastic budget control that beats the accuracy-latency frontier. Paper: HF models: Thread 👇

Pavlo Molchanov

22,222 просмотров • 3 месяцев назад

Chain-of-thought reasoning is a powerful tool to enable language models to work through complex problems. Can we use this with robots? With embodied chain-of-thought, vision-language-action (VLA) models can think through perception and planning! A 🧵👇
1:39

Chain-of-thought reasoning is a powerful tool to enable language models to work through complex problems. Can we use this with robots? With embodied chain-of-thought, vision-language-action (VLA) models can think through perception and planning! A 🧵👇

Sergey Levine

30,479 просмотров • 2 лет назад

We asked NVIDIA GTC attendees for their first impressions after interacting with OpenMind robots. Robots will only get smarter from here, and our models are only getting better.
1:49

We asked NVIDIA GTC attendees for their first impressions after interacting with OpenMind robots. Robots will only get smarter from here, and our models are only getting better.

OpenMind

15,500 просмотров • 4 месяцев назад

Better answers = better reasoning
0:21

Better answers = better reasoning

dominik kundel

109,279 просмотров • 1 месяц назад

Noam Brown from OpenAI just dropped a truth bomb:⁣ ⁣ "Your fancy AI scaffolds will be washed away by scale"⁣ ⁣ Routers, harnesses, complex agentic systems... all getting replaced by models that just work better out of the box⁣ ⁣ The reasoning models already proved this
1:33

Noam Brown from OpenAI just dropped a truth bomb:⁣ ⁣ "Your fancy AI scaffolds will be washed away by scale"⁣ ⁣ Routers, harnesses, complex agentic systems... all getting replaced by models that just work better out of the box⁣ ⁣ The reasoning models already proved this

Latent.Space

208,301 просмотров • 1 год назад

.Trenton Bricken explains how we know LLMs are actually generalizing - aka they're not just stochastic parrots: - Training models on code makes them better at reasoning in language. - Models fine tuned on math problems become better at entity detection. - We can just straightforwardly read the world-models developed by smaller NNs which are easier to interpret (Othello). Transfer learning shows models are developing a deeper understanding of their data. Full episode out Thursday.
1:37

.Trenton Bricken explains how we know LLMs are actually generalizing - aka they're not just stochastic parrots: - Training models on code makes them better at reasoning in language. - Models fine tuned on math problems become better at entity detection. - We can just straightforwardly read the world-models developed by smaller NNs which are easier to interpret (Othello). Transfer learning shows models are developing a deeper understanding of their data. Full episode out Thursday.

Dwarkesh Patel

237,812 просмотров • 2 лет назад

RynnWorld-4D 4D Embodied World Models for Robotic Manipulation
1:41

RynnWorld-4D 4D Embodied World Models for Robotic Manipulation

AK

33,467 просмотров • 1 месяц назад

We're releasing HY-Embodied-0.5, a family of foundation models for real-world embodied agents. The 2B model is now open source. It strengthens spatial-temporal perception and embodied reasoning for prediction, interaction, and planning. 🤖 The suite includes: 🔹 2B for edge deployment 🔹 32B for complex reasoning Key innovations: 🔹 Mixture-of-Transformers (MoT) architecture for modality-specific computation 🔹 Latent tokens for improved perceptual representation 🔹 Self-evolving post-training 🔹 On-policy distillation from large to small models Across 22 benchmarks, the 2B model outperforms similarly sized SOTA systems on 16 tasks. The 32B model approaches frontier-level performance. 🔗 GitHub: 🤗 Hugging Face:
0:54

We're releasing HY-Embodied-0.5, a family of foundation models for real-world embodied agents. The 2B model is now open source. It strengthens spatial-temporal perception and embodied reasoning for prediction, interaction, and planning. 🤖 The suite includes: 🔹 2B for edge deployment 🔹 32B for complex reasoning Key innovations: 🔹 Mixture-of-Transformers (MoT) architecture for modality-specific computation 🔹 Latent tokens for improved perceptual representation 🔹 Self-evolving post-training 🔹 On-policy distillation from large to small models Across 22 benchmarks, the 2B model outperforms similarly sized SOTA systems on 16 tasks. The 32B model approaches frontier-level performance. 🔗 GitHub: 🤗 Hugging Face:

Tencent Hy

34,317 просмотров • 4 месяцев назад

Big Models. Complex Projects. Running Local. Our 128GB agent computers are now regularly loading and running large models like Step 3.7 and Qwen 3.5. 122B for heavy reasoning and overnight work using Ryzen AI Max+ 395 processors.
1:16

Big Models. Complex Projects. Running Local. Our 128GB agent computers are now regularly loading and running large models like Step 3.7 and Qwen 3.5. 122B for heavy reasoning and overnight work using Ryzen AI Max+ 395 processors.

AMD Ryzen

34,670 просмотров • 2 месяцев назад

While others fight, we ship 🚀 Agno’s ReasoningTools are now live on the Playground — giving non-reasoning models the ability to "think", "analyze", and outperform Reasoning Models on Agentic workloads. If you haven't tried `ReasoningTools` yet - you definitely should 👇
1:18

While others fight, we ship 🚀 Agno’s ReasoningTools are now live on the Playground — giving non-reasoning models the ability to "think", "analyze", and outperform Reasoning Models on Agentic workloads. If you haven't tried `ReasoningTools` yet - you definitely should 👇

Ashpreet Bedi

27,864 просмотров • 1 год назад

Meet Gemini Robotics: our latest AI models designed for a new generation of helpful robots. 🤖 Based on Gemini 2.0, they bring capabilities such as better reasoning, interactivity, dexterity and generalization into the physical world. 🧵
1:29

Meet Gemini Robotics: our latest AI models designed for a new generation of helpful robots. 🤖 Based on Gemini 2.0, they bring capabilities such as better reasoning, interactivity, dexterity and generalization into the physical world. 🧵

Google DeepMind

642,824 просмотров • 1 год назад

Hegseth on Iran: Our defense is getting better, and their offense capabilities are diminishing.
0:25

Hegseth on Iran: Our defense is getting better, and their offense capabilities are diminishing.

Clash Report

31,809 просмотров • 5 месяцев назад