Загрузка видео...

Не удалось загрузить видео

На главную

Introduce CoT-VLA – Visual Chain-of-Thought reasoning for Robot Foundation Models! 🤖 By leveraging next-frame prediction as visual chain-of-thought reasoning, CoT-VLA uses future prediction to guide action generation and unlock large-scale video data for training. #CVPR2025

qingqing_zhao_'s profile picture

Qingqing Zhao

2,607 subscribers

48,083 просмотров • 1 год назад •via X (Twitter)

Наука и технологии#CVPR2025
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Introducing Alpamayo 1.5. Based on community feedback, we’ve updated our 10B-parameter chain-of-thought reasoning VLA model to be a more interactive and steerable engine for autonomous vehicle development. Built on the Cosmos-Reason2 VLM backbone, this release adds support for navigation guidance and flexible camera configurations while providing new post-training scripts for model adaptation. 🤗 Learn more:
0:11

Introducing Alpamayo 1.5. Based on community feedback, we’ve updated our 10B-parameter chain-of-thought reasoning VLA model to be a more interactive and steerable engine for autonomous vehicle development. Built on the Cosmos-Reason2 VLM backbone, this release adds support for navigation guidance and flexible camera configurations while providing new post-training scripts for model adaptation. 🤗 Learn more:

NVIDIA DRIVE

50,693 просмотров • 2 месяцев назад

Zero-shot video reasoning (chain-of-frames) isn’t just for Veo3 — open-source models can understand and edit too! 🕹️ ChronoEdit brings temporal reasoning to image editing. 🔗
0:13

Zero-shot video reasoning (chain-of-frames) isn’t just for Veo3 — open-source models can understand and edit too! 🕹️ ChronoEdit brings temporal reasoning to image editing. 🔗

Xuanchi Ren

22,653 просмотров • 8 месяцев назад

🎉 Major Update! LobeChat now fully supports DeepSeek R1 and Thinking CoT in the V1.49.12! 🔮 Experience DeepSeek R1's powerful Chain of Thought capabilities on both Community editions and LobeChat Cloud( 🧠 Witness AI's reasoning process in real-time with transparent thought 💫 Making complex problem-solving clear and intuitive #LobeChat #DeepSeekR1 #AI
0:19

🎉 Major Update! LobeChat now fully supports DeepSeek R1 and Thinking CoT in the V1.49.12! 🔮 Experience DeepSeek R1's powerful Chain of Thought capabilities on both Community editions and LobeChat Cloud( 🧠 Witness AI's reasoning process in real-time with transparent thought 💫 Making complex problem-solving clear and intuitive #LobeChat #DeepSeekR1 #AI

LobeHub

26,285 просмотров • 1 год назад

Current Vision-Language-Action (VLA) paradigms in autonomous driving primarily rely on Imitation Learning (IL), which introduces inherent challenges such as distribution shift and causal confusion. Online Reinforcement Learning offers a promising pathway to address these issues through trial-and-error learning. However, applying online reinforcement learning to VLA models in autonomous driving is hindered by inefficient exploration in continuous action spaces. MindDrive, a VLA framework comprising a large language model (LLM) with two distinct sets of LoRA parameters. The one LLM serves as a Decision Expert for scenario reasoning and driving decision-making, while the other acts as an Action Expert that dynamically maps linguistic decisions into feasible trajectories. Paper Title: MindDrive: A Vision-Language-Action Model for Autonomous Driving via Project: Link:
0:12

Current Vision-Language-Action (VLA) paradigms in autonomous driving primarily rely on Imitation Learning (IL), which introduces inherent challenges such as distribution shift and causal confusion. Online Reinforcement Learning offers a promising pathway to address these issues through trial-and-error learning. However, applying online reinforcement learning to VLA models in autonomous driving is hindered by inefficient exploration in continuous action spaces. MindDrive, a VLA framework comprising a large language model (LLM) with two distinct sets of LoRA parameters. The one LLM serves as a Decision Expert for scenario reasoning and driving decision-making, while the other acts as an Action Expert that dynamically maps linguistic decisions into feasible trajectories. Paper Title: MindDrive: A Vision-Language-Action Model for Autonomous Driving via Project: Link:

AI Bites | YouTube Channel

43,451 просмотров • 4 месяцев назад

What is $REPPO? Reppo uses prediction markets to power AI data curation. Publishers submit data and domain experts stake $REPPO to assess quality within Datanets, programmable on-chain markets for any AI use case.
0:20

What is $REPPO? Reppo uses prediction markets to power AI data curation. Publishers submit data and domain experts stake $REPPO to assess quality within Datanets, programmable on-chain markets for any AI use case.

Kraken Listings

21,193 просмотров • 1 месяц назад

We’ve added a new prompt improver to the Anthropic Console. Take an existing prompt and Claude will automatically refine it with prompt engineering techniques like chain-of-thought reasoning.
0:17

We’ve added a new prompt improver to the Anthropic Console. Take an existing prompt and Claude will automatically refine it with prompt engineering techniques like chain-of-thought reasoning.

Anthropic

319,007 просмотров • 1 год назад

My favorite paper this year: "Video models are zero-shot learners and reasoners" It illustrates that video models show emergent visual reasoning at scale - they can solve vision tasks they weren't trained for. This may be the "GPT moment" for vision. Let's break it down 👇
0:19

My favorite paper this year: "Video models are zero-shot learners and reasoners" It illustrates that video models show emergent visual reasoning at scale - they can solve vision tasks they weren't trained for. This may be the "GPT moment" for vision. Let's break it down 👇

Justine Moore

185,001 просмотров • 5 месяцев назад

Laika AI x Nuklai Excited to announce our partnership with Nuklai Nuklai is an innovative data ecosystem that will fuel the next generation of AI and Large Language Models (LLMs). Together, we're revolutionizing on-chain data accessibility and monetization. By combining Laika AI's blockchain analytics with Nuklai's ecosystem, we're creating new opportunities for data utilization powered by $LKI.
0:10

Laika AI x Nuklai Excited to announce our partnership with Nuklai Nuklai is an innovative data ecosystem that will fuel the next generation of AI and Large Language Models (LLMs). Together, we're revolutionizing on-chain data accessibility and monetization. By combining Laika AI's blockchain analytics with Nuklai's ecosystem, we're creating new opportunities for data utilization powered by $LKI.

Laika AI

29,901 просмотров • 1 год назад

See how Gemini 3 Flash and Vision-Language-Action (VLA) models work together to teach a robot how to play the board game First Orchard. This project shows how to use Gemini as the “brain” for tracking game rules and state, while the VLA handles complex physical manipulations like picking and placing fruit 🍎
0:17

See how Gemini 3 Flash and Vision-Language-Action (VLA) models work together to teach a robot how to play the board game First Orchard. This project shows how to use Gemini as the “brain” for tracking game rules and state, while the VLA handles complex physical manipulations like picking and placing fruit 🍎

Google AI Developers

26,640 просмотров • 3 месяцев назад

🤖 NVIDIA’s Gr00t N1.5 is now available in LeRobot! This is the result of a great collaboration between the Hugging Face LeRobot team and NVIDIA Robotics ! Gr00t N1.5 highlights: 🦾 Cross-embodiment foundation model for robots 🧠 Multimodal inputs: vision, language, and proprioception 🪛Tested on the Libero benchmark and real-world hardware tasks 🌍Trained on real robot, synthetic, and internet-scale video data ⚙️ Flow matching action transformer for action prediction
0:17

🤖 NVIDIA’s Gr00t N1.5 is now available in LeRobot! This is the result of a great collaboration between the Hugging Face LeRobot team and NVIDIA Robotics ! Gr00t N1.5 highlights: 🦾 Cross-embodiment foundation model for robots 🧠 Multimodal inputs: vision, language, and proprioception 🪛Tested on the Libero benchmark and real-world hardware tasks 🌍Trained on real robot, synthetic, and internet-scale video data ⚙️ Flow matching action transformer for action prediction

LeRobot

115,194 просмотров • 7 месяцев назад

Artificial Intelligence (#AI) models that process and interpret visual data are called large vision models. These models, like large language models, are trained on large amounts of data. #midjourney #dalle #stablediffusion (1/8) 🧵 ⤵️
0:10

Artificial Intelligence (#AI) models that process and interpret visual data are called large vision models. These models, like large language models, are trained on large amounts of data. #midjourney #dalle #stablediffusion (1/8) 🧵 ⤵️

Nuklai

13,614 просмотров • 2 лет назад

Long-horizon visual goals remain surprisingly hard for robot manipulation. We introduce Act2Goal, a goal-conditioned policy that uses a visual world model to reason about progress toward a goal, and practice it autonomously in the real world.
0:20

Long-horizon visual goals remain surprisingly hard for robot manipulation. We introduce Act2Goal, a goal-conditioned policy that uses a visual world model to reason about progress toward a goal, and practice it autonomously in the real world.

Jianlan Luo

95,100 просмотров • 5 месяцев назад

Ever watched someone solve a hard math problem? Their first attempt is rarely perfect. They sketch ideas, cross things out, and try new angles. This process of exploration is key to human reasoning and our latest research formalizes this as Meta Chain-of-Thought (1/8) 🧵👇
0:12

Ever watched someone solve a hard math problem? Their first attempt is rarely perfect. They sketch ideas, cross things out, and try new angles. This process of exploration is key to human reasoning and our latest research formalizes this as Meta Chain-of-Thought (1/8) 🧵👇

SynthLabs

38,868 просмотров • 1 год назад

We're very excited to introduce TAPNext: a model that sets a new state-of-art for Tracking Any Point in videos, by formulating the task as Next Token Prediction. For more, see: 🧵
0:12

We're very excited to introduce TAPNext: a model that sets a new state-of-art for Tracking Any Point in videos, by formulating the task as Next Token Prediction. For more, see: 🧵

Carl Doersch

45,234 просмотров • 1 год назад

New Moondream 2B release! 🌛 visual reasoning (!!) 🌜better object detection 🌛 improved UI understanding 🌜40% faster text generation
0:13

New Moondream 2B release! 🌛 visual reasoning (!!) 🌜better object detection 🌛 improved UI understanding 🌜40% faster text generation

vik

83,838 просмотров • 11 месяцев назад

THE NEXT TOP VISUAL OF THIS GENERATION
0:15

THE NEXT TOP VISUAL OF THIS GENERATION

하투하 (semi-ia)

339,896 просмотров • 1 год назад

SOTA object detection with powerful visual reasoning: "skateboarder wearing checkered shirt".
0:10

SOTA object detection with powerful visual reasoning: "skateboarder wearing checkered shirt".

moondream

60,524 просмотров • 8 месяцев назад

Introducing Probable, an onchain prediction market on BNB Chain, incubated by PancakeSwap and YZi Labs Learn more →
0:10

Introducing Probable, an onchain prediction market on BNB Chain, incubated by PancakeSwap and YZi Labs Learn more →

Probable

919,857 просмотров • 6 месяцев назад

the texas chain saw massacre managed to be a visual and thematic masterpiece on a budget of less than $150k
0:19

the texas chain saw massacre managed to be a visual and thematic masterpiece on a budget of less than $150k

evil

80,647 просмотров • 4 месяцев назад