Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

FoundationMotion Auto-Labeling and Reasoning about Spatial Movement in Videos

_akhaliq's profile picture

AK

504,368 subscribers

18,074 Aufrufe • vor 7 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Gemini 2.5 is driving new advancements in robotics with its strong coding, spatial reasoning, and multimodal capabilities. 🦾
0:20

Gemini 2.5 is driving new advancements in robotics with its strong coding, spatial reasoning, and multimodal capabilities. 🦾

Google AI Developers

36,119 Aufrufe • vor 1 Jahr

Can VLMs build Spatial Mental Models like humans? Reasoning from limited views? Reasoning from partial observations? Reasoning about unseen objects behind furniture / beyond current view? Check out MindCube! 🌐 📰 🤗 👩‍💻
1:26

Can VLMs build Spatial Mental Models like humans? Reasoning from limited views? Reasoning from partial observations? Reasoning about unseen objects behind furniture / beyond current view? Check out MindCube! 🌐 📰 🤗 👩‍💻

Manling Li

40,959 Aufrufe • vor 1 Jahr

Scaling 3D scene data is a long-standing challenge in scene understanding, spatial reasoning, and robotics. Since scanning, reconstruction, and labeling are so labor-intensive, data scarcity has remained a major bottleneck. 🛑 To solve this, we propose SceneVerse++: Lifting Unlabeled Internet-level Data for 3D Scene Understanding (CVPR 2026). By reconstructing internet videos and annotating 3D scenes automatically, we’ve created a massive real-world dataset for end-to-end understanding. 🌐📐 SceneVerse++ makes it easy to scale "in-the-wild" 3D scenes toward more capable spatial reasoning systems. This significantly promotes progress in 3D VQA, visual navigation, and broader tasks in Embodied AI and Robotics. 🤖🦾 We are fully open-sourced! Check out the paper, code, and data here: 🌐 Project: 📄 Paper: 📊 Dataset: Code:
2:13

Scaling 3D scene data is a long-standing challenge in scene understanding, spatial reasoning, and robotics. Since scanning, reconstruction, and labeling are so labor-intensive, data scarcity has remained a major bottleneck. 🛑 To solve this, we propose SceneVerse++: Lifting Unlabeled Internet-level Data for 3D Scene Understanding (CVPR 2026). By reconstructing internet videos and annotating 3D scenes automatically, we’ve created a massive real-world dataset for end-to-end understanding. 🌐📐 SceneVerse++ makes it easy to scale "in-the-wild" 3D scenes toward more capable spatial reasoning systems. This significantly promotes progress in 3D VQA, visual navigation, and broader tasks in Embodied AI and Robotics. 🤖🦾 We are fully open-sourced! Check out the paper, code, and data here: 🌐 Project: 📄 Paper: 📊 Dataset: Code:

Siyuan Huang

12,612 Aufrufe • vor 3 Monaten

We present VLM-3R: a Vision-Language Model capable of 3D spatial reasoning from monocular video, grounding visual cues, geometry, and camera motion. ✅ No depth sensor ✅ No pre-built 3D maps ✅ End-to-end spatial + temporal reasoning 🔗 Code & benchmark: #VLM #3DVision #LLMs
0:20

We present VLM-3R: a Vision-Language Model capable of 3D spatial reasoning from monocular video, grounding visual cues, geometry, and camera motion. ✅ No depth sensor ✅ No pre-built 3D maps ✅ End-to-end spatial + temporal reasoning 🔗 Code & benchmark: #VLM #3DVision #LLMs

Zhiwen(Aaron) Fan

14,895 Aufrufe • vor 1 Jahr

public beta is now live! we added in new features such as an ai that can answer questions about your inbox, mass unsubscribe, auto-labeling, auto-summarizations, and a totally new ui! no more waitlist, checkout :)
1:04

public beta is now live! we added in new features such as an ai that can answer questions about your inbox, mass unsubscribe, auto-labeling, auto-summarizations, and a totally new ui! no more waitlist, checkout :)

nizzy

129,292 Aufrufe • vor 1 Jahr

Spatial photos and videos on Apple Vision Pro are like nothing you’ve ever seen before. Check out these tips for capturing spatial photos and spatial videos with iPhone 16 Pro, iPhone 16, and iPhone 15 Pro.
1:35

Spatial photos and videos on Apple Vision Pro are like nothing you’ve ever seen before. Check out these tips for capturing spatial photos and spatial videos with iPhone 16 Pro, iPhone 16, and iPhone 15 Pro.

Apple Support

53,442 Aufrufe • vor 1 Jahr

Always thinking in absolute and generalizing about everything shows level reasoning
1:19

Always thinking in absolute and generalizing about everything shows level reasoning

Dr. God Abeg ooo

19,310 Aufrufe • vor 3 Monaten

this is a must have app on the Apple Vision Pro Spatial Media Toolkit turns your normal photos and videos into spatial photos and videos. It’s hypnotic
0:30

this is a must have app on the Apple Vision Pro Spatial Media Toolkit turns your normal photos and videos into spatial photos and videos. It’s hypnotic

Justin Ryan

49,150 Aufrufe • vor 2 Jahren

watch this incredible teraminx puzzle, it really tests your spatial reasoning and patience. It's so satisfying to see it succeed credit TT neanto_
1:06

watch this incredible teraminx puzzle, it really tests your spatial reasoning and patience. It's so satisfying to see it succeed credit TT neanto_

auuuummmm

350,309 Aufrufe • vor 1 Jahr

Spatial reasoning is a major challenge for the foundation models today, even in simple tasks like arranging objects in 3D space. #CVPR2025 Introducing LayoutVLM, a differentiable optimization framework that uses VLM to spatially reason about diverse scene layouts from unlabeled assets and open-ended language instructions 1/n
0:45

Spatial reasoning is a major challenge for the foundation models today, even in simple tasks like arranging objects in 3D space. #CVPR2025 Introducing LayoutVLM, a differentiable optimization framework that uses VLM to spatially reason about diverse scene layouts from unlabeled assets and open-ended language instructions 1/n

Fan-Yun Sun

92,612 Aufrufe • vor 1 Jahr

Joscha Bach says current AI doesn't need to be conscious to execute tasks, but it must simulate reality to understand it LLMs don't just predict words To solve complex problems, they build deep internal models of spatial reasoning and the human theory of mind "that is why AI can talk about reasoning and mental states"
2:07

Joscha Bach says current AI doesn't need to be conscious to execute tasks, but it must simulate reality to understand it LLMs don't just predict words To solve complex problems, they build deep internal models of spatial reasoning and the human theory of mind "that is why AI can talk about reasoning and mental states"

Haider.

17,743 Aufrufe • vor 5 Monaten

Introducing General Intuition and our $133.7M Seed from Khosla Ventures, General Catalyst, and Raine. We build foundation models and general agents for environments that require deep spatial and temporal reasoning.
0:27

Introducing General Intuition and our $133.7M Seed from Khosla Ventures, General Catalyst, and Raine. We build foundation models and general agents for environments that require deep spatial and temporal reasoning.

General Intuition

2,282,073 Aufrufe • vor 10 Monaten

Using the floor is one of the best types of resistance training a child can do...strength development, coordination and spatial awareness all in one movement... #LTAD
0:30

Using the floor is one of the best types of resistance training a child can do...strength development, coordination and spatial awareness all in one movement... #LTAD

Jeremy Frisch

10,393 Aufrufe • vor 1 Jahr

Announcing the Video Editor in Spatial Media Toolkit. Effortlessly create spatial videos or photo slideshows with music, all privately on-device. Seamlessly integrates with our powerful 2D-to-3D conversion for stunning spatial storytelling.
0:47

Announcing the Video Editor in Spatial Media Toolkit. Effortlessly create spatial videos or photo slideshows with music, all privately on-device. Seamlessly integrates with our powerful 2D-to-3D conversion for stunning spatial storytelling.

Ryan Gordon

12,353 Aufrufe • vor 1 Jahr

We've solved another piece of the generalist gaming agent puzzle! Mario requires different skills than Pokemon: reactive navigation, spatial reasoning, and safe exploration rather than long-term memory and zero-sum reasoning. Check out our new paper on finetuning VLMs to beat Mario via PPO. 👇
0:43

We've solved another piece of the generalist gaming agent puzzle! Mario requires different skills than Pokemon: reactive navigation, spatial reasoning, and safe exploration rather than long-term memory and zero-sum reasoning. Check out our new paper on finetuning VLMs to beat Mario via PPO. 👇

Seth Karten

80,747 Aufrufe • vor 3 Monaten

My reaction to Ezra Klein and Ta-Nehisi Coates dismissing Charlie Kirk without engaging with his actual arguments — labeling him a “hate monger” while ignoring the evidence. 👉 Kirk’s approach is about reasoning, not screaming values — and challenges the left’s refusal to confront ideas directly. #CharlieKirk #MediaBias #PoliticsPodcast
2:30

My reaction to Ezra Klein and Ta-Nehisi Coates dismissing Charlie Kirk without engaging with his actual arguments — labeling him a “hate monger” while ignoring the evidence. 👉 Kirk’s approach is about reasoning, not screaming values — and challenges the left’s refusal to confront ideas directly. #CharlieKirk #MediaBias #PoliticsPodcast

Alex Marlow

16,895 Aufrufe • vor 10 Monaten

for physical AI to work in the real world, it needs high-fidelity 3D models of the real world. not just for visualization — for localization, spatial reasoning, and real-to-sim workflows that close the gap between training and deployment. at Niantic Spatial 🌎, we're turning Spexi drone imagery into exactly that — city-scale Gaussian splats grounded in the environments that matter most.
1:00

for physical AI to work in the real world, it needs high-fidelity 3D models of the real world. not just for visualization — for localization, spatial reasoning, and real-to-sim workflows that close the gap between training and deployment. at Niantic Spatial 🌎, we're turning Spexi drone imagery into exactly that — city-scale Gaussian splats grounded in the environments that matter most.

asim ᯅ

49,478 Aufrufe • vor 2 Monaten

GPT-5 on Sudoku-Bench 🧩 Since releasing Sudoku-Bench in May 2025, when no LLM could solve a classic 9x9 puzzle, we've been evaluating the latest generation of models. GPT-5 now leads our leaderboard with 33% puzzles solved--approximately 2x the previous leader--and is the first LLM we've tested to solve a 9x9 Sudoku variant. However, with 67% of the much harder puzzles remaining unsolved, Sudoku-Bench continues to present significant challenges for AI reasoning. Modern Sudoku variants require models to first understand novel rulesets through meta-reasoning, then maintain global consistency across long reasoning chains. Our experiments with GRPO fine-tuning on Qwen2.5-7b and "Thought Cloning" (training on expert human reasoning from Cracking the Cryptic) show that current approaches still struggle with the spatial reasoning and creative "break-in" points that human solvers use naturally. We believe new approaches are required to solve our benchmark. These results highlight persistent gaps between computational problem-solving and human-like reasoning, particularly in tasks requiring integrated mathematical logic, spatial awareness, and creative insight. Read more about our update here: 🔗 Blogpost →
0:28

GPT-5 on Sudoku-Bench 🧩 Since releasing Sudoku-Bench in May 2025, when no LLM could solve a classic 9x9 puzzle, we've been evaluating the latest generation of models. GPT-5 now leads our leaderboard with 33% puzzles solved--approximately 2x the previous leader--and is the first LLM we've tested to solve a 9x9 Sudoku variant. However, with 67% of the much harder puzzles remaining unsolved, Sudoku-Bench continues to present significant challenges for AI reasoning. Modern Sudoku variants require models to first understand novel rulesets through meta-reasoning, then maintain global consistency across long reasoning chains. Our experiments with GRPO fine-tuning on Qwen2.5-7b and "Thought Cloning" (training on expert human reasoning from Cracking the Cryptic) show that current approaches still struggle with the spatial reasoning and creative "break-in" points that human solvers use naturally. We believe new approaches are required to solve our benchmark. These results highlight persistent gaps between computational problem-solving and human-like reasoning, particularly in tasks requiring integrated mathematical logic, spatial awareness, and creative insight. Read more about our update here: 🔗 Blogpost →

Sakana AI

154,645 Aufrufe • vor 9 Monaten