正在加载视频...

视频加载失败

返回首页

Gemini 3.1 is SOTA at 3D spatial reasoning

zachdive's profile picture

Zach Dive

9,003 subscribers

196,253 次观看 • 5 个月前 •via X (Twitter)

科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Gemini 3.1 Pro is insanely good at animating svgs
0:13

Gemini 3.1 Pro is insanely good at animating svgs

Junior García

584,168 次观看 • 5 个月前

MLLMs are great at understanding videos, but struggle with spatial reasoning—like estimating distances or tracking objects across time. the bottleneck? getting precise 3D spatial annotations on real videos is expensive and error-prone. introducing SIMS-V 🤖 [1/n]
0:14

MLLMs are great at understanding videos, but struggle with spatial reasoning—like estimating distances or tracking objects across time. the bottleneck? getting precise 3D spatial annotations on real videos is expensive and error-prone. introducing SIMS-V 🤖 [1/n]

Ellis Brown

16,426 次观看 • 8 个月前

Gemini 3.1 Pro in Gemini App vs Gemini 3.1 Pro in AI Studio i used same prompt
0:12

Gemini 3.1 Pro in Gemini App vs Gemini 3.1 Pro in AI Studio i used same prompt

Harshith

450,694 次观看 • 4 个月前

Gemini 3.1 Pro + 1 Prompt Prompt below 👇
0:10

Gemini 3.1 Pro + 1 Prompt Prompt below 👇

Ahmed

16,125 次观看 • 21 天前

Gemini 3.6 Flash is now on DeepSWE at 49%, roughly on par with Opus 4.8 at medium reasoning.
0:14

Gemini 3.6 Flash is now on DeepSWE at 49%, roughly on par with Opus 4.8 at medium reasoning.

Datacurve

244,918 次观看 • 10 天前

Gemini Pro 3.1 is so cracked at presentations. and anyone can achieve the same results. Here's the prompt ↓
0:12

Gemini Pro 3.1 is so cracked at presentations. and anyone can achieve the same results. Here's the prompt ↓

Viktor Oddy

281,202 次观看 • 5 个月前

Gemini 3.1 + Lovable Prompt below ↓
0:18

Gemini 3.1 + Lovable Prompt below ↓

Viktor Oddy

42,699 次观看 • 3 个月前

Gemini 3.5 Pro* vs Gemini 3.1 Pro Gemini 3.5 Pro very recent checkpoint output appeared in Arena Battle Mode Not even close to 3.1 Pro 😭😭
0:11

Gemini 3.5 Pro* vs Gemini 3.1 Pro Gemini 3.5 Pro very recent checkpoint output appeared in Arena Battle Mode Not even close to 3.1 Pro 😭😭

Harshith

98,489 次观看 • 1 个月前

Gemini 3.1 is so cracked at presentations.🤯 One-shoted This Animated deck for with animations! Here’s the exact prompt I used ↓
0:16

Gemini 3.1 is so cracked at presentations.🤯 One-shoted This Animated deck for with animations! Here’s the exact prompt I used ↓

Viktor Oddy

41,174 次观看 • 4 个月前

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 次观看 • 10 个月前

An abstract generative sculpture exploring knots, energy flow, and emergent structure in 3D space. Coded with Google Gemini 3.1 Pro using Three.js and GLSL shaders. 🔊
0:14

An abstract generative sculpture exploring knots, energy flow, and emergent structure in 3D space. Coded with Google Gemini 3.1 Pro using Three.js and GLSL shaders. 🔊

Techartist

22,595 次观看 • 5 个月前

Wow, Gemini 3.1 Pro just crushed one of my test problems no other model could solve. "Write a photorealistic 3D ocean simulation" 3D graphics is extremely hard. It has to encode 9-10 techniques based in physics. Being off by just 1 number can lead to bonkers results
0:10

Wow, Gemini 3.1 Pro just crushed one of my test problems no other model could solve. "Write a photorealistic 3D ocean simulation" 3D graphics is extremely hard. It has to encode 9-10 techniques based in physics. Being off by just 1 number can lead to bonkers results

Deedy

5,044,240 次观看 • 5 个月前

Gemini 3.1 Pro (preview) is now available on all platforms via Firebase AI Logic 💫 See the docs:
0:10

Gemini 3.1 Pro (preview) is now available on all platforms via Firebase AI Logic 💫 See the docs:

Firebase

18,860 次观看 • 5 个月前

Gemini 3.1 Pro is now available for all paid tiers! The default model router, Auto (Gemini 3) will use Gemini 3.1 Pro as it's pro model for complex prompts. You can also set the new model via /model to try it out. We are excited to see how you put it to use!
0:12

Gemini 3.1 Pro is now available for all paid tiers! The default model router, Auto (Gemini 3) will use Gemini 3.1 Pro as it's pro model for complex prompts. You can also set the new model via /model to try it out. We are excited to see how you put it to use!

Gemini CLI

399,766 次观看 • 5 个月前

❤️‍🔥Gemini 3.1 just one-shotted this insane aniamted website Prompt included ↓
0:17

❤️‍🔥Gemini 3.1 just one-shotted this insane aniamted website Prompt included ↓

Viktor Oddy

96,943 次观看 • 5 个月前

Testing Gemini 3.1 in After Effects with the "pelican riding a bike" challenge
0:16

Testing Gemini 3.1 in After Effects with the "pelican riding a bike" challenge

Davey

180,972 次观看 • 5 个月前

Google DeepMind is absolutely on fire 🔥 they have just launched Gemini Robotics-ER 1.5 their first broadly available robotics AI model designed to act as the "high-level reasoning brain" for robots. This is Google's first Gemini Robotics model made available to all developers. - Available in preview through Google AI Studio and Gemini API. - First thinking model for robots interacting with the physical world. Handles complex commands and orchestrates sophisticated robotic behaviors. - Key capabilities: Advanced spatial reasoning, multi-step task planning, Google Search integration, precise 2D pointing, object reasoning, and video analysis. - Flexible thinking budget lets developers tune speed vs accuracy. Can think longer for complex tasks or respond quickly for reactive operations. - Enhanced safety filters refuse dangerous tasks and recognize physical limits.
0:15

Google DeepMind is absolutely on fire 🔥 they have just launched Gemini Robotics-ER 1.5 their first broadly available robotics AI model designed to act as the "high-level reasoning brain" for robots. This is Google's first Gemini Robotics model made available to all developers. - Available in preview through Google AI Studio and Gemini API. - First thinking model for robots interacting with the physical world. Handles complex commands and orchestrates sophisticated robotic behaviors. - Key capabilities: Advanced spatial reasoning, multi-step task planning, Google Search integration, precise 2D pointing, object reasoning, and video analysis. - Flexible thinking budget lets developers tune speed vs accuracy. Can think longer for complex tasks or respond quickly for reactive operations. - Enhanced safety filters refuse dangerous tasks and recognize physical limits.

AshutoshShrivastava

137,034 次观看 • 10 个月前

Direct3D‑S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
0:12

Direct3D‑S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention

Dreaming Tulpa 🥓👑

27,877 次观看 • 1 年前