正在加载视频...

视频加载失败

返回首页

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

augmentedcamel's profile picture

Mikameel ᯅ

2,291 subscribers

75,587 次观看 • 17 天前 •via X (Twitter)

艺术科学技术教育
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

Our embodied reasoning models are getting even better.
0:23

Our embodied reasoning models are getting even better.

Armen Aghajanyan

14,465 次观看 • 25 天前

MindJourney Test-Time Scaling with World Models for Spatial Reasoning
0:43

MindJourney Test-Time Scaling with World Models for Spatial Reasoning

AK

61,738 次观看 • 1 年前

Turn any AI Model into Reasoning Model with Deepseek r1 <thinking> Architecture. Models like GPT4o and Sonnet 3.5 are Implementation Models But a new breakthrough with Deepseek can make them a Reasoning model. Here's a step-by-step Explanation: 🧵
0:28

Turn any AI Model into Reasoning Model with Deepseek r1 <thinking> Architecture. Models like GPT4o and Sonnet 3.5 are Implementation Models But a new breakthrough with Deepseek can make them a Reasoning model. Here's a step-by-step Explanation: 🧵

CJ Zafir

192,667 次观看 • 1 年前

I've been messing with geometric dissolve and it's getting pretty neat.
0:21

I've been messing with geometric dissolve and it's getting pretty neat.

poiyomi

74,352 次观看 • 3 年前

There are just a handful of parkour animation sequences around but those ones are really good to see.
0:27

There are just a handful of parkour animation sequences around but those ones are really good to see.

D.K.

651,406 次观看 • 2 年前

Playing around with some different challenge types for Haste
0:26

Playing around with some different challenge types for Haste

wilhelm nylund

94,649 次观看 • 2 年前

Playing around with some different capture interactions on Specs and this feels pretty good.
0:24

Playing around with some different capture interactions on Specs and this feels pretty good.

MatthewHallberg

193,840 次观看 • 1 年前

Reasoning over long horizons would allow robots to generalize better to unseen environments and settings zero-shot. One mechanism for this kind of reasoning would be world models, but traditional video world models still tend to struggle with long horizons, and are very data intensive to train. But what if instead of predicting images about the future, we predicted just the symbolic information necessary for reasoning? Nishanth Kumar tells us about Pixels to Predicates, a method for symbol grounding which allows a VLM to plan sequences of robot skills to achieve unseen goals in previously unseen settings. To find out more, watch episode #44 of RoboPapers with Michael Cho - Rbt/Acc and Chris Paxton now!
1:05:20

Reasoning over long horizons would allow robots to generalize better to unseen environments and settings zero-shot. One mechanism for this kind of reasoning would be world models, but traditional video world models still tend to struggle with long horizons, and are very data intensive to train. But what if instead of predicting images about the future, we predicted just the symbolic information necessary for reasoning? Nishanth Kumar tells us about Pixels to Predicates, a method for symbol grounding which allows a VLM to plan sequences of robot skills to achieve unseen goals in previously unseen settings. To find out more, watch episode #44 of RoboPapers with Michael Cho - Rbt/Acc and Chris Paxton now!

RoboPapers

19,676 次观看 • 8 个月前

The new RapidPipeline plugin for Unreal Engine lets you optimize CAD & 3D models directly in the Unreal Editor. Import major CAD formats, remove invisible geometry, perform remeshing, and more with one-click actions. Details: #RapidPipeline #UnrealEngine #UE5 #sponsored #ad
2:46

The new RapidPipeline plugin for Unreal Engine lets you optimize CAD & 3D models directly in the Unreal Editor. Import major CAD formats, remove invisible geometry, perform remeshing, and more with one-click actions. Details: #RapidPipeline #UnrealEngine #UE5 #sponsored #ad

80 LEVEL

13,405 次观看 • 6 个月前

🚨 Big news for AI innovation: Claude Opus 4 and Claude Sonnet 4, Anthropic's most advanced models, are now available in Amazon Bedrock. These powerful models offer hybrid reasoning, 200K token context windows, and are designed for AI agents. From financial analysis to high-quality writing, to enhanced reasoning, coding, agentic capabilities and more—all with the enterprise-grade security of Amazon Web Services.
0:30

🚨 Big news for AI innovation: Claude Opus 4 and Claude Sonnet 4, Anthropic's most advanced models, are now available in Amazon Bedrock. These powerful models offer hybrid reasoning, 200K token context windows, and are designed for AI agents. From financial analysis to high-quality writing, to enhanced reasoning, coding, agentic capabilities and more—all with the enterprise-grade security of Amazon Web Services.

Amazon

123,056 次观看 • 1 年前

She is named Lilith for a reason. These fight sequences are so good.
1:25

She is named Lilith for a reason. These fight sequences are so good.

Greatex

663,704 次观看 • 2 个月前

Playing around with some ideas for the Book of Mormon trailer....
2:27

Playing around with some ideas for the Book of Mormon trailer....

Dustin Harding ✨ From the Dust Films

29,746 次观看 • 2 个月前

just playing around with bone controls for easier skirt animation😊
0:42

just playing around with bone controls for easier skirt animation😊

𝐸𝓊

50,220 次观看 • 1 年前

New Qwen 2511 features: - Stronger Multi‑Person Consistency - Built‑in Community LoRAs - Reduced Image drift with Better identity stability - Improved Geometric Reasoning for Structural edits Try today and take image editing to the next level. Follow us for more updates!
1:26

New Qwen 2511 features: - Stronger Multi‑Person Consistency - Built‑in Community LoRAs - Reduced Image drift with Better identity stability - Improved Geometric Reasoning for Structural edits Try today and take image editing to the next level. Follow us for more updates!

Alibaba Cloud

202,400 次观看 • 7 个月前

1/ We are excited to announce SGS-1, a SOTA foundation model for physical engineering design. SGS-1 enables the creation of manufacturable CAD geometry for real engineering workflows. This example shows SGS-1 in Fusion360 CAD software creating a bracket for a roller assembly.
0:37

1/ We are excited to announce SGS-1, a SOTA foundation model for physical engineering design. SGS-1 enables the creation of manufacturable CAD geometry for real engineering workflows. This example shows SGS-1 in Fusion360 CAD software creating a bracket for a roller assembly.

Spectral Labs

216,883 次观看 • 11 个月前

You can build your 3D models directly from a prompt into Claude code. All thanks to this beautiful python project, build123 a parametric modeling framework for 2D and 3D CAD. It is built on the Open Cascade geometric kernel and it is suitable for 3D printing.
0:36

You can build your 3D models directly from a prompt into Claude code. All thanks to this beautiful python project, build123 a parametric modeling framework for 2D and 3D CAD. It is built on the Open Cascade geometric kernel and it is suitable for 3D printing.

Marco Franzon

20,819 次观看 • 4 个月前

Want high-quality 3D meshes with sharp geometric details? Try our newly released MeshFormer! It only takes 8 GPUs for two days of training, outperforming state-of-the-art models that use over a hundred GPUs! With 3D-native input guidance, representations, supervision, and post-processing, we significantly improve the training efficiency and geometric quality of feed-forward reconstruction models! Project page: Chong Zeng
0:21

Want high-quality 3D meshes with sharp geometric details? Try our newly released MeshFormer! It only takes 8 GPUs for two days of training, outperforming state-of-the-art models that use over a hundred GPUs! With 3D-native input guidance, representations, supervision, and post-processing, we significantly improve the training efficiency and geometric quality of feed-forward reconstruction models! Project page: Chong Zeng

Minghua Liu

16,350 次观看 • 2 年前