Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis
Paper
•
2601.14253
•
Published
•
5
AI & ML interests
None defined yet.
Recent Activity
View all activity
akhaliq
submitted
a
paper
to Daily Papers
1 day ago
akhaliq
submitted
a
paper
to Daily Papers
8 days ago
akhaliq
submitted
a
paper
to Daily Papers
9 days ago
akhaliq
submitted
a
paper
to Daily Papers
16 days ago
akhaliq
submitted
2
papers
to Daily Papers
22 days ago
akhaliq
submitted
3
papers
to Daily Papers
about 1 month ago
What matters for Representation Alignment: Global Information or Spatial Structure?
Paper
•
2512.10794
•
Published
•
9
Towards a Science of Scaling Agent Systems
Paper
•
2512.08296
•
Published
•
15
ThreadWeaver: Adaptive Threading for Efficient Parallel Reasoning in Language Models
Paper
•
2512.07843
•
Published
•
22
akhaliq
authored
a
paper
3 months ago
dylanebert
posted
an
update
5 months ago
Post
4234
These are the current best Generative 3D
Render:
#1 - CSM
#2 - TRELLIS (open-source)
#3 - Zaohaowu3D
Topology:
#1 - Hunyuan3D-2
#2 - TRELLIS (open-source)
#3 - Hunyuan3D-2.1
as voted/submitted openly on https://huggingface.co/spaces/dylanebert/3d-arena
Render:
#1 - CSM
#2 - TRELLIS (open-source)
#3 - Zaohaowu3D
Topology:
#1 - Hunyuan3D-2
#2 - TRELLIS (open-source)
#3 - Hunyuan3D-2.1
as voted/submitted openly on https://huggingface.co/spaces/dylanebert/3d-arena
- 1 reply
dylanebert
posted
an
update
7 months ago
Post
2797
https://huggingface.co/spaces/dylanebert/3d-arena now supports topology-only voting and ranking!
Let's see which Gen3D model produces the best topology
Let's see which Gen3D model produces the best topology
dylanebert
posted
an
update
7 months ago
Post
579
https://huggingface.co/spaces/dylanebert/3d-arena now has an official paper!
Check it out 3D Arena: An Open Platform for Generative 3D Evaluation (2506.18787)
Check it out 3D Arena: An Open Platform for Generative 3D Evaluation (2506.18787)
dylanebert
authored
a
paper
7 months ago
Post
2767
It will be very interesting to benchmark how energy-efficient the new Falcon-Edge is: https://huggingface.co/blog/tiiuae/falcon-edge
Should be super efficient on CPU according to the numbers published for BitNet: https://github.com/microsoft/BitNet/blob/main/assets/intel_performance.jpg
Should be super efficient on CPU according to the numbers published for BitNet: https://github.com/microsoft/BitNet/blob/main/assets/intel_performance.jpg
- 1 reply
dylanebert
posted
an
update
10 months ago
Post
4145
You now have the option to filter 3D Arena to open source models.
https://huggingface.co/spaces/dylanebert/3d-arena
https://huggingface.co/spaces/dylanebert/3d-arena
- 1 reply
dylanebert
posted
an
update
10 months ago
Post
1718
Impressive new Image-to-3D model from Tencent!
Here's how the topology (left) compares to the open source state-of-the-art (right)
(using the
Try it out here: tencent/Hunyuan3D-2mv
Here's how the topology (left) compares to the open source state-of-the-art (right)
(using the
Simplify option for reduced poly count)Try it out here: tencent/Hunyuan3D-2mv
dylanebert
posted
an
update
11 months ago
Post
1425
📢 New #1 in Generative 3D
CSM/Cube from Common Sense Machines is now the top ranked image-to-3d model
check out the results in https://huggingface.co/spaces/dylanebert/3d-arena
CSM/Cube from Common Sense Machines is now the top ranked image-to-3d model
check out the results in https://huggingface.co/spaces/dylanebert/3d-arena
Post
1777
Nice paper comparing the fp8 inference efficiency of Nvidia H100 and Intel Gaudi2:
An Investigation of FP8 Across Accelerators for LLM Inference (2502.01070)
The conclusion is interesting: "Our findings highlight that the Gaudi 2, by leveraging FP8, achieves higher throughput-to-power efficiency during LLM inference"
One aspect of AI hardware accelerators that is often overlooked is how they consume less energy than GPUs. It's nice to see researchers starting carrying out experiments to measure this!
Gaudi3 results soon...
The conclusion is interesting: "Our findings highlight that the Gaudi 2, by leveraging FP8, achieves higher throughput-to-power efficiency during LLM inference"
One aspect of AI hardware accelerators that is often overlooked is how they consume less energy than GPUs. It's nice to see researchers starting carrying out experiments to measure this!
Gaudi3 results soon...
dylanebert
posted
an
update
12 months ago
Post
3404
I made a 1 minute video explaining the DeepSeek situation
R1: deepseek-ai/DeepSeek-R1
Janus Pro: deepseek-ai/Janus-Pro-7B
R1: deepseek-ai/DeepSeek-R1
Janus Pro: deepseek-ai/Janus-Pro-7B
- 3 replies