tencent/HunyuanImage-3.0
Text-to-Image
•
83B
•
Updated
•
39.6k
•
•
715
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning
AT$^2$PO: Agentic Turn-based Policy Optimization via Tree Search
Tibron
updated
a
model
about 6 hours ago
kbyran
authored
a
paper
10 days ago
Post
224
We are pleased to introduce a brand-new lightweight LLM, Youtu-LLM:
(1) Youtu-LLM has a total of 2B parameters, employing a 32-layer dense MLA architecture and equipped with an innovative STEM- and agentic-oriented vocabulary;
(2) Based on approximately 11T tokens of pre-training, particularly with native 128k long context extension and native agentic mid-training, Youtu-LLM-2B is comparable to Qwen3-4B in general and agent capabilities;
(3) We have open-sourced the Base/Instruct versions, as well as the evaluation code for reproducing the test metrics. In the technical report, we share our experience of native agentic pre-training in detail.
Youtu-LLM-2B is very suitable as a starting point for exploring on-device agent practice. Meanwhile, we are currently extending this paradigm to larger-scale explorations. We welcome more discussion and collaboration!
🔗 Check the project here: https://github.com/TencentCloudADP/youtu-tip/tree/master/youtu-llm
🤗 Check the models here: https://huggingface.co/collections/tencent/youtu
(1) Youtu-LLM has a total of 2B parameters, employing a 32-layer dense MLA architecture and equipped with an innovative STEM- and agentic-oriented vocabulary;
(2) Based on approximately 11T tokens of pre-training, particularly with native 128k long context extension and native agentic mid-training, Youtu-LLM-2B is comparable to Qwen3-4B in general and agent capabilities;
(3) We have open-sourced the Base/Instruct versions, as well as the evaluation code for reproducing the test metrics. In the technical report, we share our experience of native agentic pre-training in detail.
Youtu-LLM-2B is very suitable as a starting point for exploring on-device agent practice. Meanwhile, we are currently extending this paradigm to larger-scale explorations. We welcome more discussion and collaboration!
🔗 Check the project here: https://github.com/TencentCloudADP/youtu-tip/tree/master/youtu-llm
🤗 Check the models here: https://huggingface.co/collections/tencent/youtu
- 1 reply
Junrulu
authored
a
paper
23 days ago
kkakkkka
submitted
a
paper
to Daily Papers
about 2 months ago
Junrulu
authored
a
paper
2 months ago
ZeqiangLai
authored
a
paper
2 months ago
YanshekWoo
authored
2
papers
3 months ago
xxzcc
authored
2
papers
3 months ago
Jarvis73
authored
a
paper
3 months ago
ZeqiangLai
authored
a
paper
4 months ago
HowieYan
authored
5
papers
5 months ago
CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image
Paper
•
2502.12894
•
Published
•
18
P3-SAM: Native 3D Part Segmentation
Paper
•
2509.06784
•
Published
•
23
X-Part: high fidelity and structure coherent shape decomposition
Paper
•
2509.08643
•
Published
•
27
PREF: Phasorial Embedding Fields for Compact Neural Representations
Paper
•
2205.13524
•
Published
Dual-Space NeRF: Learning Animatable Avatars and Scene Lighting in Separate Spaces
Paper
•
2208.14851
•
Published
YuanLiuuuuuu
authored
a
paper
5 months ago
Junrulu
authored
a
paper
7 months ago