two different paths
Leco Li PRO
imnotkitty
AI & ML interests
None yet
Recent Activity
replied to
their
post
about 13 hours ago
The 2025 Chinese LLM Showdown: Western Models Still Dominate Top 4, but China Leads the Open-Source Arena.
🏆 The Champions: Claude-Opus-4.5, Gemini-3-Pro, GPT-5.2, and Gemini-3-Flash sweep the top four spots.
🚀 The Pursuers: Doubao and DeepSeek-V3.2 tie for first place among Chinese models; GLM-4.7, ERNIE-5.0, and Kimi secure their positions in the domestic top five.
🔥 The Biggest Highlight: The top three spots on the open-source leaderboard are entirely held by Team China (DeepSeek, GLM, Kimi), outperforming the best western open-source models.
updated
a collection
1 day ago
Text Generation
liked
a model
1 day ago
Qwen/Qwen3-4B-Instruct-2507
Organizations
replied to
their
post
about 13 hours ago
replied to
their
post
1 day ago
Makes sense lol. I’ll focus on Kimi K2.5 later , they’ve been performing quite well recently.
reacted to
their
post with 🚀
2 days ago
Post
3522
The 2025 Chinese LLM Showdown: Western Models Still Dominate Top 4, but China Leads the Open-Source Arena.
🏆 The Champions: Claude-Opus-4.5, Gemini-3-Pro, GPT-5.2, and Gemini-3-Flash sweep the top four spots.
🚀 The Pursuers: Doubao and DeepSeek-V3.2 tie for first place among Chinese models; GLM-4.7, ERNIE-5.0, and Kimi secure their positions in the domestic top five.
🔥 The Biggest Highlight: The top three spots on the open-source leaderboard are entirely held by Team China (DeepSeek, GLM, Kimi), outperforming the best western open-source models.
🏆 The Champions: Claude-Opus-4.5, Gemini-3-Pro, GPT-5.2, and Gemini-3-Flash sweep the top four spots.
🚀 The Pursuers: Doubao and DeepSeek-V3.2 tie for first place among Chinese models; GLM-4.7, ERNIE-5.0, and Kimi secure their positions in the domestic top five.
🔥 The Biggest Highlight: The top three spots on the open-source leaderboard are entirely held by Team China (DeepSeek, GLM, Kimi), outperforming the best western open-source models.
-
- 4 replies
reacted to
their
post with 🔥
2 days ago
Post
2181
đź‘€Just published a first-look at
tencent/HunyuanImage-3.0-Instruct
Tested its multi-image fusion and single-reference consistency. The results on complex prompts are quite impressive.
What’s the most creative image task you’d give it?
👉 Read the full analysis: https://huggingface.co/blog/imnotkitty/tencent-hy-image-v30-i2i
Tested its multi-image fusion and single-reference consistency. The results on complex prompts are quite impressive.
What’s the most creative image task you’d give it?
👉 Read the full analysis: https://huggingface.co/blog/imnotkitty/tencent-hy-image-v30-i2i
-
- 8 replies
reacted to
their
post with 🔥
2 days ago
Post
2296
đź“ŚSame day, Two Releases.
Jan 27th just got interesting on Open-source AI modles.
âś…Kimi K2.5: How to make models "think" across text and vision natively?
moonshotai/Kimi-K2.5
âś…DeepSeek-OCR 2: How to make models "see" more like humans, not scanners?
deepseek-ai/DeepSeek-OCR-2
One focuses on depth of reasoning, the other on precision of vision.
What's the key differentiator for a multimodal model in your view: raw power or computational elegance?
Jan 27th just got interesting on Open-source AI modles.
âś…Kimi K2.5: How to make models "think" across text and vision natively?
moonshotai/Kimi-K2.5
âś…DeepSeek-OCR 2: How to make models "see" more like humans, not scanners?
deepseek-ai/DeepSeek-OCR-2
One focuses on depth of reasoning, the other on precision of vision.
What's the key differentiator for a multimodal model in your view: raw power or computational elegance?
reacted to
their
post with 🚀
2 days ago
Post
172
✨New Model: Ant Open-Sources LingBot-VLA
robbyant/lingbot-vla-4b
👉Goal: Enable "one brain, multiple robots". The same model can control 9 different robot body types.
👉Performance: Broke the real-robot operation record on the GM-100 benchmark.
👉For Devs: Fully open-sourced (model + full toolkit). Claims to adapt to new tasks with only ~80 demos.
robbyant/lingbot-vla-4b
👉Goal: Enable "one brain, multiple robots". The same model can control 9 different robot body types.
👉Performance: Broke the real-robot operation record on the GM-100 benchmark.
👉For Devs: Fully open-sourced (model + full toolkit). Claims to adapt to new tasks with only ~80 demos.
posted
an
update
3 days ago
Post
3522
The 2025 Chinese LLM Showdown: Western Models Still Dominate Top 4, but China Leads the Open-Source Arena.
🏆 The Champions: Claude-Opus-4.5, Gemini-3-Pro, GPT-5.2, and Gemini-3-Flash sweep the top four spots.
🚀 The Pursuers: Doubao and DeepSeek-V3.2 tie for first place among Chinese models; GLM-4.7, ERNIE-5.0, and Kimi secure their positions in the domestic top five.
🔥 The Biggest Highlight: The top three spots on the open-source leaderboard are entirely held by Team China (DeepSeek, GLM, Kimi), outperforming the best western open-source models.
🏆 The Champions: Claude-Opus-4.5, Gemini-3-Pro, GPT-5.2, and Gemini-3-Flash sweep the top four spots.
🚀 The Pursuers: Doubao and DeepSeek-V3.2 tie for first place among Chinese models; GLM-4.7, ERNIE-5.0, and Kimi secure their positions in the domestic top five.
🔥 The Biggest Highlight: The top three spots on the open-source leaderboard are entirely held by Team China (DeepSeek, GLM, Kimi), outperforming the best western open-source models.
-
-
-
- 4 replies
posted
an
update
6 days ago
Post
172
✨New Model: Ant Open-Sources LingBot-VLA
robbyant/lingbot-vla-4b
👉Goal: Enable "one brain, multiple robots". The same model can control 9 different robot body types.
👉Performance: Broke the real-robot operation record on the GM-100 benchmark.
👉For Devs: Fully open-sourced (model + full toolkit). Claims to adapt to new tasks with only ~80 demos.
robbyant/lingbot-vla-4b
👉Goal: Enable "one brain, multiple robots". The same model can control 9 different robot body types.
👉Performance: Broke the real-robot operation record on the GM-100 benchmark.
👉For Devs: Fully open-sourced (model + full toolkit). Claims to adapt to new tasks with only ~80 demos.
replied to
their
post
8 days ago
Nah it's open source.
replied to
their
post
8 days ago
posted
an
update
8 days ago
Post
2296
đź“ŚSame day, Two Releases.
Jan 27th just got interesting on Open-source AI modles.
âś…Kimi K2.5: How to make models "think" across text and vision natively?
moonshotai/Kimi-K2.5
âś…DeepSeek-OCR 2: How to make models "see" more like humans, not scanners?
deepseek-ai/DeepSeek-OCR-2
One focuses on depth of reasoning, the other on precision of vision.
What's the key differentiator for a multimodal model in your view: raw power or computational elegance?
Jan 27th just got interesting on Open-source AI modles.
âś…Kimi K2.5: How to make models "think" across text and vision natively?
moonshotai/Kimi-K2.5
âś…DeepSeek-OCR 2: How to make models "see" more like humans, not scanners?
deepseek-ai/DeepSeek-OCR-2
One focuses on depth of reasoning, the other on precision of vision.
What's the key differentiator for a multimodal model in your view: raw power or computational elegance?
replied to
their
post
8 days ago
It's already there!
posted
an
update
9 days ago
Post
2181
đź‘€Just published a first-look at
tencent/HunyuanImage-3.0-Instruct
Tested its multi-image fusion and single-reference consistency. The results on complex prompts are quite impressive.
What’s the most creative image task you’d give it?
👉 Read the full analysis: https://huggingface.co/blog/imnotkitty/tencent-hy-image-v30-i2i
Tested its multi-image fusion and single-reference consistency. The results on complex prompts are quite impressive.
What’s the most creative image task you’d give it?
👉 Read the full analysis: https://huggingface.co/blog/imnotkitty/tencent-hy-image-v30-i2i
-
-
-
- 8 replies