Discover ANY AI to make more online for less.

select between over 22,900 AI Tool and 17,900 AI News Posts.

<
New
Agents
Marketing
Video
Image
Music
Coding
Communication
Education
Travel
>

Sina's open model VibeThinker-3B aims to show reasoning compresses well but factual knowledge doesn't
Sina's open model VibeThinker-3B aims to show reasoning compresses well but factual knowledge doesn't

Sina Weibo's VibeThinker-3B has just three billion parameters but matches models like DeepSeek V3.2 and Kimi K2.5 on math and coding benchmarks. Those models are up to 333 times larger. The secret isn't size but multi-stage post-training. The researchers propose a hypothesis based on their findings: logical reasoning compresses well into small models, but broad world knowledge does not.
The article Sina's open model VibeThinker-3B aims to show reasoning compresses well but factual knowledge doesn't appeared first on The Decoder.

Discover Copy
Rating

Innovation

Pricing

Technology

Usability

We have discovered similar tools to what you are looking for. Check out our suggestions for similar AI tools.

venturebeat
Why Weibo’s tiny VibeThinker-3B has the AI world arguing over benchmarks

<p>On Sunday, a team of nine researchers at <a href="https://weibo.com/">Sina Weibo</a> — the Chinese social media giant better known for its microblogging platform than [...]

Match Score: 642.67

venturebeat
Weibo's new open source AI model VibeThinker-1.5B outperforms DeepSeek

<p>Another day in late 2025, another impressive result from a Chinese company in open source artificial intelligence.</p><p>Chinese social networking company <a href="https:/ [...]

Match Score: 385.15

venturebeat
Microsoft built Phi-4-reasoning-vision-15B to know when to think — and wh

<p><a href="https://www.microsoft.com/en-us">Microsoft</a> on Tuesday released <a href="https://www.microsoft.com/en-us/research/blog/phi-4-reasoning-vision-and-the [...]

Match Score: 189.74

venturebeat
Phi-4 proves that a 'data-first' SFT methodology is the new diffe

<p>AI engineers often chase performance by scaling up LLM parameters and data, but the trend toward smaller, more efficient, and better-focused models has accelerated. </p><p>The &l [...]

Match Score: 119.99

venturebeat
What to be thankful for in AI in 2025

<p>Hello, dear readers. Happy belated Thanksgiving and Black Friday!</p><p>This year has felt like living inside a permanent DevDay. Every week, some lab drops a new model, a new age [...]

Match Score: 116.61

venturebeat
New training method boosts AI multimodal reasoning with smaller, smarter da

<p>Researchers at MiroMind AI and several Chinese universities have released <a href="https://arxiv.org/abs/2511.16334"><u>OpenMMReasoner</u></a>, a new trainin [...]

Match Score: 99.64

venturebeat
Researchers say they trained a foundation model from scratch for about $1,5

<p>Training a foundation LLM from scratch costs millions and requires internet-scale data — which is why most enterprises don&#x27;t bother. Sapient thinks it has a cheaper path.</p> [...]

Match Score: 94.77

venturebeat
MeMo's memory model lets teams upgrade their LLM without retraining it

<p>Enabling LLMs to acquire new knowledge after training remains a major hurdle for enterprise AI — current solutions are either too expensive, too slow, or constrained by context window limit [...]

Match Score: 94.25

venturebeat
MIT's MeMo lets teams swap in a better LLM without retraining — and

<p>Enabling LLMs to acquire new knowledge after training remains a major hurdle for enterprise AI — current solutions are either too expensive, too slow, or constrained by context window limit [...]

Match Score: 93.20