Alibaba Qwen 3.5 Small Models: 0.8B & 2B Benchmarks and Edge Tests

Alibaba Qwen 3.5 Small models run offline on phones and laptops; 0.8B and 2B sizes, with mixed reliability on hard tasks.
Manila Bulletin

DepEd NCR conducts first unified science high school admissions test for Grade 7

The Department of Education–National Capital Region (DepEd NCR) on Saturday, March 7, conducted the first Unified Science High School Admissions Test ...
GitHub

ProverGen: A Framework for First-Order Logic Reasoning Dataset Generation

ProverGen is a novel framework that synergizes the generative strengths of Large Language Models (LLMs) with the rigor and precision of symbolic provers to create scalable, diverse, and high-quality ...
IEEE

The Proposal of an Application for Consideration Logical Thinking with Human-Shaped Pictogram

Abstract: Logical thinking is essential for organizing one's thoughts and fostering the generation of diverse and innovative ideas. However, acquiring logical thinking skills is not straightforward.
Live Science on MSN

'Proof by intimidation': AI is confidently solving 'impossible' math problems. But can it ...

AI could soon spew out hundreds of mathematical proofs that look "right" but contain hidden flaws, or proofs so complex we can't verify them. How will we know if they're right?
IEEE

Funny-Valen-Tine: Planning Solution Distribution Enhances Machine Abstract Reasoning Ability

Abstract: The importance of visual abstract reasoning problems in the field of image processing cannot be overstated. Both Bongard-Logo problems and Raven’s progressive matrices (RPM) belong to the ...