Open‑Source 35B Intern‑S2‑Preview Rivals Trillion‑Parameter Models on Scientific Benchmarks

The open‑source 35‑billion‑parameter Intern‑S2‑Preview model achieves scientific‑task performance comparable to trillion‑parameter models, thanks to full‑link “general‑specialized” training, reinforced‑learning scaling, and hardware‑aware optimizations, and it outperforms leading closed‑source models on benchmarks such as MolecularIQ and crystal‑structure generation.

InternLMLarge Language Modelbenchmark

0 likes · 11 min read

Open‑Source 35B Intern‑S2‑Preview Rivals Trillion‑Parameter Models on Scientific Benchmarks

HyperAI Super Neural

Feb 3, 2026 · Artificial Intelligence

Walrus: 1.3B Transformer Model Beats Prior Foundations Across 19 Physics Domains

Walrus, a 1.3 billion‑parameter Transformer built by Polymathic AI, is pretrained on 19 diverse physics scenarios—including astrophysics, geoscience, rheology, plasma physics and acoustics—using techniques like patch jittering, adaptive compute tokenization and space‑time factorized attention, and consistently outperforms earlier foundation models on both short‑ and long‑term continuum dynamics predictions.

Foundation ModelTransformerWalrus

0 likes · 13 min read

Walrus: 1.3B Transformer Model Beats Prior Foundations Across 19 Physics Domains

PaperAgent

Jan 17, 2026 · Artificial Intelligence

Hypergraphs Turn LLMs into Reliable Material Discovery Agents

This article explains how representing multi‑component scientific knowledge as hyperedges, rather than traditional triples, enables large language models to traverse complex material interactions, reduce hallucinations, and generate verifiable experimental designs, demonstrated through a large hypergraph built from thousands of scaffold papers.

AI reasoningHypergraphLLM

0 likes · 7 min read

Hypergraphs Turn LLMs into Reliable Material Discovery Agents