DigestAI news desk

Cut through the AI noise.

Research4 min read

NVIDIA researchers introduce Physis-Lang, boosting Cosmos3 past Veo 3.1

A joint team from NVIDIA, MIT and the University of Oxford presented Physis-Lang, a framework that treats physical language as an optimizable representation for video models. The system adds a physics‑reasoning field to captions and uses a self‑evolving loop where a frozen GPT‑5.5 captioner is guided by a Gemini‑3.1‑Pro critic, improving caption F1 from 78.64 to 87.82 after nine iterations. On…

1 source

Key points

  • Physis-Lang framework adds physics‑reasoning captions, reaching 48.2 ± 1.4 on Physics‑IQ Verified with Cosmos3‑Super.
  • Cosmos3‑Nano with Physis‑Lang beats Google Veo 3.1 on three of four benchmarks, e.g., 43.41 vs 34.99 on Physics‑IQ Verified.
  • Local PhysThinker‑C/U models keep most gains, reducing API expense from $24.12K to $0.12K.

When compared with Google’s Veo 3.1, Cosmos3‑Nano equipped with Physis‑Lang outperformed on three of four benchmarks, for example scoring 43.41 versus 34.99 on Physics‑IQ Verified. The researchers also distilled the pipeline into two local Qwen‑based models, PhysThinker‑C and PhysThinker‑U, which retained most of the gains while cutting API costs from about $24.12K to $0.12K, and a fully local setup cost $0. No code or weights have been released yet; only the paper and repository are available.

Full story from MarkTechPost · by Asif RazzaqOpen source ↗

NVIDIA Researchers Introduce Physis-Lang: Self-Evolving Physical Language That Lifts Cosmos 3 Past Veo 3.1 on Physics Benchmarks

MarkTechPost · 30 September 2026

Loading the full article…

This text was published by MarkTechPost and written by Asif Razzaq. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Topics · follow one to build your own front page
NVIDIAGoogleMITUniversity of OxfordCosmos3-SuperCosmos3-NanoVeo 3.1Physis-LangPhysThinker-CPhysThinker-UAsif Razzaq

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Research

All →

Related stories