NVIDIA Physis-Lang Uses Causal Prompts to Enforce Physics in Video Models
NVIDIA, MIT, and Oxford introduced Physis-Lang, an open framework that injects causal physics reasoning and physics negative prompts into generative video models. Applied to Cosmos3 and Wan2.1, it outperforms Google Veo 3.1 on rigorous physical benchmark splits.
Impact: Medium
Why it matters
Prompt engineers and creative developers can immediately reduce video hallucinations like liquid clipping and rigid motion defying gravity by appending structured causal steps and negative physical constraints.
TL;DR
- 01Adding structured physics_reasoning and physics_negative_prompt fields lifts video model fidelity without retraining.
- 02Cosmos3-Nano equipped with Physis-Lang outperforms Google Veo 3.1 on the VideoPhy-2 Hard physics benchmark (62.36 vs 58.43).
- 03Distilling prompt upsampling into a 4B VLM (PhysThinker) reduced prompt preparation costs from $24.12K to $0.12K.
Key facts
- Physics-IQ Verified Score (Cosmos3-Super)
- 48.2 ± 1.4 (Rank 1)
- VideoPhy-2 Hard Split
- 62.36 (Cosmos3-Nano) vs 58.43 (Veo 3.1)
- Prompting-Only Gain (PhyGenBench)
- +5.62 points on frozen Cosmos3-Nano
- Prompt Pipeline Cost Reduction
- From $24.12K (API) to $0.12K (PhysThinker)
Why Video World Models Defy Physical Laws
Most video diffusion architectures memorize visual co-occurrences without understanding causal constraints, leading to artifacts like solids melting without heat or water flowing uphill. Rather than introducing complex auxiliary latents, Physis-Lang uses structured natural language as the common representation across data curation, fine-tuning, and prompt conditioning.
The Structured Prompt Schema
The framework expands conventional prompts into two explicit conditioning components:
1. physics_reasoning: Explicitly spells out entities, causal mechanisms, interactions, physical principles (e.g., gravity, thermodynamics), and temporal transitions. 2. physics_negative_prompt: Formulates scene-specific implausible failure cases to steer the model away from degenerate physical states.
{
"prompt": "A ceramic coffee mug drops onto a solid hardwood floor",
"physics_reasoning": "Gravitational acceleration pulls the mug downward; impact force exceeds tensile strength of glazed ceramic; brittle fracture propagates from point of contact; shards scatter outward with kinetic energy.",
"physics_negative_prompt": "Mug bouncing like rubber; mug passing through hardwood floor; mug shattering before contact; zero-gravity floating shards"
}Benchmark Results and Frozen Model Gains
On the Physics-IQ Verified snapshot, Cosmos3-Super with Physis-Lang achieved 48.2 ± 1.4, taking the top spot. On VideoPhy-2 Hard split, Cosmos3-Nano scored 62.36 against Google Veo 3.1's 58.43.
Crucially for prompt engineers, running structured physics reasoning and negative prompts on a frozen Cosmos3-Nano without any fine-tuning lifted PhyGenBench scores by +5.62 points (61.67 to 67.29).
Try it in 2 minutes
{
"prompt": "A block of ice melting on a hot steel griddle",
"physics_reasoning": "Thermal conduction transfers heat from the steel surface to the ice bottom; solid water undergoes phase change into liquid; gravity pulls melted water outward across the surface.",
"physics_negative_prompt": "Ice maintaining cube edges while shrinking; water floating upward; sudden vanishing without puddle formation"
}json
✓ When to use
- Generating videos with complex physical dynamics such as fluids, collisions, or thermal phase changes.
- Formulating negative prompts to prevent visual clipping and defying gravitational laws in AI video.
- Curating synthetic video training sets where physical realism is required.
What to do today
- Incorporate a physics_reasoning block in generative video prompts explaining physical transitions step by step.
- Add an explicit physics_negative_prompt listing physically impossible behaviors like clipping or gravity defiance.
- Test dual-prompt conditioning on local video generators like Wan2.1 or Cosmos3.
Sources