The paper is "The invisible hand of physics" from a surprisingly diverse set of authors (Parsa Esmati, @Somjit77): https://arxiv.org/abs/2606.05328 ; It's from just a few days ago. I learned about it from a nice talk by @katjahofmann today.

The paper from earlier in the year is by @soniajoseph_ etal: https://arxiv.org/abs/2602.07050

@giffmana Without getting into the who has a good world model debate, I'm not sure linear probe is a good way to measure the quality of the representation (but it's the best we have, though)

@giffmana i love linear probes. have you seen RAPTOR?

To be clear, this is not a V-JEPA or VideoMAE diss, just resurrecting the fact that "pure videogen" models may indeed learn an explicit model of the world/physics as a byproduct.

Also cc @mapo1 we chatted about this and you also intuitively pushed back against such claim.

At the beginning of the year, there was another paper who did this check only for V-MAE and V-JEPA, and showed both have some understanding of physics. This new paper essentially extends the study to diffusion-based "pure videogen" models and shows they understand physics very well.

@giffmana basically; RL trained enough with domain randomization allows you to predict state from the hidden state

accidental state estimator

@giffmana Haven’t read the paper but this feels a bit suspicious 🤨 the video models examined here are tiny and mostly not very good at producing physically plausible videos, how is plausibility defined in this context?

Yeah I’m not familiar with the benchmark and should probably read more about it, but my vibe from the figure above is that most properties that are strictly better in diffusion are appearance preservation over frames (permanence, shape etc) rather than “hard core temporal” properties. Definitely not saying VJEPA solves these, but I would say that the results on temporal properties are less convincing

@hila_chefer Same bench (but slightly different protocol) that Sonia's paper from earlier in the year.

@giffmana This is evidence for what we were discussing today @Germs96: that the information contained in V-JEPA representations is a subset of that of video generators

If linear probe is positive, it's a very strong signal the information is there *and explicit* (in whatever is the input to the probe)

If it's negative it doesn't mean the info isn't there, but at least that the info isn't there in an easily extractive way.

The next step is attention probe, which we used a lot in the CapPa pallet and also Sonia used in her pallet on the topic earlier this year.

> So a model might be shit at generating but still have a grasp of what it *should* be generating. the infamous knowing-doing gap 🤓 I actually think if that were the case methods like REPA wouldn't help because the "know" that the model gains would not lead to "do" I'm mostly basing this on the metrics- the ones that seem much better seem to be appearance-based, whereas the more challenging temporal ones (e.g., gravity solidity here) are not as impressive but will take a look!

@giffmana This paper compares 1B-2B diffusion models with 300m semantic models! No wonder they are better - since they are just bigger. There are larger versions of V-JEPA and the results might be different if those were included!

@artemZholus Yeah that's a fair point! Cc @Somjit77

Note my point here is the positive signal on "pure video models" so that's unaffected by this point.

(I'm not super deeply familiar either) This page shows examples of positives/negatives for IntPhys: https://intphys.cognitive-ml.fr/benchmark/test_blocks.html#block-o1-object-permanence

And this page for InfLevel: https://github.com/allenai/inflevel

Just from looking at them, I do feel that it's more than just good appearance preservation.

What I have the feeling might cause at least your initial skepticism, is that these are not generation benchmarks, but discrimination benchmarks. So a model might be shit at generating but still have a grasp of what it *should* be generating.

@ziv_ravid @giffmana Yeah, but it's a good way to see if the information you want is easily extractable, which *kind of* suggests that the model represents it well

@giffmana @mapo1 But isn't that indeed a JEPA diss? If what you say is true, what's the justification for JEPA?

@giffmana Video generation models need to understand physics for accurate generation, I think representation learning methods could learn physics more efficiently but that’s hard to evaluate

@yacineMTB Nice, i had not seen it