A frozen V-JEPA already encodes speed: counterfactual supervision lifts a 4B video model to 72.1, ahead of open peers
Video-language models are usually trained on captions and question-answer pairs, so they learn to retrieve the few attributes the text names rather than to read how a clip changes. V-JEPA-LM instead uses pixel transformations to build counterfactual samples whose two versions of the same clip have different answers, forcing the language model to read dynamics already present in a frozen encoder. Trained in one stage on 4.53M public samples with 32 visual tokens per frame, its 1B to 8B models lead every size class in average score across eleven video benchmarks, with the 4B model at 72.1.