Pavel Tokmakov

ML research scientist at TRI

[Anurag Bagchi @Miccooper9]

[1/6] Ego-centric World Models

We introduce EgoWM — a video world model that simulates EVE-1X humanoid interactions from a single ego-view image + full-body joint angle trajectories.

Moreover it effortlessly generalizes to extreme OOD domains, including paintings !

[Anurag Bagchi @Miccooper9]

[ICCV 25] Refer Everything Model (REM)

(1/6) We leverage Text-to-Video Generation models to zero-shot segment any concept in a video using text. REM generalises to dynamic concepts like smoke, light-beam and more without ever having seen segmentation masks for these entities.

[Pavel Tokmakov @ptokmakov]

@oskurovic @parallel_domain We are planning to release it in the coming months. Please stay tuned!

[Pavel Tokmakov @ptokmakov]

Check out our latest work on Learning to Track with Object Permanence https://t.co/O2OHBTOU6J! We use synthetic data from @parallel_domain, which provides dense ground truth annotations, including for invisible objects, to learn to track behind occlusions.

[Pavel Tokmakov @ptokmakov]

Ablation analysis demonstrates the importance of dataset size for learning this challenging behaviour. Collecting such a dataset in the real world would be extremely expensive, further emphasizing the value of synthetic data in ML research. @ljlijie, @adnothing, @ToyotaResearch

[Pavel Tokmakov @ptokmakov]

Our method is fully online, runs in real-time, and is end-to-end trainable. The resulting model is transferred to real videos with a simple, data-efficient approach, and outperforms the state-of-the-art on KITTI and MOT17 benchmarks by significant margins.