Daniil Gavrilov

Qantara achieves a remarkable 91.2 SR on the LeWM control suite, redefining the capabilities of JEPA world models to operate across multiple inference paradigms without retraining.

Correlation-structured supervision from video-derived ordinal signals can replace traditional reward mechanisms, achieving robust policy learning across diverse tasks.

Stable features in sparse autoencoders dominate predictive power, while unstable features reveal a surprising low-dimensional structure that complicates reproducibility.

Causal manipulation of TTS features enables unprecedented control over speech synthesis, transforming how we can steer voice characteristics in real-time.

Bootstrapping student policies with teacher-aligned rollouts within a KL-constrained trust region significantly boosts on-policy distillation performance in math reasoning tasks.

Ditch the decoder: Directly predicting future latent embeddings with a temporal transformer yields state-of-the-art MBRL performance, especially in complex, partially observable environments.