Fei Teng

OmniMimic, a training framework that turns directionally limited animal demonstrations into a single multi-gait policy over target per-axis velocity ranges, and uses a shared actor with soft-gated, gait-specialized residual experts to balance reusable locomotion skills with gait-specific corrections.

Angular-to-Cartesian projection distortions have long bottlenecked spherical 3D perception, but explicitly modulating voxel features with spherical range-azimuth geometry outperforms top surround-view models like SurroundOcc and TPVFormer across varied wild environments.

LLMs can enhance ontology rankers for rare-disease diagnosis, boosting recall significantly while retaining valuable evidence trails.

Transforming point seeds into temporally consistent object instances, PS-Track sets a new benchmark in multi-object tracking without relying on traditional bounding box annotations.

Dynamic allocation of compute resources based on attention entropy can yield significant speedups in long-context LLM inference without sacrificing quality.

Achieve state-of-the-art 3D occupancy prediction by unifying geometric, semantic, and textual information within a novel omnidirectional framework.