Xiu Li

By learning to predict goal reachability directly from offline trajectories, PRTS enables robots to reason about task progress and physical feasibility, leading to substantial improvements in long-horizon planning and zero-shot generalization.

Simply plugging in RoTE, a lightweight temporal embedding module, can boost existing Transformer-based sequential recommendation models by over 20% on standard benchmarks.

Achieve state-of-the-art real-world image dehazing by jointly reconstructing the clear scene and scattering variables, even with non-uniform haze and complex lighting.

Existing image editing models fall short when it comes to precise spatial manipulations, but a new benchmark and dataset reveal the path to closing the gap.