Xu Zhang

Achieve state-of-the-art remote sensing image-text retrieval without the computational burden of large-scale vision-language model pre-training, thanks to a novel two-stage approach.

Unified benchmarks reveal the state-of-the-art in simultaneously addressing multiple real-world image degradations like blur, low-light, and rain.

Unlock the power of small LLMs for ICD coding: Code-Centric Learning lets them rival the performance of much larger proprietary models.

Forget linear outlines: this new method generates longer, more coherent stories by starting with the climax and expanding bidirectionally using Monte Carlo Tree Search.

By randomly attending to different time patches and progressively mixing scales, SEMixer achieves state-of-the-art long-term time series forecasting with a lightweight architecture.

Stop letting noisy, low-predictability data ruin your time series models: APTF dynamically identifies and penalizes these samples during training, leading to improved forecasting and classification accuracy.