Yang Ji

A unified benchmark reveals the trade-offs between pixel-wise accuracy and perceptual realism in state-of-the-art image super-resolution techniques.

Forget static prompts: LDEPrompt dynamically expands and freezes prompts based on layer importance, achieving state-of-the-art performance in class-incremental learning.

Quantum-inspired gating unlocks better knowledge transfer in class-incremental learning, outperforming existing methods by dynamically modeling task relationships.

Explicitly modeling image degradation within diffusion-based super-resolution unlocks more realistic and perceptually pleasing results on real-world images.

Ditch the clunky text-based reasoning: LaST-VLA achieves new benchmarks in autonomous driving by thinking in a physically-grounded, latent spatio-temporal space.