Hao Li

Injecting region-specific awareness into the diffusion model's initial noise unlocks significantly better compositional image generation, outperforming existing methods in cross-region coherence.

LLMs that ace general web browsing still flunk at scientific literature discovery, revealing a critical gap in research-oriented AI agent capabilities.

SPD-SheafNets learn richer geometric representations than standard GNNs by operating directly on matrix-valued features, achieving SOTA on molecular property prediction by capturing relationships between directions.

AI-guided simulations reveal the precise mechanisms of siloxane poisoning in gas sensors, paving the way for designing sensors that resist degradation.

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

Density-dependent shifts in the potential of zero charge reveal a more accurate predictor for oxygen reduction activity than traditional magnetic descriptors in M-N-C electrocatalysts.

AI coding agents are surprisingly bad at logging, requiring humans to silently fix 72.5% of their logging mistakes.

Robots can now better assemble boxes in the real world thanks to a video-generative value model that anticipates future states, moving beyond static snapshots for more reliable task progress assessment.

Inverting the standard multimodal learning paradigm, Uni-ViGU shows a video generator can serve as the foundation for both video generation *and* understanding, achieving competitive performance on both.

Structured composition unlocks significantly better agent performance compared to flat skill invocation, even with the same skill set.