Xin Wang

LLMs are surprisingly bad at fixing real-world logging security vulnerabilities, despite being moderately effective at detecting them.

Reconstructing 3D scenes from a single view gets a boost by explicitly recognizing and leveraging repeated object instances, like chairs and tables, to inform and refine the reconstruction.

RL unlocks genuinely new tool-use capabilities in LLMs by enabling compositional strategies that surpass what's achievable through mere re-sampling, challenging the notion that RL only improves reliability.

Stop wasting compute: a learned policy can intelligently allocate LLM inference budgets, boosting accuracy by up to 12.8% compared to uniform allocation.

VLMs can be easily fooled in the real world by strategically manipulating lighting, causing them to misinterpret scenes and hallucinate nonsensical captions.

Breast cancer risk prediction from MRI just got a whole lot faster and more interpretable, thanks to a novel 2.5D approach that beats both 2D and 3D models.

The best deepfake audio detectors are surprisingly biased by audio quality, speaker gender, and language, undermining their real-world reliability.