Zihao Wang

Longitudinal imaging difference reporting can now be accurately assessed with a benchmark that captures clinically significant changes, setting a new standard for medical imaging models.

Explicitly planning musical structure with MusicLayout allows for unprecedented control and inspection in text-to-music generation, transforming how we create and refine compositions.

Action-conditioned world models may be failing in fundamental ways, with systematic degradation in simulator fidelity revealed by a new diagnostic framework.

MMLMs can be made 99% safer against harmful multimodal inputs without sacrificing utility, thanks to a novel calibration approach.

TreeCredit redefines credit assignment in multi-agent reasoning, leading to better accuracy and lower inference costs through innovative state-matched comparisons.

Logarithmic-depth networks can efficiently learn complex Boolean functions that constant-depth networks cannot, revealing a critical algorithmic separation in neural network capabilities.

Captions generated by PercepCap are not only more accurate but also grounded in explicit spatio-temporal perception, revealing the underlying reasoning behind each description.

Design knowledge is the game-changer that boosts repository-level code generation, leading to a 9.55 percentage point improvement in performance over existing models.