Bo Zhang

DT-Guard outperforms larger models in safety classification while maintaining low-latency performance, proving that reasoning supervision can be efficiently internalized.

Integrating physics-informed neural networks with finite-element analysis yields a highly accurate and efficient surrogate model for elastodynamic wave propagation in heterogeneous materials.

Generating visually faithful driving simulations just got a boost with a novel framework that stabilizes error accumulation and enhances realism in closed-loop scenarios.

UniCoder achieves state-of-the-art visual-to-code generation by transforming blind exploration into guided policy improvement, setting a new standard for the field.

Achieving trillion-parameter performance with just 35 billion parameters by scaling agent horizons reveals a new frontier in model efficiency.