Jian Zhao

AI-native games could redefine interactive entertainment by making generative AI an essential part of gameplay, rather than just a tool for enhancement.

Unified vision-language perception in MLLMs is not just an evolution; it’s a critical leap toward achieving artificial general intelligence.

V-Zero achieves fine-grained visual reasoning without any annotated answer labels, outperforming traditional methods in both speed and accuracy.

UGV path tracking accuracy can be improved by over 11.5% on challenging terrains using a novel DNN Koopman-based compensation strategy.

CustomShift achieves unprecedented balance between semantic fidelity and subject consistency in image generation, outperforming existing methods by leveraging a novel attention distribution shift.

ALMANAC reveals that agents can significantly improve their collaborative competence by learning from detailed human mental model annotations.

Achieve spatially precise control in FPS world models by injecting actions locally, without segmentation labels, enabling zero-shot generalization across games.

Domain-adapting LLMs for EDA requires explicit RAG scenario training to prevent performance degradation, and QA augmentation during corpus construction further boosts performance.

LLMs can rediscover known algorithms, but only after targeted unlearning and with the help of a generative verifier to avoid "thought collapse," revealing both the innovative potential and limitations of these models.