Tianyi Wang

Achieving an ensemble F1-score of 0.9124, this deep learning model redefines AML diagnosis by aggregating complex cellular data into actionable insights.

Achieve more reliable ADAS by using a physics-informed neural network that leverages damper characteristics to estimate wheel load more accurately than existing methods.

Current video understanding models struggle with long-horizon robustness and non-speech audio, as revealed by the new OmniPro benchmark designed for comprehensive omni-modal proactive evaluation.

Escaping the endless cat-and-mouse game of deepfake detection may be possible by shifting from static pattern recognition to physics-inspired dynamical stability analysis, where real images are stable and deepfakes are not.

PPO can be made sample-efficient and stable for long-horizon reasoning in LLMs by treating the problem as a sequence-level contextual bandit, sidestepping the need for computationally expensive multi-sampling.

By prioritizing diversity over accuracy in experience replay, DyJR significantly boosts LLM reasoning performance in RL, outperforming GRPO and other baselines without sacrificing training efficiency.

Achieve better video editing without retraining by dynamically locking background features based on a "hallucination metric" that detects when the diffusion model is about to go astray.

LLMs can boost autonomous driving behavior classification accuracy to over 94% by fusing numerical time-series data with high-level semantic features.

Achieve accurate single-shot 3D imaging of specular surfaces by intelligently fusing polarization and structured illumination cues using a physics-informed deep learning approach.