Yuan Gao

Achieving a 95.24% win rate in multi-vehicle racing, SGTP redefines real-time planning by integrating game-theoretic principles with GPU-accelerated sampling.

Current ADS testing practices are hampered by major challenges, but an evidence-centered closed-loop framework could revolutionize how we ensure their safety and functionality.

CFM-Bench reveals that without a unified evaluation framework, the true potential of channel foundation models remains obscured, hindering meaningful comparisons with task-specific architectures.

Achieving a 76.42% compilation success rate, Chat2Scenic revolutionizes scenario generation for autonomous driving by effectively bridging regulatory language and executable scripts.

Long-term identity preservation in multi-object tracking is far more challenging than previously understood, with all tested methods exhibiting substantial fragmentation in trajectories.

World models may be fundamentally misfiring by imagining future states kinematically, leading to significant performance drops without corresponding diagnostic signals.

ClinRAG-GRAPH achieves impressive pCR prediction accuracy while ensuring interpretability and robustness against imaging biases across multiple centers.

TRCGL-Net achieves a remarkable tail-class mAP of 0.4904, setting a new benchmark for rare disease recognition in chest X-ray classification.

Clarifying memories can significantly boost the factual accuracy and personalization of conversational agents, while irrelevant memories lead to degraded responses.

Achieving state-of-the-art kanji reading accuracy, Sarashina2.2-TTS sets a new standard for Japanese speech synthesis while ensuring cross-lingual robustness.

WVM outperforms existing models by accurately assessing task progressions and improving robotic manipulation from both expert and suboptimal data.

Sports expose surprising limitations in VLMs' spatial reasoning, as current models struggle to generalize from existing benchmarks despite fine-tuning gains on a new, large-scale dataset.

A 4B-parameter model outperforms Gemini-3-Pro in autonomous driving by incorporating physics-informed constraints and style-aware training, suggesting specialized models can surpass larger, general-purpose models in domain-specific tasks.