YU DU

7

Papers

97

Total Citations

Papers (7)

AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark

Towards Understanding Camera Motions in Any Video

NeurIPS 2025arXiv

Homomorphism Expressivity of Spectral Invariant Graph Neural Networks

TrajAgent: An LLM-Agent Framework for Trajectory Modeling via Large-and-Small Model Collaboration

NeurIPS 2025arXiv

Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference

NeurIPS 2025arXiv

Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Models

NeurIPS 2025arXiv

EvoLM: In Search of Lost Language Model Training Dynamics

NeurIPS 2025arXiv