"au:"Yilun Du"" — arXiv2 SearchShowing 1–8 of 8 results
/ Date/ Name
Apr 22, 2026Building a Precise Video Language with Human-AI OversightFeb 23, 2026A Very Big Video Reasoning SuiteJan 8, 2026Large Language Models Are Bad Dice Players: LLMs Struggle to Generate Random Numbers from Statistical DistributionsJul 7, 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic CapabilitiesOct 20, 2022Composing Ensembles of Pre-trained Models via Iterative ConsensusJun 3, 2022Compositional Visual Generation with Composable Diffusion ModelsOct 7, 2021Weakly Supervised Human-Object Interaction Detection in Video via Contrastive Spatiotemporal RegionsNov 24, 2020Energy-Based Models for Continual Learning