Showing 1–20 of 22 results
/ Date/ Name
Mar 18, 2026TAPESTRY: From Geometry to Appearance via Consistent Turntable VideosDec 15, 2025Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation ModelJul 23, 2025Confounded Causal Imitation Learning with Instrumental VariablesJun 10, 2025Seedance 1.0: Exploring the Boundaries of Video Generation ModelsJul 10, 2024Identification and Estimation of the Bi-Directional MR with Some Invalid InstrumentsJul 7, 2024An Improved Method for Personalizing Diffusion ModelsFeb 7, 2024Learning by Doing: An Online Causal Reinforcement Learning Framework with Causal-Aware PolicyFeb 2, 2024Boximator: Generating Rich and Controllable Motions for Video SynthesisNov 18, 2023Make Pixels Dance: High-Dynamic Video GenerationJul 5, 2023What Matters in Training a GPT4-Style Language Model with Multimodal Inputs?Feb 10, 2023A Survey on Causal Reinforcement LearningDec 16, 2022Biomedical image analysis competitions: The state of current participation practiceNov 22, 2022X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language TasksJun 1, 2022Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-trainingNov 16, 2021Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual ConceptsOct 24, 2020Jointly Optimizing State Operation Prediction and Value Generation for Dialogue State TrackingOct 24, 2020Open-Domain Dialogue Generation Based on Pre-trained Language ModelsOct 21, 2020A Simple and Efficient Multi-Task Learning Approach for Conditioned Dialogue GenerationOct 21, 2020Multi-Domain Dialogue State Tracking based on State GraphSep 19, 2020Causal Discovery with Multi-Domain LiNGAM for Latent Factors