Showing 1–20 of 30 results
/ Date/ Name
Jun 6, 2024DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D DataMar 14, 2023InstMove: Instance Motion for Object-centric Video SegmentationApr 30, 2025ReVision: Refining Video Diffusion with Explicit 3D Motion ModelingDec 19, 2024Flowing from Words to Pixels: A Noise-Free Framework for Cross-Modality EvolutionNov 26, 2018PNS: Population-Guided Novelty Search for Reinforcement Learning in Hard Exploration EnvironmentsJul 29, 2022Explicit Occlusion Reasoning for Multi-person 3D Human Pose EstimationJul 21, 2022In Defense of Online Models for Video Instance SegmentationJun 13, 2024Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and Time-Dependent Layer NormalizationJun 1, 2023Discovering Failure Modes of Text-guided Diffusion Models via Adversarial SearchDec 18, 2025Differences That Matter: Auditing Models for Capability Gap Discovery and RectificationMar 13, 2023PoseExaminer: Automated Testing of Out-of-Distribution Robustness in Human Pose and Shape EstimationNov 30, 2020Nothing But Geometric Constraints: A Model-Free Method for Articulated Object Pose EstimationDec 18, 2025Generative Adversarial Reasoner: Enhancing LLM Reasoning with Adversarial Reinforcement LearningApr 28, 2025SpatialReasoner: Towards Explicit and Generalizable 3D Spatial ReasoningNov 20, 2025TriDiff-4D: Fast 4D Generation through Diffusion-based Triplane Re-posingFeb 9, 2026Autoregressive Image Generation with Masked Bit ModelingAug 22, 2023Animal3D: A Comprehensive Dataset of 3D Animal Pose and ShapeMar 29, 2026DSevolve: Enabling Real-Time Adaptive Scheduling on Dynamic Shop Floor with LLM-Evolved Heuristic PortfoliosJun 13, 2023Generating Images with 3D Annotations Using Diffusion ModelsNov 18, 2022The Runner-up Solution for YouTube-VIS Long Video Challenge 2022