Showing 1–20 of 21 results
/ Date/ Name
Jan 21, 2026Walk through Paintings: Egocentric World Models from Internet PriorsNov 24, 2025SLMFix: Leveraging Small Language Models for Error Fixing with Reinforcement LearningMay 29, 2025Argus: Vision-Centric Reasoning with Grounded Chain-of-ThoughtMar 13, 2025V2Edit: Versatile Video Diffusion Editor for Videos and 3D ScenesDec 5, 2024PaintScene4D: Consistent 4D Scene Generation from Text PromptsOct 11, 2024SceneCraft: Layout-Guided 3D Scene GenerationOct 10, 2024Emergent Visual Grounding in Large Multimodal Models Without Grounding SupervisionJul 26, 2024Floating No More: Object-Ground Reconstruction from a Single ImageOct 19, 2023Frozen Transformers in Language Models Are Effective Visual Encoder LayersSep 28, 2023Improving Equivariance in State-of-the-Art Supervised Depth and Normal PredictorsSep 25, 2023Aligning Large Multimodal Models with Factually Augmented RLHFAug 3, 2023Revisiting Deformable Convolution for Depth CompletionJun 8, 2023Stochastic Multi-Person 3D Motion ForecastingMay 4, 2023Contrastive Mean Teacher for Domain Adaptive Object DetectorsAug 2, 2022The Curse of Low Task Diversity: On the Failure of Transfer Learning to Outperform MAML and Their Empirical EquivalenceJun 9, 2022Beyond RGB: Scene-Property Synthesis with Neural Radiance FieldsMay 4, 2021Hallucination Improves Few-Shot Object DetectionAug 22, 2020Few-Shot Learning with Intra-Class Knowledge TransferNov 29, 2019Unlocking the Full Potential of Small Data with Diverse SupervisionJul 18, 2019Growing a Brain: Fine-Tuning by Increasing Model Capacity