Showing 1–13 of 13 results
/ Date/ Name
Apr 22, 2026SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language ModelsApr 22, 2026R-CoV: Region-Aware Chain-of-Verification for Alleviating Object Hallucinations in LVLMsJun 30, 2023MTR++: Multi-Agent Motion Prediction with Symmetric Scene Modeling and Guided Intention QueryingJan 15, 2023DSVT: Dynamic Sparse Voxel Transformer with Rotated SetsSep 27, 2022Motion Transformer with Global Intention Localization and Local Movement RefinementSep 20, 2022MTR-A: 1st Place Solution for 2022 Waymo Open Dataset Challenge -- Motion PredictionFeb 5, 2019Learning Decision Trees Recurrently Through CommunicationFeb 15, 2018Multimodal Explanations: Justifying Decisions and Pointing to the EvidenceJan 28, 2017Exploiting saliency for object segmentation from image level labelsNov 28, 2016Gaze Embeddings for Zero-Shot Image ClassificationMar 29, 2016Latent Embeddings for Zero-shot ClassificationMar 29, 2016Multi-Cue Zero-Shot Learning with Strong SupervisionSep 30, 2014Evaluation of Output Embeddings for Fine-Grained Image Classification