Showing 1–18 of 18 results
/ Date/ Name
Sep 30, 2025CWM: An Open-Weights LLM for Research on Code Generation with World ModelsAug 13, 2025DINOv3Jul 25, 2025Back to the Features: DINO as a Foundation for Video World ModelsJun 11, 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and PlanningMar 20, 2025Accelerating Transformer Inference and Training with 2:4 Activation SparsityFeb 12, 2025Inference-time sparse attention with asymmetric indexingNov 1, 2024SimpleFSDP: Simpler Fully Sharded Data Parallel with torch.compileSep 30, 2024Characterizing and Efficiently Accelerating Multimodal Generation Model InferenceApr 14, 2023DINOv2: Learning Robust Visual Features without SupervisionNov 15, 2022Hybrid Transformers for Music Source SeparationDec 23, 2020Training data-efficient image transformers & distillation through attentionMay 26, 2020End-to-End Object Detection with TransformersDec 3, 2019PyTorch: An Imperative Style, High-Performance Deep Learning LibraryNov 6, 2019MLPerf Inference BenchmarkNov 16, 2017Frame Interpolation with Multi-Scale Deep Loss Functions and Generative Adversarial NetworksSep 13, 2016Crafting a multi-task CNN for viewpoint estimationDec 8, 2015Deep Exemplar 2D-3D Detection by Adapting from Real to Rendered ViewsDec 22, 2014Convolutional Neural Networks for joint object detection and pose estimation: A comparative study