Showing 1–11 of 11 results
/ Date/ Name
Jun 11, 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and PlanningFeb 15, 2024Revisiting Feature Prediction for Learning Visual Representations from VideoDec 19, 2023Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language ModelApr 14, 2023DINOv2: Learning Robust Visual Features without SupervisionDec 10, 2022Uniform Masking Prevails in Vision-Language PretrainingOct 14, 2022Neural Attentive CircuitsNov 13, 2017Three Factors Influencing Minima in SGDOct 13, 2017Residual Connections Encourage Iterative InferenceJun 16, 2017A Closer Look at Memorization in Deep NetworksMay 9, 2016Theano: A Python framework for fast computation of mathematical expressionsNov 24, 2015Dynamic Capacity Networks