SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning Paper • 2512.13874 • Published 21 days ago • 16
FrontierCS: Evolving Challenges for Evolving Intelligence Paper • 2512.15699 • Published 19 days ago • 5
Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understanding Paper • 2512.04000 • Published Dec 3, 2025 • 3
Aggregated Residual Transformations for Deep Neural Networks Paper • 1611.05431 • Published Nov 16, 2016 • 2
Sample-Efficient Neural Architecture Search by Learning Action Space Paper • 1906.06832 • Published Jun 17, 2019
Momentum Contrast for Unsupervised Visual Representation Learning Paper • 1911.05722 • Published Nov 13, 2019 • 2
Image Sculpting: Precise Object Editing with 3D Geometry Control Paper • 2401.01702 • Published Jan 2, 2024 • 20
Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs Paper • 2401.06209 • Published Jan 11, 2024
Masked Feature Prediction for Self-Supervised Visual Pre-Training Paper • 2112.09133 • Published Dec 16, 2021
SLIP: Self-supervision meets Language-Image Pre-training Paper • 2112.12750 • Published Dec 23, 2021 • 1
ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders Paper • 2301.00808 • Published Jan 2, 2023