PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding Paper • 2504.13180 • Published 18 days ago • 17
Perception Encoder: The best visual embeddings are not at the output of the network Paper • 2504.13181 • Published 18 days ago • 34
FlashVideo:Flowing Fidelity to Detail for Efficient High-Resolution Video Generation Paper • 2502.05179 • Published Feb 7 • 24