MM-IQ: Benchmarking Human-Like Abstraction and Reasoning in Multimodal Models Paper • 2502.00698 • Published 3 days ago • 18
AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Understanding Paper • 2502.01341 • Published 2 days ago • 29
OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models Paper • 2502.01061 • Published 2 days ago • 115
Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming Paper • 2501.18837 • Published 5 days ago • 7