An Empirical Study of GPT-4o Image Generation Capabilities Paper • 2504.05979 • Published 18 days ago • 61
Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling Paper • 2504.13169 • Published 9 days ago • 39
WORLDMEM: Long-term Consistent World Simulation with Memory Paper • 2504.12369 • Published 10 days ago • 30
Perception Encoder: The best visual embeddings are not at the output of the network Paper • 2504.13181 • Published 9 days ago • 31
REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers Paper • 2504.10483 • Published 12 days ago • 20