Gated Condition Injection without Multimodal Attention: Towards Controllable Linear-Attention Transformers Paper • 2603.27666 • Published 7 days ago • 12
Image Editing As Programs with Diffusion Models Paper • 2506.04158 • Published Jun 4, 2025 • 24
Can MLLMs Guide Me Home? A Benchmark Study on Fine-Grained Visual Reasoning from Transit Maps Paper • 2505.18675 • Published May 24, 2025 • 27
VeriThinker: Learning to Verify Makes Reasoning Model Efficient Paper • 2505.17941 • Published May 23, 2025 • 25
Dimple: Discrete Diffusion Multimodal Large Language Model with Parallel Decoding Paper • 2505.16990 • Published May 22, 2025 • 22
Running Featured 906 Kolors Character With Flux 🤹 906 Kolors Character to keep character developed with Flux