Researchers introduced MATE (Mutually Adversarial self-Training with Evolving data), a reinforcement-learning post-training framework that has the generation and understanding branches of a unified mu…
Researchers introduced FLAT (Flexible-Length Aligned Transmodal representations), a pre-training framework that jointly optimizes a shared multimodal encoder with text-to-image and image-to-text decod…
Researchers introduced SVDtrunc, a two-step block-level compression scheme for Diffusion Transformers (DiTs), which outperforms competing approaches across GenEval, HPSv2, and DPG benchmarks while ret…
Researchers propose ReNFT, a method that repairs mode collapse in reward post-training of diffusion generators by recalibrating internal probability mass, preserving 98.9% and 99.0% of NFT's reward on…
FoundationVision has released Infinity, a bitwise visual autoregressive text-to-image model that generates 1024×1024 photorealistic images in 0.8 seconds, outperforming diffusion models like SD3-Mediu…
Researchers have found that structural template tokens in diffusion transformers act as implicit semantic registers, enabling a training-free head-pruning rule that removes roughly 20% of attention FL…
Researchers introduced SciDraw-Bench, a benchmark for evaluating scientific figure generation by text-to-image and multimodal models, covering 32 tasks across eight figure types and ten disciplines. I…