Paper Trail
Search
Search
Dark mode
Light mode
Explorer
Tag: mit
7 items with this tag.
Mar 18, 2026
Autoregressive Image Generation without Vector Quantization
paper
understanding-generation
multimodal
google
mit
Mar 18, 2026
Training Diffusion Models with Reinforcement Learning
paper
image-generation-posttrain
berkeley
mit
modality/image
modality/text
Mar 18, 2026
Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps
paper
image-generation-posttrain
google
nyu
mit
modality/image
Mar 18, 2026
Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
paper
vision-tokenizer
mit
Mar 18, 2026
What matters for Representation Alignment: Global Information or Spatial Structure?
paper
vision-tokenizer
multimodal
mit
Mar 05, 2026
2026-03 Self-Flow
diffusion
computer-vision
machine-learning
paper
mit
bfl
Mar 05, 2026
2026-03 DREAM
multimodal
diffusion
computer-vision
machine-learning
paper
mit