NitroFusion2 brings adversarial loss to the text stream of multimodal diffusion transformers
NitroFusion2 applies adversarial distillation to the text stream of MMDiTs, enabling one-step generation of sharp text and details.
Stories per day · 30 days
2 RSS
Related3d-generation1adversarial-distillation1dinov21dyna-21dyna-robotics1flow-matching1latent-space1multimodal-ai1physical-ai1robotics1scene-generation1world-action-model1
10 stories, newest first · one card per story
Stories tagged #diffusion-transformers
Paper generates 3D scenes in implicit latents from 2D models
Diffusion transformers model scenes in a 3D latent from DINOv2, SigLIP2, and DA3 instead of redundant 2D views.
Dyna-2: General Purpose Physical Agents with Hour-Long Autonomy — Jason Ma, Dyna Robotics
Dyna Robotics details Dyna-2, a world-action model trained on a million hours and deployed on working robots.
5
MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers
Training-free MC-Sparse speeds diffusion-transformer denoising up to 2.32× with negligible quality loss.
MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers
MC-Sparse narrows the dense-sparse attention gap, speeding diffusion denoising up to 2.32× with little quality loss.
Structured Residual Connectivity Matters for Diffusion Transformers
Structured residual paths in diffusion transformers cut FID and training iterations with almost no extra parameters.
Beyond Future Prediction: Denoising as Generative Adaptation for Robot Control
NowWAM adapts diffusion transformers for robot control by denoising current frames, hitting 87.7% on LIBERO-Plus.
VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention
VC-Attention is a training-free low-bit attention method for diffusion transformers, achieving 1.46-1.59x kernel speedups on datacenter GPUs with higher fidelity.
Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation
Marigold V2 adapts diffusion transformers for monocular depth estimation, improving AbsRel 16-26% over the previous best on KITTI and ETH3D.
VoT: Vision-of-Thought for Unified Multimodal Representation Alignment
Researchers propose Vision-of-Thought (VoT), a discrete visual-planning token layer between VLMs and diffusion transformers improving text-to-image semantic alignment.