Diffusion Transformer (DiT)
PulseAugur coverage of Diffusion Transformer (DiT) — every cluster mentioning Diffusion Transformer (DiT) across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
StepAudio 3 models advance real-time dialogue, general audio, and music generation
Researchers have introduced the StepAudio 3 family of models, encompassing real-time interaction, general audio generation, and music creation. StepAudio 3 Realtime focuses on continuous spoken dialogue with a listen-co…
-
LLaDA-Image sets new open-source SOTA for image generation
Researchers have introduced LLaDA-Image, a novel framework for generating high-quality images using a 6B Diffusion Transformer trained from scratch. This model leverages image-only pre-training and a specialized optimiz…
-
New RASA framework disentangles spatial and motion priors for character animation
Researchers have developed RASA, a new framework for cross-identity character animation that disentangles spatial mapping from motion control. The system uses a two-stage process: a Spatial Prior Calibrator to align ide…
-
New research explores advanced diffusion models for generation, robustness, and speed
Researchers are developing advanced diffusion models for various applications, including image generation, time-series synthesis, and natural language processing. New methods like Simplax aim to improve categorical gene…
-
New pruning framework slashes image model size, enables 24GB GPU inference
Researchers have developed a Tree-structured Mixed-policy Pruning (TMP) framework designed to reduce the parameter count and computational requirements of large-scale image generation models. This framework is applicabl…
-
BrainG3N introduces dual-purpose tokenizer for controllable 3D brain MRI generation
Researchers have developed BrainG3N, a novel tokenizer for generating 3D brain MRI scans. This system utilizes a dual-purpose approach with a masked-autoencoder (MAE) encoder and a CNN decoder, decoupling the need for c…
-
New research tackles video generation challenges in control, consistency, and efficiency
Researchers are developing advanced techniques for video generation, focusing on improving control, consistency, and efficiency. CineOrchestra aims to unify control over subjects, cameras, and shot transitions in cinema…