Tag
CoInteract introduces an end-to-end Diffusion Transformer framework that jointly models RGB appearance and HOI geometry to generate physically-plausible human-object interaction videos with stable hands/faces and zero inference overhead.
HiCoDiT is a novel Hierarchical Codec Diffusion Transformer for video-to-speech generation that leverages the hierarchical structure of RVQ-based codec discrete speech tokens, using coarse-to-fine conditioning with dual-scale normalization to achieve strong audio-visual alignment.
HiVLA introduces a hierarchical vision-language-action framework that decouples semantic planning from motor control using a diffusion transformer action expert for improved robotic manipulation. The system combines a VLM planner for task decomposition and visual grounding with a specialized DiT action expert using cascaded cross-attention, outperforming end-to-end baselines particularly in long-horizon tasks and fine-grained manipulation.
OneHOI is a unified diffusion transformer framework that consolidates human-object interaction (HOI) generation and editing into a single conditional denoising process using relational modeling and structured attention mechanisms. The approach achieves state-of-the-art results across both HOI generation and editing tasks with support for multiple control modalities.
Baidu releases ERNIE-Image, an open-weight text-to-image generation model with 8B parameters built on Diffusion Transformer architecture, achieving state-of-the-art performance among open-weight models with strong capabilities in text rendering, instruction following, and structured image generation.
Baidu releases ERNIE-Image-Turbo, a distilled text-to-image generation model that achieves fast generation in 8 inference steps while maintaining strong text rendering, instruction following, and structured image generation capabilities.
Nucleus-Image is an open-source text-to-image diffusion transformer with 17B parameters across 64 routed experts, activating only ~2B parameters per forward pass. It matches or exceeds leading models like Qwen-Image and Imagen4 while maintaining high efficiency, released with full model weights, training code, and dataset.