8 papers
Cosmos 3: Omnimodal World Models for Physical AI
NVIDIA, :, Aditi +293
We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-t…
The Pragmatic Persona: Discovering LLM Persona through Bridging Inference
Jisoo Yang, Jongwon Ryu, Minuk Ma +2
Large Language Models (LLMs) reveal inherent and distinctive personas through dialogue. However, most existing persona discovery approaches rely on surface-level lexical or stylist…
A Hidden Semantic Bottleneck in Conditional Embeddings of Diffusion Transformers
Trung X. Pham, Kang Zhang, Ji Woo Hong +1
Diffusion Transformers have achieved state-of-the-art performance in class-conditional and multimodal generation, yet the structure of their learned conditional embeddings remains…
World Simulation with Video Foundation Models for Physical AI
NVIDIA, :, Arslan Ali +87
We introduce [Cosmos-Predict2.5], the latest generation of the Cosmos World Foundation Models for Physical AI. Built on a flow-based architecture, [Cosmos-Predict2.5] unifies Text2…
Model-Guided Dual-Role Alignment for High-Fidelity Open-Domain Video-to-Audio Generation
Kang Zhang, Trung X. Pham, Suyeon Lee +3
We present MGAudio, a novel flow-based framework for open-domain video-to-audio generation, which introduces model-guided dual-role alignment as a central design principle. Unlike…
ITA-MDT: Image-Timestep-Adaptive Masked Diffusion Transformer Framework for Image-Based Virtual Try-On
Ji Woo Hong, Tri Ton, Trung X. Pham +3
This paper introduces ITA-MDT, the Image-Timestep-Adaptive Masked Diffusion Transformer Framework for Image-Based Virtual Try-On (IVTON), designed to overcome the limitations of pr…