261 citations · 444 across the 32 of their papers we have counts for
36 papers
PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation
Cong Wei, Xuanchi Ren, Bryan Chu +8
Unified Multimodal Models (UMMs) often rely on separate visual representations for understanding and generation, increasing visual context length and complicating integration with…
NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation
NVIDIA, :, Aarti Basant +33
As autonomous vehicle capabilities advance, the safe evaluation of driving policies in long-tail scenarios remains a critical bottleneck. In closed-loop simulation, the driving pol…
Data-Forcing Distillation: Restoring Diversity and Fidelity in Few-Step Video Generation
Siyi Chen, Shaowei Liu, Yixuan Jia +4
Recent progress has shown promise in distilling multi-step video diffusion models into efficient few-step students. Among them, Distribution Matching Distillation (DMD) and its suc…
APE: Agentic Prompt Enhancer for Image Generation and Editing
Zijian Huang, Jay Zhangjie Wu, Zian Wang +5
Natural language has become a powerful interface for image generation and editing, yet text-guided visual systems remain highly sensitive to prompt formulation. Semantically simila…
PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion
Yifan Lu, Qi Wu, Jay Zhangjie Wu +4
Most practical high-resolution text-to-image systems, including latent diffusion and autoregressive models, perform generation in a compact latent space, and a decoder maps the gen…
Lyra 2.0: Explorable Generative 3D Worlds
Tianchang Shen, Sherwin Bahmani, Kai He +12
Recent advances in video generation enable a new paradigm for 3D scene creation: generating camera-controlled videos that simulate scene walkthroughs, then lifting them to 3D via f…
MoRight: Motion Control Done Right
Shaowei Liu, Xuanchi Ren, Tianchang Shen +5
Generating motion-controlled videos--where user-specified actions drive physically plausible scene dynamics under freely chosen viewpoints--demands two capabilities: (1) disentangl…
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
Kewei Zhang, Ye Huang, Yufan Deng +5
While the Transformer architecture dominates many fields, its quadratic self-attention complexity hinders its use in large-scale applications. Linear attention offers an efficient…
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…
ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation
Jay Zhangjie Wu, Xuanchi Ren, Tianchang Shen +11
Recent advances in large generative models have greatly enhanced both image editing and in-context image generation, yet a critical gap remains in ensuring physical consistency, wh…
SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
Junsong Chen, Yuyang Zhao, Jincheng Yu +17
We introduce SANA-Video, a small diffusion model that can efficiently generate videos up to 720x1280 resolution and minute-length duration. SANA-Video synthesizes high-resolution,…
Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation
Sherwin Bahmani, Tianchang Shen, Jiawei Ren +10
The ability to generate virtual environments is crucial for applications ranging from gaming to physical AI domains such as robotics, autonomous driving, and industrial AI. Current…
ViPE: Video Pose Engine for 3D Geometric Perception
Jiahui Huang, Qunjie Zhou, Hesam Rabeti +12
Accurate 3D geometric perception is an important prerequisite for a wide range of spatial AI systems. While state-of-the-art methods depend on large-scale training data, acquiring…
Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models
Xuanchi Ren, Yifan Lu, Tianshi Cao +13
Collecting and annotating real-world data for safety-critical physical AI systems, such as Autonomous Vehicle (AV), is time-consuming and costly. It is especially challenging to ca…
Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control
NVIDIA, :, Hassan Abu Alhaija +38
We introduce Cosmos-Transfer, a conditional world generation model that can generate world simulations based on multiple spatial control inputs of various modalities such as segmen…
GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control
Xuanchi Ren, Tianchang Shen, Jiahui Huang +7
We present GEN3C, a generative video model with precise Camera Control and temporal 3D Consistency. Prior video models already generate realistic videos, but they tend to leverage…
Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models
Jay Zhangjie Wu, Yuxuan Zhang, Haithem Turki +6
Neural Radiance Fields and 3D Gaussian Splatting have revolutionized 3D reconstruction and novel-view synthesis task. However, achieving photorealistic rendering from extreme novel…
DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models
Ruofan Liang, Zan Gojcic, Huan Ling +8
Understanding and modeling lighting effects are fundamental tasks in computer vision and graphics. Classic physically-based rendering (PBR) accurately simulates the light transport…
Cosmos World Foundation Model Platform for Physical AI
NVIDIA, :, Niket Agarwal +76
Physical AI needs to be trained digitally first. It needs a digital twin of itself, the policy model, and a digital twin of the world, the world model. In this paper, we present th…
Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos
Hanxue Liang, Jiawei Ren, Ashkan Mirzaei +8
Recent advancements in static feed-forward scene reconstruction have demonstrated significant progress in high-quality novel view synthesis. However, these models often struggle wi…
SCube: Instant Large-Scale Scene Reconstruction using VoxSplats
Xuanchi Ren, Yifan Lu, Hanxue Liang +6
We present SCube, a novel method for reconstructing large-scale 3D scenes (geometry, appearance, and semantics) from a sparse set of posed images. Our method encodes reconstructed…
L4GM: Large 4D Gaussian Reconstruction Model
Jiawei Ren, Kevin Xie, Ashkan Mirzaei +8
We present L4GM, the first 4D Large Reconstruction Model that produces animated objects from a single-view video input -- in a single feed-forward pass that takes only a second. Ke…
Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models
Huan Ling, Seung Wook Kim, Antonio Torralba +2
Text-guided diffusion models have revolutionized image and video generation and have also been successfully used for optimization-based 3D object synthesis. Here, we instead focus…
3DiffTection: 3D Object Detection with Geometry-Aware Diffusion Features
Chenfeng Xu, Huan Ling, Sanja Fidler +1
We present 3DiffTection, a state-of-the-art method for 3D object detection from single images, leveraging features from a 3D-aware diffusion model. Annotating large-scale image dat…