collaborators

6 papers

cs.CV2026

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…

cs.LG2026

Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation

Yuying Li, Leqi Zheng, Yongzi Yu +6

On-Policy distillation (OPD) in large language models is shifting from full-trace KL supervision toward more selective training paradigms. Recent OPD methods increasingly focus on…

cs.CV2026

Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenization

Xuanyu Zhu, Yan Bai, Yang Shi +4

Representation autoencoders that reuse frozen pretrained vision encoders as visual tokenizers have achieved strong reconstruction and generation quality. However, existing methods…

cs.CV2026

MMVIAD: Multi-view Multi-task Video Understanding for Industrial Anomaly Detection

Xiran Zhao, Jing Jin, Yan Bai +6

Industrial anomaly detection is critical for manufacturing quality control, yet existing datasets mainly focus on static images or sparse views, which do not fully reflect continuo…

cs.CV2025

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…

cs.AI2025

Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning

NVIDIA, :, Alisson Azzolini +51

Physical AI systems need to perceive, understand, and perform complex actions in the physical world. In this paper, we present the Cosmos-Reason1 models that can understand the phy…