We present Omni-I2C, a comprehensive benchmark designed to evaluate the capability of Large Multimodal Models (LMMs) in converting complex, structured digital graphics into executable code. We argue that this task represents a non-trivial challenge for the current generation of LMMs: it demands an unprecedented synergy between high-fidelity visual perception -- to parse intricate spatial hierarchies and symbolic details -- and precise generative expression -- to synthesize syntactically sound and logically consistent code. Unlike traditional descriptive tasks, Omni-I2C requires a holistic understanding where any minor perceptual hallucination or coding error leads to a complete failure in visual reconstruction. Omni-I2C features 1080 meticulously curated samples, defined by its breadth across subjects, image modalities, and programming languages. By incorporating authentic user-sourced cases, the benchmark spans a vast spectrum of digital content -- from scientific visualizations to complex symbolic notations -- each paired with executable reference code. To complement this diversity, our evaluation framework provides necessary depth; by decoupling performance into perceptual fidelity and symbolic precision, it transcends surface-level accuracy to expose the granular structural failures and reasoning bottlenecks of current LMMs. Our evaluation reveals a substantial performance gap among leading LMMs; even state-of-the-art models struggle to preserve structural integrity in complex scenarios, underscoring that multimodal code generation remains a formidable challenge. Data and code are available at https://github.com/MiliLab/Omni-I2C.
OmniEarth-Bench: Towards Holistic Evaluation of Earth's Six Spheres and Cross-Spheres Interactions with Multimodal Observational Earth Data
National University of Defense Technology, China（国防科技大学）；Shanghai Artificial Intelligence Laboratory, China（上海人工智能实验室）；Beijing University of Posts and Telecommunications, China（北京邮电大学）；Zhejiang University, China（浙江大学）；Shanghai Jiao Tong University, China（上海交通大学）；Fudan University, China（复旦大学）；Sun Yat-sen University, China（中山大学）；Nanjing University, China（南京大学）；University of Science and Technology of China（中国科学技术大学）；Wuhan University, China（武汉大学）
Wuhan University（武汉大学）；North Carolina State University（北卡罗来纳州立大学）
This paper studies the problem of holistic 3D wireframe perception (HoW-3D), a new task of perceiving both the visible 3D wireframes and the invisible ones from single-view 2D images. As the non-front surfaces of an object cannot be directly observed in a single view, estimating the non-line-of-sight (NLOS) geometries in HoW-3D is a fundamentally challenging problem and remains open in computer vision. We study the problem of HoW-3D by proposing an ABC-HoW benchmark, which is created on top of CAD models sourced from the ABC-dataset with 12k single-view images and the corresponding holistic 3D…
OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding
The Hong Kong Polytechnic University（香港理工大学）；OPPO Research Institute（OPPO研究院）；Colorado School of Mines（科罗拉多矿业学院）；Nanyang Technological University（南洋理工大学）；Shanghai Jiao Tong University（上海交通大学）
Perceptually Grounded and Semantics-Aware Evaluation for Holistic Co-Speech Gesture Generation
Max Planck Institute for Psycholinguistics（马克斯·普朗克心理语言学研究所）；Utrecht University（乌得勒支大学）；Donders Institute for Brain Cognition and Behaviour（唐德斯脑认知与行为研究所）
CUHK-Shenzhen（香港中文大学（深圳））；The Future Network of Intelligence Institute, CUHK-Shenzhen（香港中文大学（深圳）未来智联网络研究院）
We present a new framework to reconstruct holistic 3D indoor scenes including both room background and indoor objects from single-view images. Existing methods can only produce 3D shapes of indoor objects with limited geometry quality because of the heavy occlusion of indoor scenes. To solve this, we propose an instance-aligned implicit function (InstPIFu) for detailed object reconstruction. Combining with instance-aligned attention module, our method is empowered to decouple mixed local features toward the occluded instances. Additionally, unlike previous methods that simply represents the ro…
Technical University of Denmark（丹麦技术大学）；Helmholtz Munich（慕尼黑亥姆霍兹中心）；Google（谷歌公司）；Northwestern University（西北大学）；Technical University of Munich（慕尼黑工业大学）；Munich Center of Machine Learning（慕尼黑机器学习中心）；University of Copenhagen（哥本哈根大学）；Copenhagen University Hospital（哥本哈根大学医院）
OmniScaleSR: Unleashing Scale-Controlled Diffusion Prior for Faithful and Realistic Arbitrary-Scale Image Super-Resolution
School of Information Science and Electronic Engineering, Shanghai Jiao Tong University（上海交通大学信息科学与电子工程学院）；College of Information, Mechanical and Electrical Engineering, Shanghai Normal University（上海师范大学信息、机械与电气工程学院）；Transsion in China（中国Transsion）；MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University（上海交通大学人工智能教育部重点实验室）
Xi’an Jiaotong University（西安交通大学）；Tsinghua University（清华大学）；DAMO Academy, Alibaba Group（阿里云实验室）；Chinese Academy of Sciences（中国科学院）；National University of Singapore（新加坡国立大学）
Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models
School of Computer Science and Technology, UCAS（UCAS计算机科学与技术学院）；The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, CASIA（复杂系统认知与决策智能重点实验室）；School of Computer Science and Engineering, Beihang University（北航计算机科学与工程学院）；State Key Laboratory of Networking and Switching Technology, BUPT（网络与交换技术国家重点实验室）；AMAP, Alibaba Group（阿里妈妈实验室，阿里巴巴集团）
Institute of Trustworthy Embodied AI, Fudan University（复旦大学可信具身人工智能研究所）；Shanghai Collaborative Innovation Center of Intelligent Visual Computing（上海智能视觉计算协同创新中心）；Bytedance Seed（字节跳动Seed）；The University of Hong Kong（香港大学）
Lumina-OmniLV: A Unified Multimodal Framework for General Low-Level Vision
Shanghai Jiao Tong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）；University of Macau（澳门大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Shenzhen University of Advanced Technology（深圳先进技术大学）；Institute of Artificial Intelligence (TeleAI), China Telecom（中国电信人工智能研究院（TeleAI））
EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；JAIST（日本先进科学技术研究所）；Tsinghua University（清华大学）；The University of Tokyo（东京大学）；Keio University（庆应义塾大学）
A training-free framework for high-fidelity appearance transfer via diffusion transformers
School of Intelligence Science and Technology, Nanjing University（南京大学智能科学与技术学院）；School of Artificial Intelligence, Jilin University（吉林大学人工智能学院）；School of New Media and Communication, Tianjin University（天津大学新媒体与传播学院）；JIUTIAN Research（中移九天）；State Key Laboratory of Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）
OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-Time Self-Aware Emotional Speech Synthesis
Shenzhen Key Laboratory for High Performance Data Mining（深圳高性能数据挖掘重点实验室）；Shenzhen Institute of Advanced Technology（深圳先进技术研究院）；Chinese Academy of Sciences（中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）；Tongyi Laboratory（通义实验室）；University of New South Wales（新南威尔士大学）；National University of Singapore（新加坡国立大学）；University of Science and Technology of China（中国科学技术大学）；MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition（脑启发智能感知与认知重点实验室）
AnyID: Ultra-Fidelity Universal Identity-Preserving Video Generation from Any Visual References
School of Computer Science and Technology, MOEKLINNS, Xi’an Jiaotong University（西安交通大学计算机科学与技术学院、MOEKLINNS）；Alibaba Cloud Computing（阿里云计算有限公司）；Tsinghua University（清华大学）
Multimodal Prompt Perceiver: Empower Adaptiveness, Generalizability and Fidelity for All-in-One Image Restoration
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；University of Science and Technology of China（中国科学技术大学）
