publications

2026

1. NeurIPS

   GenScale: A Benchmark for Relative Object Scale in Image Generation and Editing

   Lingxiao Li , Max Whitton , Ledell Wu , and Boqing Gong

   In Conference on Neural Information Processing Systems (NeurIPS), Evaluations and Datasets Track, 2026

   Abs PDF Project Page

   Modern image generation and editing systems can produce photorealistic, prompt-aligned images, but still often render familiar objects at implausible relative sizes. To measure this failure mode, we introduce GenScale, a benchmark and evaluation protocol for real-world relative object scale in image generation and editing. GenScale contains 900 image-level entries and 1,643 pairwise anchor-target scale relations across common-object generation, human-product generation with metric dimensions, and scale correction from failed generations. We further design a human-calibrated ordinal judge for scalable pairwise scale evaluation. Last but not the least, we introduce Rescale, a model-agnostic post-processing agent for localized scale correction without modifying the source generator. Experiments reveal that state-of-the-art image generators and editors cannot reliably observe relative scale yet, while Rescale consistently improves scale plausibility across generated and edited images. Together, GenScale establishes relative object scale as a distinct, measurable, and actionable capability for image generation systems.

2. ECCV

   Moiré Video Authentication: A Physical Signature Against AI Video Generation

   Yuan Qing* , Kunyu Zheng* , Lingxiao Li* , Boqing Gong , and Chang Xiao

   In European Conference on Computer Vision (ECCV), 2026

   Abs PDF Code Project Page

   Recent advances in video generation have made AI-synthesized content increasingly difficult to distinguish from real footage. We propose a physics-based authentication signature that real cameras produce naturally, but that generative models cannot faithfully reproduce. Our approach exploits the Moiré effect: the interference fringes formed when a camera views a compact two-layer grating structure. We derive the Moiré motion invariant, showing that fringe phase and grating image displacement are linearly coupled by optical geometry, independent of viewing distance and grating structure. A verifier extracts both signals from video and tests their correlation. We validate the invariant on both real-captured and AI-generated videos from multiple state-of-the-art generators, and find that real and AI-generated videos produce significantly different correlation signatures, suggesting a robust means of differentiating them. Our work demonstrates that deterministic optical phenomena can serve as physically grounded, verifiable signatures against AI-generated video.

3. ECCV

   VisReason: A Large-Scale Dataset for Visual Chain-of-Thought Reasoning

   Lingxiao Li , Yifan Wang , Xinyan Gao , Chen Tang , Xiangyu Yue , and Chenyu You

   In European Conference on Computer Vision (ECCV), 2026

   Abs PDF Code Project Page

   Chain-of-Thought (CoT) prompting has proven remarkably effective for eliciting complex reasoning in large language models (LLMs). Yet, its potential in multimodal large language models (MLLMs) remains largely untapped, hindered by the absence of large-scale datasets that capture the rich, spatially grounded reasoning intrinsic to visual understanding. Existing visual-CoT resources are typically small, domain-specific, or lack the human-like stepwise structure necessary for compositional visual reasoning. In this paper, we introduce VisReason, a large-scale dataset designed to advance visual Chain-of-Thought reasoning. VisReason comprises 489K annotated examples spanning four diverse domains, each featuring multi-round, human-like rationales that guide MLLMs through interpretable visual reasoning steps. Building upon this, we curate VisReason-Pro, a 165K subset produced with a stronger expert-level GPT annotator, enriched with detailed reasoning traces and 3D spatial grounding via depth-informed annotations. Fine-tuning the state-of-the-art Qwen2.5-VL model on VisReason and VisReason-Pro yields substantial improvements in step-by-step visual reasoning accuracy, interpretability, and cross-benchmark generalization. These results demonstrate that VisReason equips MLLMs with more systematic and generalizable reasoning capabilities. We envision VisReason as a cornerstone for cultivating human-like visual reasoning, paving the way toward the next generation of multimodal intelligence.

2025

1. ICCV

   HypDAE: Hyperbolic Diffusion Autoencoders for Hierarchical Few-shot Image Generation

   Lingxiao Li , Kaixuan Fan , Boqing Gong , and Xiangyu Yue

   In International Conference on Computer Vision (ICCV), 2025

   Abs PDF Code Project Page

   Few-shot image generation aims to generate diverse and high-quality images for an unseen class given only a few examples in that class. However, existing methods often suffer from a trade-off between image quality and diversity while offering limited control over the attributes of newly generated images. In this work, we propose Hyperbolic Diffusion Autoencoders (HypDAE), a novel approach that operates in hyperbolic space to capture hierarchical relationships among images and texts from seen categories. By leveraging pre-trained foundation models, HypDAE generates diverse new images for unseen categories with exceptional quality by varying semantic codes or guided by textual instructions. Most importantly, the hyperbolic representation introduces an additional degree of control over semantic diversity through the adjustment of radii within the hyperbolic disk. Extensive experiments and visualizations demonstrate that HypDAE significantly outperforms prior methods by achieving a superior balance between quality and diversity with limited data and offers a highly controllable and interpretable generation process.

2. ASPLOS

   Nazar: Monitoring and Adapting ML Models on Mobile Devices

   Wei Hao , Zixi Wang , Lauren Hong , Lingxiao Li , Nader Karayanni , Chengzhi Mao , Junfeng Yang , and Asaf Cidon

   In ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2025

   Abs PDF

   ML models are increasingly being pushed to mobile devices, for low-latency inference and offline operation. However, once the models are deployed, it is hard for ML operators to track their accuracy, which can degrade unpredictably (e.g., due to data drift). We design Nazar, the first end-to-end system for continuously monitoring and adapting models on mobile devices without requiring feedback from users. Our key observation is that often model degradation is due to a specific root cause, which may affect a large group of devices. Therefore, once Nazar detects a consistent degradation across a large number of devices, it employs a root cause analysis to determine the origin of the problem and applies a cause-specific adaptation. We evaluate Nazar on two computer vision datasets, and show it consistently boosts accuracy compared to existing approaches. On a dataset containing photos collected from driving cars, Nazar improves the accuracy on average by 15%.

3. TMC

   radarODE: an ODE-Embedded Deep Learning Model for Contactless ECG Reconstruction from Millimeter-Wave Radar

   Yuanyuan Zhang , Runwei Guan , Lingxiao Li , Rui Yang , Yutao Yue , and Eng Gee Lim

   IEEE Transactions on Mobile Computing , 2025

   Abs PDF

   Radar-based cardiac monitoring has become a popular research direction recently, but the fine-grained electrocardiogram (ECG) signal is still hard to reconstruct from millimeter-wave radar signal. The key obstacle is to decouple cardiac activities in the electrical domain (i.e., ECG) from that in the mechanical domain (i.e., heartbeat), and most existing research only uses purely data-driven methods to map such domain transformation as a black box. Therefore, this work first proposes a signal model that considers the fine-grained cardiac feature sensed by radar, and a novel deep learning framework called radarODE is designed to extract both temporal and morphological features for generating ECG. In addition, ordinary differential equations are embedded in radarODE as a decoder to provide morphological prior, helping the convergence of the model training and improving the robustness under body movements. After being validated on the dataset, the proposed radarODE achieves better performance compared with the benchmark in terms of missed detection rate, root mean square error, Pearson correlation coefficient with improvements of 9%, 16% and 19%, respectively. The validation results imply that radarODE is capable of recovering ECG signals from radar signals with high fidelity and can potentially be implemented in real-life scenarios

2024

1. NeurIPS

   BIFRÖST: 3D-Aware Image compositing with Language Instructions

   Lingxiao Li , Kaixiong Gong , Weihong Li , Xili Dai , Tao Chen , Xiaojun Yuan , and Xiangyu Yue

   In Advanced Neural Information Processing System (NeurIPS), 2024

   Abs PDF Code Project Page

   This paper introduces Bifröst, a novel 3D-aware framework that is built upon diffusion models to perform instruction-based image composition. Previous methods concentrate on image compositing at the 2D level, which fall short in handling complex spatial relationships (e.g., occlusion). Bifröst addresses these issues by training MLLM as a 2.5D location predictor and integrating depth maps as an extra condition during the generation process to bridge the gap between 2D and 3D, which enhances spatial comprehension and supports sophisticated spatial interactions. Our method begins by fine-tuning MLLM with a custom counterfactual dataset to predict 2.5D object locations in complex backgrounds from language instructions. Then, the image-compositing model is uniquely designed to process multiple types of input features, enabling it to perform high-fidelity image compositions that consider occlusion, depth blur, and image harmonization. Extensive qualitative and quantitative evaluations demonstrate that Bifröst significantly outperforms existing methods, providing a robust solution for generating realistically composed images in scenarios demanding intricate spatial understanding. This work not only pushes the boundaries of generative image compositing but also reduces reliance on expensive annotated datasets by effectively utilizing existing resources in innovative ways.

2023

1. ICCV

   The Euclidean Space is Evil: Hyperbolic Attribute Editing for Few-shot Image Generation

   Lingxiao Li , Yi Zhang , and Shuhui Wang

   In International Conference on Computer Vision (ICCV), 2023

   Abs PDF Code

   Few-shot image generation is a challenging task since it aims to generate diverse new images for an unseen category with only a few images. Existing methods suffer from the trade-off between the quality and diversity of generated images. To tackle this problem, we propose Hyperbolic Attribute Editing(HAE), a simple yet effective method. Unlike prior arts that work in Euclidean space, HAE captures the hierarchy among images using data from seen categories in hyperbolic space. Given a well-trained HAE, images of unseen categories can be generated by moving the latent code of a given image toward any meaningful directions in the Poincaré disk with a fixing radius. Most importantly, the hyperbolic space allows us to control the semantic diversity of the generated images by setting different radii in the disk. Extensive experiments and visualizations demonstrate that HAE is capable of not only generating images with promising quality and diversity using limited data but achieving a highly controllable and interpretable editing process.

2018

1. ITME

   Model Checking the Reliability of Data Center Network

   Congwei Ni , Sihan Cheng , Xutao Wang , Tianyun Hu , Zhenjin Dai , Dongliang Zhang , Lingxiao Li , and Xin Huang

   In 9th International Conference on Information Technology in Medicine and Education (ITME), 2018

   Abs DOI PDF

   Data center network provides a basis for internet-based applications nowadays, thereby the reliability of it is vital. The purpose of this research is to examine and compare the reliability of two data center network architectures, which are Common Tree and Fat-tree topology structure. To verify the reliability of these two architectures, a tool called PRISM with the function of probabilistic model checking is used in this paper. Results show that Fat-tree topology structure is more reliable than Common Tree, and the reliabilities of core layer, edge/ aggregation layer and terminal layer decline sequentially.