Search

Recent advancements have established Diffusion Transformers (DiTs) as a dominant framework in generative modeling. Building on this success, Lumina-Next achieves exceptional performance in the generation of photorealistic images with Next-DiT. However, its potential for video generation remains largely untapped, with significant challenges in modeling the spatiotemporal complexity inherent to video data. To address this, we introduce Lumina-Video, a framework that leverages the strengths of Next-DiT while introducing tailored solutions for video synthesis. Lumina-Video incorporates a Multi-scale Next-DiT architecture, which jointly learns multiple patchifications to enhance both efficiency and flexibility. By incorporating the motion score as an explicit condition, Lumina-Video also enables direct control of generated videos' dynamic degree. Combined with a progressive training scheme with increasingly higher resolution and FPS, and a multi-source training scheme with mixed natural and synthetic data, Lumina-Video achieves remarkable aesthetic quality and motion smoothness at high training and inference efficiency. We additionally propose Lumina-V2A, a video-to-audio model based on Next-DiT, to create synchronized sounds for generated videos. Codes are released at https://www.github.com/Alpha-VLLM/Lumina-Video.

We present TAR3D, a novel framework that consists of a 3D-aware Vector Quantized-Variational AutoEncoder (VQ-VAE) and a Generative Pre-trained Transformer (GPT) to generate high-quality 3D assets. The core insight of this work is to migrate the multimodal unification and promising learning capabilities of the next-token prediction paradigm to conditional 3D object generation. To achieve this, the 3D VQ-VAE first encodes a wide range of 3D shapes into a compact triplane latent space and utilizes a set of discrete representations from a trainable codebook to reconstruct fine-grained geometries under the supervision of query point occupancy. Then, the 3D GPT, equipped with a custom triplane position embedding called TriPE, predicts the codebook index sequence with prefilling prompt tokens in an autoregressive manner so that the composition of 3D geometries can be modeled part by part. Extensive experiments on ShapeNet and Objaverse demonstrate that TAR3D can achieve superior generation quality over existing methods in text-to-3D and image-to-3D tasks

Diffusion models have demonstrated impressive performance in face restoration. Yet, their multi-step inference process remains computationally intensive, limiting their applicability in real-world scenarios. Moreover, existing methods often struggle to generate face images that are harmonious, realistic, and consistent with the subject's identity. In this work, we propose OSDFace, a novel one-step diffusion model for face restoration. Specifically, we propose a visual representation embedder (VRE) to better capture prior information and understand the input face. In VRE, low-quality faces are processed by a visual tokenizer and subsequently embedded with a vector-quantized dictionary to generate visual prompts. Additionally, we incorporate a facial identity loss derived from face recognition to further ensure identity consistency. We further employ a generative adversarial network (GAN) as a guidance model to encourage distribution alignment between the restored face and the ground truth. Experimental results demonstrate that OSDFace surpasses current state-of-the-art (SOTA) methods in both visual quality and quantitative metrics, generating high-fidelity, natural face images with high identity consistency. The code and model will be released at https://github.com/jkwang28/OSDFace., Comment: 8 pages, 6 figures. The code and model will be available at https://github.com/jkwang28/OSDFace

For the diagnosis of diabetes retinopathy (DR) images, this paper proposes a classification method based on artificial intelligence. The core lies in a new data augmentation method, GreenBen, which first extracts the green channel grayscale image from the retinal image and then performs Ben enhancement. Considering that diabetes macular edema (DME) is a complication closely related to DR, this paper constructs a joint classification framework of DR and DME based on multi task learning and attention module, and uses GreenBen to enhance its data to reduce the difference of DR images and improve the accuracy of model classification. We conducted extensive experiments on three publicly available datasets, and our method achieved the best results. For GreenBen, whether based on the ResNet50 network or the Swin Transformer network, whether for individual classification or joint DME classification, compared with other data augmentation methods, GreenBen achieved stable and significant improvements in DR classification results, with an accuracy increase of 10%.

We propose a physics-informed data-driven framework for urban wind estimation. This framework validates and incorporates the Reynolds number independence for flows under various working conditions, thus allowing the extrapolation for wind conditions far beyond the training data. Another key enabler is a machine-learned non-dimensionalized manifold from snapshot data. The velocity field is modeled using a double encoder-decoder approach. The first encoder normalizes data using the oncoming wind speed, while the second encoder projects this normalized data onto the isometric feature mapping manifold. The decoders reverse this process, with $k$-nearest neighbor performing the first decoding and the second undoing the normalization. The manifold is coarse-grained by clustering to reduce the computational load for de- and encoding. The sensor-based flow estimation is based on the estimate of the oncoming wind speed and a mapping from sensor signal to the manifold latent variables. The proposed machine-learned flow estimation framework is exemplified for the flow above an Unmanned Aerial Vehicle vertiport. The wind estimation is shown to generalize well for rare wind conditions, not included in the original database.

Medical abstractive summarization faces the challenge of balancing faithfulness and informativeness. Current methods often sacrifice key information for faithfulness or introduce confabulations when prioritizing informativeness. While recent advancements in techniques like in-context learning (ICL) and fine-tuning have improved medical summarization, they often overlook crucial aspects such as faithfulness and informativeness without considering advanced methods like model reasoning and self-improvement. Moreover, the field lacks a unified benchmark, hindering systematic evaluation due to varied metrics and datasets. This paper addresses these gaps by presenting a comprehensive benchmark of six advanced abstractive summarization methods across three diverse datasets using five standardized metrics. Building on these findings, we propose uMedSum, a modular hybrid summarization framework that introduces novel approaches for sequential confabulation removal followed by key missing information addition, ensuring both faithfulness and informativeness. Our work improves upon previous GPT-4-based state-of-the-art (SOTA) medical summarization methods, significantly outperforming them in both quantitative metrics and qualitative domain expert evaluations. Notably, we achieve an average relative performance improvement of 11.8% in reference-free metrics over the previous SOTA. Doctors prefer uMedSum's summaries 6 times more than previous SOTA in difficult cases where there are chances of confabulations or missing information. These results highlight uMedSum's effectiveness and generalizability across various datasets and metrics, marking a significant advancement in medical summarization., Comment: 12 pages

Light fields (LFs), conducive to comprehensive scene radiance recorded across angular dimensions, find wide applications in 3D reconstruction, virtual reality, and computational photography.However, the LF acquisition is inevitably time-consuming and resource-intensive due to the mainstream acquisition strategy involving manual capture or laborious software synthesis.Given such a challenge, we introduce LFdiff, a straightforward yet effective diffusion-based generative framework tailored for LF synthesis, which adopts only a single RGB image as input.LFdiff leverages disparity estimated by a monocular depth estimation network and incorporates two distinctive components: a novel condition scheme and a noise estimation network tailored for LF data.Specifically, we design a position-aware warping condition scheme, enhancing inter-view geometry learning via a robust conditional signal.We then propose DistgUnet, a disentanglement-based noise estimation network, to harness comprehensive LF representations.Extensive experiments demonstrate that LFdiff excels in synthesizing visually pleasing and disparity-controllable light fields with enhanced generalization capability.Additionally, comprehensive results affirm the broad applicability of the generated LF data, spanning applications like LF super-resolution and refocusing., Comment: 11 pages,9 figures

The study of complex networks has significantly advanced our understanding of community structures which serves as a crucial feature of real-world graphs. Detecting communities in graphs is a challenging problem with applications in sociology, biology, and computer science. Despite the efforts of an interdisciplinary community of scientists, a satisfactory solution to this problem has not yet been achieved. This review article delves into the topic of community detection in graphs, which serves as a thorough exposition of various community detection methods from perspectives of modularity-based method, spectral clustering, probabilistic modelling, and deep learning. Along with the methods, a new community detection method designed by us is also presented. Additionally, the performance of these methods on the datasets with and without ground truth is compared. In conclusion, this comprehensive review provides a deep understanding of community detection in graphs.

Experimental assessment of safe and precise flight control algorithms for unmanned aerial vehicles (UAVs) under gusty wind conditions requires the capability to generate a large range of velocity profiles. In this study, we employ a small fan array wind generator which can generate flows with large spatial and temporal variability. We perform a thorough aerodynamic characterization operating the fans uniformly from a low to the maximum level. PIV and hot-wire measurements indicate a jet-like flow with nearly uniform core which monotonously contracts in streamwise direction and surrounding growing unsteady shear-layers. These complex dynamics results in a limited region with desired flow profile and turbulence level. The experimental results shed light on the flow generated by a full-scale fan array wind generator, and indicate the need for further improvements via properly designed add-ons and dedicated control algorithms., Comment: 22 pages

Deep learning has opened up new possibilities for light field super-resolution (SR), but existing methods trained on synthetic datasets with simple degradations (e.g., bicubic downsampling) suffer from poor performance when applied to complex real-world scenarios. To address this problem, we introduce LytroZoom, the first real-world light field SR dataset capturing paired low- and high-resolution light fields of diverse indoor and outdoor scenes using a Lytro ILLUM camera. Additionally, we propose the Omni-Frequency Projection Network (OFPNet), which decomposes the omni-frequency components and iteratively enhances them through frequency projection operations to address spatially variant degradation processes present in all frequency components. Experiments demonstrate that models trained on LytroZoom outperform those trained on synthetic datasets and are generalizable to diverse content and devices. Quantitative and qualitative evaluations verify the superiority of OFPNet. We believe this work will inspire future research in real-world light field SR., Comment: CVPRW 2023

Designing an effective representation learning method for multimodal sentiment analysis tasks is a crucial research direction. The challenge lies in learning both shared and private information in a complete modal representation, which is difficult with uniform multimodal labels and a raw feature fusion approach. In this work, we propose a deep modal shared information learning module based on the covariance matrix to capture the shared information between modalities. Additionally, we use a label generation module based on a self-supervised learning strategy to capture the private information of the modalities. Our module is plug-and-play in multimodal tasks, and by changing the parameterization, it can adjust the information exchange relationship between the modes and learn the private or shared information between the specified modes. We also employ a multi-task learning strategy to help the model focus its attention on the modal differentiation training data. We provide a detailed formulation derivation and feasibility proof for the design of the deep modal shared information learning module. We conduct extensive experiments on three common multimodal sentiment analysis baseline datasets, and the experimental results validate the reliability of our model. Furthermore, we explore more combinatorial techniques for the use of the module. Our approach outperforms current state-of-the-art methods on most of the metrics of the three public datasets.

Privacy protection raises great attention on both legal levels and user awareness. To protect user privacy, countries enact laws and regulations requiring software privacy policies to regulate their behavior. However, privacy policies are written in natural languages with many legal terms and software jargon that prevent users from understanding and even reading them. It is desirable to use NLP techniques to analyze privacy policies for helping users understand them. Furthermore, existing datasets ignore law requirements and are limited to English. In this paper, we construct the first Chinese privacy policy dataset, namely CA4P-483, to facilitate the sequence labeling tasks and regulation compliance identification between privacy policies and software. Our dataset includes 483 Chinese Android application privacy policies, over 11K sentences, and 52K fine-grained annotations. We evaluate families of robust and representative baseline models on our dataset. Based on baseline performance, we provide findings and potential research directions on our dataset. Finally, we investigate the potential applications of CA4P-483 combing regulation requirements and program analysis., Comment: Accepted by EMNLP 2022 (The 2022 Conference on Empirical Methods in Natural Language Processing)