Artificial intelligence (AI)-based chest X-ray (CXR) interpretation assistants have demonstrated significant progress and are increasingly being applied in clinical settings. However, contemporary medical AI models often adhere to a simplistic input-to-output paradigm, directly processing an image and an instruction to generate a result, where the instructions may be integral to the model's architecture. This approach overlooks the modeling of the inherent diagnostic reasoning in chest X-ray interpretation. Such reasoning is typically sequential, where each interpretive stage considers the images, the current task, and the contextual information from previous stages. This oversight leads to several shortcomings, including misalignment with clinical scenarios, contextless reasoning, and untraceable errors. To fill this gap, we construct CXRTrek, a new multi-stage visual question answering (VQA) dataset for CXR interpretation. The dataset is designed to explicitly simulate the diagnostic reasoning process employed by radiologists in real-world clinical settings for the first time. CXRTrek covers 8 sequential diagnostic stages, comprising 428,966 samples and over 11 million question-answer (Q&A) pairs, with an average of 26.29 Q&A pairs per sample. Building on the CXRTrek dataset, we propose a new vision-language large model (VLLM), CXRTrekNet, specifically designed to incorporate the clinical reasoning flow into the VLLM framework. CXRTrekNet effectively models the dependencies between diagnostic stages and captures reasoning patterns within the radiological context. Trained on our dataset, the model consistently outperforms existing medical VLLMs on the CXRTrek benchmarks and demonstrates superior generalization across multiple tasks on five diverse external datasets. The dataset and model can be found in our repository (https://github.com/guanjinquan/CXRTrek).
Appearance editing according to user needs is a pivotal task in video editing. Existing text-guided methods often lead to ambiguities regarding user intentions and restrict fine-grained control over editing specific aspects of objects. To overcome these limitations, this paper introduces a novel approach named {Zero-to-Hero}, which focuses on reference-based video editing that disentangles the editing process into two distinct problems. It achieves this by first editing an anchor frame to satisfy user requirements as a reference image and then consistently propagating its appearance across other frames. We leverage correspondence within the original frames to guide the attention mechanism, which is more robust than previously proposed optical flow or temporal modules in memory-friendly video generative models, especially when dealing with objects exhibiting large motions. It offers a solid ZERO-shot initialization that ensures both accuracy and temporal consistency. However, intervention in the attention mechanism results in compounded imaging degradation with over-saturated colors and unknown blurring issues. Starting from Zero-Stage, our Hero-Stage Holistically learns a conditional generative model for vidEo RestOration. To accurately evaluate the consistency of the appearance, we construct a set of videos with multiple appearances using Blender, enabling a fine-grained and deterministic evaluation. Our method outperforms the best-performing baseline with a PSNR improvement of 2.6 dB. The project page is at https://github.com/Tonniia/Zero2Hero.
Co-Speech Gesture Video Generation aims to generate vivid speech videos from audio-driven still images, which is challenging due to the diversity of different parts of the body in terms of amplitude of motion, audio relevance, and detailed features. Relying solely on audio as the control signal often fails to capture large gesture movements in video, leading to more pronounced artifacts and distortions. Existing approaches typically address this issue by introducing additional a priori information, but this can limit the practical application of the task. Specifically, we propose a Motion Mask-Guided Two-Stage Network (MMGT) that uses audio, as well as motion masks and motion features generated from the audio signal to jointly drive the generation of synchronized speech gesture videos. In the first stage, the Spatial Mask-Guided Audio Pose Generation (SMGA) Network generates high-quality pose videos and motion masks from audio, effectively capturing large movements in key regions such as the face and gestures. In the second stage, we integrate the Motion Masked Hierarchical Audio Attention (MM-HAA) into the Stabilized Diffusion Video Generation model, overcoming limitations in fine-grained motion generation and region-specific detail control found in traditional methods. This guarantees high-quality, detailed upper-body video generation with accurate texture and motion details. Evaluations show improved video quality, lip-sync, and gesture. The model and code are available at https://github.com/SIA-IDE/MMGT.
Lightweight semantic segmentation is essential for many downstream vision tasks. Unfortunately, existing methods often struggle to balance efficiency and performance due to the complexity of feature modeling. Many of these existing approaches are constrained by rigid architectures and implicit representation learning, often characterized by parameter-heavy designs and a reliance on computationally intensive Vision Transformer-based frameworks. In this work, we introduce an efficient paradigm by synergizing explicit and implicit modeling to balance computational efficiency with representational fidelity. Our method combines well-defined Cartesian directions with explicitly modeled views and implicitly inferred intermediate representations, efficiently capturing global dependencies through a nested attention mechanism. Extensive experiments on challenging datasets, including ADE20K, CityScapes, Pascal Context, and COCO-Stuff, demonstrate that LeMoRe strikes an effective balance between performance and efficiency.
Existing low-light image enhancement (LLIE) and joint LLIE and deblurring (LLIE-deblur) models have made strides in addressing predefined degradations, yet they are often constrained by dynamically coupled degradations. To address these challenges, we introduce a Unified Receptance Weighted Key Value (URWKV) model with multi-state perspective, enabling flexible and effective degradation restoration for low-light images. Specifically, we customize the core URWKV block to perceive and analyze complex degradations by leveraging multiple intra- and inter-stage states. First, inspired by the pupil mechanism in the human visual system, we propose Luminance-adaptive Normalization (LAN) that adjusts normalization parameters based on rich inter-stage states, allowing for adaptive, scene-aware luminance modulation. Second, we aggregate multiple intra-stage states through exponential moving average approach, effectively capturing subtle variations while mitigating information loss inherent in the single-state mechanism. To reduce the degradation effects commonly associated with conventional skip connections, we propose the State-aware Selective Fusion (SSF) module, which dynamically aligns and integrates multi-state features across encoder stages, selectively fusing contextual information. In comparison to state-of-the-art models, our URWKV model achieves superior performance on various benchmarks, while requiring significantly fewer parameters and computational resources.
Compositional generalization is the ability of generalizing novel compositions from seen primitives, and has received much attention in vision-and-language (V\&L) recently. Due to the multi-modal nature of V\&L tasks, the primitives composing compositions source from different modalities, resulting in multi-sourced novel compositions. However, the generalization ability over multi-sourced novel compositions, \textit{i.e.}, multi-sourced compositional generalization (MSCG) remains unexplored. In this paper, we explore MSCG in the context of visual question answering (VQA), and propose a retrieval-augmented training framework to enhance the MSCG ability of VQA models by learning unified representations for primitives from different modalities. Specifically, semantically equivalent primitives are retrieved for each primitive in the training samples, and the retrieved features are aggregated with the original primitive to refine the model. This process helps the model learn consistent representations for the same semantic primitives across different modalities. To evaluate the MSCG ability of VQA models, we construct a new GQA-MSCG dataset based on the GQA dataset, in which samples include three types of novel compositions composed of primitives from different modalities. Experimental results demonstrate the effectiveness of the proposed framework. We release GQA-MSCG at https://github.com/NeverMoreLCH/MSCG.
Recent advancements in unified vision-language models (VLMs), which integrate both visual understanding and generation capabilities, have attracted significant attention. The underlying hypothesis is that a unified architecture with mixed training on both understanding and generation tasks can enable mutual enhancement between understanding and generation. However, this hypothesis remains underexplored in prior works on unified VLMs. To address this gap, this paper systematically investigates the generalization across understanding and generation tasks in unified VLMs. Specifically, we design a dataset closely aligned with real-world scenarios to facilitate extensive experiments and quantitative evaluations. We evaluate multiple unified VLM architectures to validate our findings. Our key findings are as follows. First, unified VLMs trained with mixed data exhibit mutual benefits in understanding and generation tasks across various architectures, and this mutual benefits can scale up with increased data. Second, better alignment between multimodal input and output spaces will lead to better generalization. Third, the knowledge acquired during generation tasks can transfer to understanding tasks, and this cross-task generalization occurs within the base language model, beyond modality adapters. Our findings underscore the critical necessity of unifying understanding and generation in VLMs, offering valuable insights for the design and optimization of unified VLMs.
Deep models, such as convolutional neural networks (CNNs) and vision transformer (ViT), demonstrate remarkable performance in image classification. However, those deep models require large data to fine-tune, which is impractical in the medical domain due to the data privacy issue. Furthermore, despite the feasible performance of contrastive language image pre-training (CLIP) in the natural domain, the potential of CLIP has not been fully investigated in the medical field. To face these challenges, we considered three scenarios: 1) we introduce a novel CLIP variant using four CNNs and eight ViTs as image encoders for the classification of brain cancer and skin cancer, 2) we combine 12 deep models with two federated learning techniques to protect data privacy, and 3) we involve traditional machine learning (ML) methods to improve the generalization ability of those deep models in unseen domain data. The experimental results indicate that maxvit shows the highest averaged (AVG) test metrics (AVG = 87.03\%) in HAM10000 dataset with multimodal learning, while convnext\_l demonstrates remarkable test with an F1-score of 83.98\% compared to swin\_b with 81.33\% in FL model. Furthermore, the use of support vector machine (SVM) can improve the overall test metrics with AVG of $\sim 2\%$ for swin transformer series in ISIC2018. Our codes are available at https://github.com/AIPMLab/SkinCancerSimulation.
Traditional approaches in unsupervised or self supervised learning for skeleton-based action classification have concentrated predominantly on the dynamic aspects of skeletal sequences. Yet, the intricate interaction between the moving and static elements of the skeleton presents a rarely tapped discriminative potential for action classification. This paper introduces a novel measurement, referred to as spatial-temporal joint density (STJD), to quantify such interaction. Tracking the evolution of this density throughout an action can effectively identify a subset of discriminative moving and/or static joints termed "prime joints" to steer self-supervised learning. A new contrastive learning strategy named STJD-CL is proposed to align the representation of a skeleton sequence with that of its prime joints while simultaneously contrasting the representations of prime and nonprime joints. In addition, a method called STJD-MP is developed by integrating it with a reconstruction-based framework for more effective learning. Experimental evaluations on the NTU RGB+D 60, NTU RGB+D 120, and PKUMMD datasets in various downstream tasks demonstrate that the proposed STJD-CL and STJD-MP improved performance, particularly by 3.5 and 3.6 percentage points over the state-of-the-art contrastive methods on the NTU RGB+D 120 dataset using X-sub and X-set evaluations, respectively.
Modern VLMs have achieved near-saturation accuracy in English document visual question-answering (VQA). However, this task remains challenging in lower resource languages due to a dearth of suitable training and evaluation data. In this paper we present scalable methods for curating such datasets by focusing on Hungarian, approximately the 17th highest resource language on the internet. Specifically, we present HuDocVQA and HuDocVQA-manual, document VQA datasets that modern VLMs significantly underperform on compared to English DocVQA. HuDocVQA-manual is a small manually curated dataset based on Hungarian documents from Common Crawl, while HuDocVQA is a larger synthetically generated VQA data set from the same source. We apply multiple rounds of quality filtering and deduplication to HuDocVQA in order to match human-level quality in this dataset. We also present HuCCPDF, a dataset of 117k pages from Hungarian Common Crawl PDFs along with their transcriptions, which can be used for training a model for Hungarian OCR. To validate the quality of our datasets, we show how finetuning on a mixture of these datasets can improve accuracy on HuDocVQA for Llama 3.2 11B Instruct by +7.2%. Our datasets and code will be released to the public to foster further research in multilingual DocVQA.
The ability to simulate the world in a spatially consistent manner is a crucial requirements for effective world models. Such a model enables high-quality visual generation, and also ensures the reliability of world models for downstream tasks such as simulation and planning. Designing a memory module is a crucial component for addressing spatial consistency: such a model must not only retain long-horizon observational information, but also enables the construction of explicit or implicit internal spatial representations. However, there are no dataset designed to promote the development of memory modules by explicitly enforcing spatial consistency constraints. Furthermore, most existing benchmarks primarily emphasize visual coherence or generation quality, neglecting the requirement of long-range spatial consistency. To bridge this gap, we construct a dataset and corresponding benchmark by sampling 150 distinct locations within the open-world environment of Minecraft, collecting about 250 hours (20 million frames) of loop-based navigation videos with actions. Our dataset follows a curriculum design of sequence lengths, allowing models to learn spatial consistency on increasingly complex navigation trajectories. Furthermore, our data collection pipeline is easily extensible to new Minecraft environments and modules. Four representative world model baselines are evaluated on our benchmark. Dataset, benchmark, and code are open-sourced to support future research.
Diffusion Transformers (DiT) have become the de-facto model for generating high-quality visual content like videos and images. A huge bottleneck is the attention mechanism where complexity scales quadratically with resolution and video length. One logical way to lessen this burden is sparse attention, where only a subset of tokens or patches are included in the calculation. However, existing techniques fail to preserve visual quality at extremely high sparsity levels and might even incur non-negligible compute overheads. % To address this concern, we propose Re-ttention, which implements very high sparse attention for visual generation models by leveraging the temporal redundancy of Diffusion Models to overcome the probabilistic normalization shift within the attention mechanism. Specifically, Re-ttention reshapes attention scores based on the prior softmax distribution history in order to preserve the visual quality of the full quadratic attention at very high sparsity levels. % Experimental results on T2V/T2I models such as CogVideoX and the PixArt DiTs demonstrate that Re-ttention requires as few as 3.1\% of the tokens during inference, outperforming contemporary methods like FastDiTAttn, Sparse VideoGen and MInference. Further, we measure latency to show that our method can attain over 45\% end-to-end % and over 92\% self-attention latency reduction on an H100 GPU at negligible overhead cost. Code available online here: \href{https://github.com/cccrrrccc/Re-ttention}{https://github.com/cccrrrccc/Re-ttention}
Continual learning is rapidly emerging as a key focus in computer vision, aiming to develop AI systems capable of continuous improvement, thereby enhancing their value and practicality in diverse real-world applications. In healthcare, continual learning holds great promise for continuously acquired digital pathology data, which is collected in hospitals on a daily basis. However, panoramic segmentation on digital whole slide images (WSIs) presents significant challenges, as it is often infeasible to obtain comprehensive annotations for all potential objects, spanning from coarse structures (e.g., regions and unit objects) to fine structures (e.g., cells). This results in temporally and partially annotated data, posing a major challenge in developing a holistic segmentation framework. Moreover, an ideal segmentation model should incorporate new phenotypes, unseen diseases, and diverse populations, making this task even more complex. In this paper, we introduce a novel and unified Incremental Relationship-guided Segmentation (IRS) learning scheme to address temporally acquired, partially annotated data while maintaining out-of-distribution (OOD) continual learning capacity in digital pathology. The key innovation of IRS lies in its ability to realize a new spatial-temporal OOD continual learning paradigm by mathematically modeling anatomical relationships between existing and newly introduced classes through a simple incremental universal proposition matrix. Experimental results demonstrate that the IRS method effectively handles the multi-scale nature of pathological segmentation, enabling precise kidney segmentation across various structures (regions, units, and cells) as well as OOD disease lesions at multiple magnifications. This capability significantly enhances domain generalization, making IRS a robust approach for real-world digital pathology applications.
Gaussian Splatting (GS) has recently emerged as an efficient representation for rendering 3D scenes from 2D images and has been extended to images, videos, and dynamic 4D content. However, applying style transfer to GS-based representations, especially beyond simple color changes, remains challenging. In this work, we introduce CLIPGaussians, the first unified style transfer framework that supports text- and image-guided stylization across multiple modalities: 2D images, videos, 3D objects, and 4D scenes. Our method operates directly on Gaussian primitives and integrates into existing GS pipelines as a plug-in module, without requiring large generative models or retraining from scratch. CLIPGaussians approach enables joint optimization of color and geometry in 3D and 4D settings, and achieves temporal coherence in videos, while preserving a model size. We demonstrate superior style fidelity and consistency across all tasks, validating CLIPGaussians as a universal and efficient solution for multimodal style transfer.
Object counting has progressed from class-specific models, which count only known categories, to class-agnostic models that generalize to unseen categories. The next challenge is Referring Expression Counting (REC), where the goal is to count objects based on fine-grained attributes and contextual differences. Existing methods struggle with distinguishing visually similar objects that belong to the same category but correspond to different referring expressions. To address this, we propose C-REX, a novel contrastive learning framework, based on supervised contrastive learning, designed to enhance discriminative representation learning. Unlike prior works, C-REX operates entirely within the image space, avoiding the misalignment issues of image-text contrastive learning, thus providing a more stable contrastive signal. It also guarantees a significantly larger pool of negative samples, leading to improved robustness in the learned representations. Moreover, we showcase that our framework is versatile and generic enough to be applied to other similar tasks like class-agnostic counting. To support our approach, we analyze the key components of sota detection-based models and identify that detecting object centroids instead of bounding boxes is the key common factor behind their success in counting tasks. We use this insight to design a simple yet effective detection-based baseline to build upon. Our experiments show that C-REX achieves state-of-the-art results in REC, outperforming previous methods by more than 22\% in MAE and more than 10\% in RMSE, while also demonstrating strong performance in class-agnostic counting. Code is available at https://github.com/cvlab-stonybrook/c-rex.
Visual texts embedded in videos carry rich semantic information, which is crucial for both holistic video understanding and fine-grained reasoning about local human actions. However, existing video understanding benchmarks largely overlook textual information, while OCR-specific benchmarks are constrained to static images, limiting their ability to capture the interaction between text and dynamic visual contexts. To address this gap, we propose VidText, a new benchmark designed for comprehensive and in-depth evaluation of video text understanding. VidText offers the following key features: 1) It covers a wide range of real-world scenarios and supports multilingual content, encompassing diverse settings where video text naturally appears. 2) It introduces a hierarchical evaluation framework with video-level, clip-level, and instance-level tasks, enabling assessment of both global summarization and local retrieval capabilities. 3) The benchmark also introduces a set of paired perception reasoning tasks, ranging from visual text perception to cross-modal reasoning between textual and visual information. Extensive experiments on 18 state-of-the-art Large Multimodal Models (LMMs) reveal that current models struggle across most tasks, with significant room for improvement. Further analysis highlights the impact of both model-intrinsic factors, such as input resolution and OCR capability, and external factors, including the use of auxiliary information and Chain-of-Thought reasoning strategies. We hope VidText will fill the current gap in video understanding benchmarks and serve as a foundation for future research on multimodal reasoning with video text in dynamic environments.
Motivation: Model selection is a ubiquitous challenge in statistics. For penalized models, model selection typically entails tuning hyperparameters to maximize a measure of fit or minimize out-of-sample prediction error. However, these criteria fail to reflect other desirable characteristics, such as model sparsity, interpretability, or smoothness. Results: We present the R package pared to enable the use of multi-objective optimization for model selection. Our approach entails the use of Gaussian process-based optimization to efficiently identify solutions that represent desirable trade-offs. Our implementation includes popular models with multiple objectives including the elastic net, fused lasso, fused graphical lasso, and group graphical lasso. Our R package generates interactive graphics that allow the user to identify hyperparameter values that result in fitted models which lie on the Pareto frontier. Availability: We provide the R package pared and vignettes illustrating its application to both simulated and real data at https://github.com/priyamdas2/pared.
Classifier-Free Guidance (CFG) is a widely used technique for improving conditional diffusion models by linearly combining the outputs of conditional and unconditional denoisers. While CFG enhances visual quality and improves alignment with prompts, it often reduces sample diversity, leading to a challenging trade-off between quality and diversity. To address this issue, we make two key contributions. First, CFG generally does not correspond to a well-defined denoising diffusion model (DDM). In particular, contrary to common intuition, CFG does not yield samples from the target distribution associated with the limiting CFG score as the noise level approaches zero -- where the data distribution is tilted by a power $w \gt 1$ of the conditional distribution. We identify the missing component: a R\'enyi divergence term that acts as a repulsive force and is required to correct CFG and render it consistent with a proper DDM. Our analysis shows that this correction term vanishes in the low-noise limit. Second, motivated by this insight, we propose a Gibbs-like sampling procedure to draw samples from the desired tilted distribution. This method starts with an initial sample from the conditional diffusion model without CFG and iteratively refines it, preserving diversity while progressively enhancing sample quality. We evaluate our approach on both image and text-to-audio generation tasks, demonstrating substantial improvements over CFG across all considered metrics. The code is available at https://github.com/yazidjanati/cfgig
The Lasso is a prominent algorithm for variable selection. However, its instability in the presence of correlated variables in the high-dimensional setting is well-documented. Although previous research has attempted to address this issue by modifying the Lasso loss function, this paper introduces an approach that simplifies the data processed by Lasso. We propose that decorrelating variables before applying the Lasso improves the stability of variable selection regardless of the direction of correlation among predictors. Furthermore, we highlight that the irrepresentable condition, which ensures consistency for the Lasso, is satisfied after variable decorrelation under two assumptions. In addition, by noting that the instability of the Lasso is not limited to high-dimensional settings, we demonstrate the effectiveness of the proposed approach for low-dimensional data. Finally, we present empirical results that indicate the efficacy of the proposed method across different variable selection techniques, highlighting its potential for broader application. The DVS R package is developed to facilitate the implementation of the methodology proposed in this paper.
The field of hypothesis generation promises to reduce costs in neuroscience by narrowing the range of interventional studies needed to study various phenomena. Existing machine learning methods can generate scientific hypotheses from complex datasets, but many approaches assume causal relationships are static over time, limiting their applicability to systems with dynamic, state-dependent behavior, such as the brain. While some techniques attempt dynamic causal discovery through factor models, they often restrict relationships to linear patterns or impose other simplifying assumptions. We propose a novel method that models dynamic graphs as a conditionally weighted superposition of static graphs, where each static graph can capture nonlinear relationships. This approach enables the detection of complex, time-varying interactions between variables beyond linear limitations. Our method improves f1-scores of predicted dynamic causal patterns by roughly 22-28% on average over baselines in some of our experiments, with some improvements reaching well over 60%. A case study on real brain data demonstrates our method's ability to uncover relationships linked to specific behavioral states, offering valuable insights into neural dynamics.