We investigate the convergence properties of popular data-augmentation samplers for Bayesian probit regression. Leveraging recent results on Gibbs samplers for log-concave targets, we provide simple and explicit non-asymptotic bounds on the associated mixing times (in Kullback-Leibler divergence). The bounds depend explicitly on the design matrix and the prior precision, while they hold uniformly over the vector of responses. We specialize the results for different regimes of statistical interest, when both the number of data points $n$ and parameters $p$ are large: in particular we identify scenarios where the mixing times remain bounded as $n,p\to\infty$, and ones where they do not. The results are shown to be tight (in the worst case with respect to the responses) and provide guidance on choices of prior distributions that provably lead to fast mixing. An empirical analysis based on coupling techniques suggests that the bounds are effective in predicting practically observed behaviours.
This paper introduces a discriminator-free adversarial-based approach termed DDA-MLIC for Unsupervised Domain Adaptation (UDA) in the context of Multi-Label Image Classification (MLIC). While recent efforts have explored adversarial-based UDA methods for MLIC, they typically include an additional discriminator subnet. Nevertheless, decoupling the classification and the discrimination tasks may harm their task-specific discriminative power. Herein, we address this challenge by presenting a novel adversarial critic directly derived from the task-specific classifier. Specifically, we employ a two-component Gaussian Mixture Model (GMM) to model both source and target predictions, distinguishing between two distinct clusters. Instead of using the traditional Expectation Maximization (EM) algorithm, our approach utilizes a Deep Neural Network (DNN) to estimate the parameters of each GMM component. Subsequently, the source and target GMM parameters are leveraged to formulate an adversarial loss using the Fr\'echet distance. The proposed framework is therefore not only fully differentiable but is also cost-effective as it avoids the expensive iterative process usually induced by the standard EM method. The proposed method is evaluated on several multi-label image datasets covering three different types of domain shift. The obtained results demonstrate that DDA-MLIC outperforms existing state-of-the-art methods in terms of precision while requiring a lower number of parameters. The code is made publicly available at github.com/cvi2snt/DDA-MLIC.
This paper introduces Multimodal Speculative Decoding (MSD) to accelerate Multimodal Large Language Models (MLLMs) inference. Speculative decoding has been shown to accelerate Large Language Models (LLMs) without sacrificing accuracy. However, current speculative decoding methods for MLLMs fail to achieve the same speedup as they do for LLMs. To address this, we reimagine speculative decoding specifically for MLLMs. Our analysis of MLLM characteristics reveals two key design principles for MSD: (1) Text and visual tokens have fundamentally different characteristics and need to be processed separately during drafting. (2) Both language modeling ability and visual perception capability are crucial for the draft model. For the first principle, MSD decouples text and visual tokens in the draft model, allowing each to be handled based on its own characteristics. For the second principle, MSD uses a two-stage training strategy: In stage one, the draft model is trained on text-only instruction-tuning datasets to improve its language modeling ability. In stage two, MSD gradually introduces multimodal data to enhance the visual perception capability of the draft model. Experiments show that MSD boosts inference speed by up to $2.29\times$ for LLaVA-1.5-7B and up to $2.46\times$ for LLaVA-1.5-13B on multimodal benchmarks, demonstrating its effectiveness. Our code is available at https://github.com/Lyn-Lucy/MSD.
Text-to-image diffusion models have emerged as powerful tools for high-quality image generation and editing. Many existing approaches rely on text prompts as editing guidance. However, these methods are constrained by the need for manual prompt crafting, which can be time-consuming, introduce irrelevant details, and significantly limit editing performance. In this work, we propose optimizing semantic embeddings guided by attribute classifiers to steer text-to-image models toward desired edits, without relying on text prompts or requiring any training or fine-tuning of the diffusion model. We utilize classifiers to learn precise semantic embeddings at the dataset level. The learned embeddings are theoretically justified as the optimal representation of attribute semantics, enabling disentangled and accurate edits. Experiments further demonstrate that our method achieves high levels of disentanglement and strong generalization across different domains of data.
A key trend in Large Reasoning Models (e.g., OpenAI's o3) is the native agentic ability to use external tools such as web browsers for searching and writing/executing code for image manipulation to think with images. In the open-source research community, while significant progress has been made in language-only agentic abilities such as function calling and tool integration, the development of multi-modal agentic capabilities that involve truly thinking with images, and their corresponding benchmarks, are still less explored. This work highlights the effectiveness of Visual Agentic Reinforcement Fine-Tuning (Visual-ARFT) for enabling flexible and adaptive reasoning abilities for Large Vision-Language Models (LVLMs). With Visual-ARFT, open-source LVLMs gain the ability to browse websites for real-time information updates and write code to manipulate and analyze input images through cropping, rotation, and other image processing techniques. We also present a Multi-modal Agentic Tool Bench (MAT) with two settings (MAT-Search and MAT-Coding) designed to evaluate LVLMs' agentic search and coding abilities. Our experimental results demonstrate that Visual-ARFT outperforms its baseline by +18.6% F1 / +13.0% EM on MAT-Coding and +10.3% F1 / +8.7% EM on MAT-Search, ultimately surpassing GPT-4o. Visual-ARFT also achieves +29.3 F1% / +25.9% EM gains on existing multi-hop QA benchmarks such as 2Wiki and HotpotQA, demonstrating strong generalization capabilities. Our findings suggest that Visual-ARFT offers a promising path toward building robust and generalizable multimodal agents.
We propose Visual-only Question Answering (VoQA), a novel multimodal task in which questions are visually embedded within images, without any accompanying textual input. This requires models to locate, recognize, and reason over visually embedded textual questions, posing challenges for existing large vision-language models (LVLMs), which show notable performance drops even with carefully designed prompts. To bridge this gap, we introduce Guided Response Triggering Supervised Fine-tuning (GRT-SFT), a structured fine-tuning strategy that guides the model to perform step-by-step reasoning purely based on visual input, significantly improving model performance. Our work enhances models' capacity for human-like visual understanding in complex multimodal scenarios, where information, including language, is perceived visually.
Density regression models allow a comprehensive understanding of data by modeling the complete conditional probability distribution. While flexible estimation approaches such as normalizing flows (NF) work particularly well in multiple dimensions, interpreting the input-output relationship of such models is often difficult, due to the black-box character of deep learning models. In contrast, existing statistical methods for multivariate outcomes such as multivariate conditional transformation models (MCTM) are restricted in flexibility and are often not expressive enough to represent complex multivariate probability distributions. In this paper, we combine MCTM with state-of-the-art and autoregressive NF to leverage the transparency of MCTM for modeling interpretable feature effects on the marginal distributions in the first step and the flexibility of neural-network-based NF techniques to account for complex and non-linear relationships in the joint data distribution. We demonstrate our method's versatility in various numerical experiments and compare it with MCTM and other NF models on both simulated and real-world data.
Knowledge distillation (KD) is a valuable technique for compressing large deep learning models into smaller, edge-suitable networks. However, conventional KD frameworks rely on pre-trained high-capacity teacher networks, which introduce significant challenges such as increased memory/storage requirements, additional training costs, and ambiguity in selecting an appropriate teacher for a given student model. Although a teacher-free distillation (self-distillation) has emerged as a promising alternative, many existing approaches still rely on architectural modifications or complex training procedures, which limit their generality and efficiency. To address these limitations, we propose a novel framework based on teacher-free distillation that operates using a single student network without any auxiliary components, architectural modifications, or additional learnable parameters. Our approach is built on a simple yet highly effective augmentation, called intra-class patch swap augmentation. This augmentation simulates a teacher-student dynamic within a single model by generating pairs of intra-class samples with varying confidence levels, and then applying instance-to-instance distillation to align their predictive distributions. Our method is conceptually simple, model-agnostic, and easy to implement, requiring only a single augmentation function. Extensive experiments across image classification, semantic segmentation, and object detection show that our method consistently outperforms both existing self-distillation baselines and conventional teacher-based KD approaches. These results suggest that the success of self-distillation could hinge on the design of the augmentation itself. Our codes are available at https://github.com/hchoi71/Intra-class-Patch-Swap.
Few-Shot Segmentation (FSS) aims to learn class-agnostic segmentation on few classes to segment arbitrary classes, but at the risk of overfitting. To address this, some methods use the well-learned knowledge of foundation models (e.g., SAM) to simplify the learning process. Recently, SAM 2 has extended SAM by supporting video segmentation, whose class-agnostic matching ability is useful to FSS. A simple idea is to encode support foreground (FG) features as memory, with which query FG features are matched and fused. Unfortunately, the FG objects in different frames of SAM 2's video data are always the same identity, while those in FSS are different identities, i.e., the matching step is incompatible. Therefore, we design Pseudo Prompt Generator to encode pseudo query memory, matching with query features in a compatible way. However, the memories can never be as accurate as the real ones, i.e., they are likely to contain incomplete query FG, and some unexpected query background (BG) features, leading to wrong segmentation. Hence, we further design Iterative Memory Refinement to fuse more query FG features into the memory, and devise a Support-Calibrated Memory Attention to suppress the unexpected query BG features in memory. Extensive experiments have been conducted on PASCAL-5$^i$ and COCO-20$^i$ to validate the effectiveness of our design, e.g., the 1-shot mIoU can be 4.2% better than the best baseline.
Place recognition is a cornerstone of vehicle navigation and mapping, which is pivotal in enabling systems to determine whether a location has been previously visited. This capability is critical for tasks such as loop closure in Simultaneous Localization and Mapping (SLAM) and long-term navigation under varying environmental conditions. In this survey, we comprehensively review recent advancements in place recognition, emphasizing three representative methodological paradigms: Convolutional Neural Network (CNN)-based approaches, Transformer-based frameworks, and cross-modal strategies. We begin by elucidating the significance of place recognition within the broader context of autonomous systems. Subsequently, we trace the evolution of CNN-based methods, highlighting their contributions to robust visual descriptor learning and scalability in large-scale environments. We then examine the emerging class of Transformer-based models, which leverage self-attention mechanisms to capture global dependencies and offer improved generalization across diverse scenes. Furthermore, we discuss cross-modal approaches that integrate heterogeneous data sources such as Lidar, vision, and text description, thereby enhancing resilience to viewpoint, illumination, and seasonal variations. We also summarize standard datasets and evaluation metrics widely adopted in the literature. Finally, we identify current research challenges and outline prospective directions, including domain adaptation, real-time performance, and lifelong learning, to inspire future advancements in this domain. The unified framework of leading-edge place recognition methods, i.e., code library, and the results of their experimental evaluations are available at https://github.com/CV4RA/SOTA-Place-Recognitioner.
Document image parsing is challenging due to its complexly intertwined elements such as text paragraphs, figures, formulas, and tables. Current approaches either assemble specialized expert models or directly generate page-level content autoregressively, facing integration overhead, efficiency bottlenecks, and layout structure degradation despite their decent performance. To address these limitations, we present \textit{Dolphin} (\textit{\textbf{Do}cument Image \textbf{P}arsing via \textbf{H}eterogeneous Anchor Prompt\textbf{in}g}), a novel multimodal document image parsing model following an analyze-then-parse paradigm. In the first stage, Dolphin generates a sequence of layout elements in reading order. These heterogeneous elements, serving as anchors and coupled with task-specific prompts, are fed back to Dolphin for parallel content parsing in the second stage. To train Dolphin, we construct a large-scale dataset of over 30 million samples, covering multi-granularity parsing tasks. Through comprehensive evaluations on both prevalent benchmarks and self-constructed ones, Dolphin achieves state-of-the-art performance across diverse page-level and element-level settings, while ensuring superior efficiency through its lightweight architecture and parallel parsing mechanism. The code and pre-trained models are publicly available at https://github.com/ByteDance/Dolphin
The pursuit of decision safety in clinical applications highlights the potential of concept-based methods in medical imaging. While these models offer active interpretability, they often suffer from concept leakages, where unintended information within soft concept representations undermines both interpretability and generalizability. Moreover, most concept-based models focus solely on local explanations (instance-level), neglecting the global decision logic (dataset-level). To address these limitations, we propose Concept Rule Learner (CRL), a novel framework to learn Boolean logical rules from binarized visual concepts. CRL employs logical layers to capture concept correlations and extract clinically meaningful rules, thereby providing both local and global interpretability. Experiments on two medical image classification tasks show that CRL achieves competitive performance with existing methods while significantly improving generalizability to out-of-distribution data. The code of our work is available at https://github.com/obiyoag/crl.
Adversarial training is one of the most effective adversarial defenses, but it incurs a high computational cost. In this study, we show that transformers adversarially pretrained on diverse tasks can serve as robust foundation models and eliminate the need for adversarial training in downstream tasks. Specifically, we theoretically demonstrate that through in-context learning, a single adversarially pretrained transformer can robustly generalize to multiple unseen tasks without any additional training, i.e., without any parameter updates. This robustness stems from the model's focus on robust features and its resistance to attacks that exploit non-predictive features. Besides these positive findings, we also identify several limitations. Under certain conditions (though unrealistic), no universally robust single-layer transformers exist. Moreover, robust transformers exhibit an accuracy--robustness trade-off and require a large number of in-context demonstrations. The code is available at https://github.com/s-kumano/universally-robust-in-context-learner.
In this paper, we present a multi-label stereo matching method to simultaneously estimate the depth of the transparent objects and the occluded background in transparent scenes.Unlike previous methods that assume a unimodal distribution along the disparity dimension and formulate the matching as a single-label regression problem, we propose a multi-label regression formulation to estimate multiple depth values at the same pixel in transparent scenes. To resolve the multi-label regression problem, we introduce a pixel-wise multivariate Gaussian representation, where the mean vector encodes multiple depth values at the same pixel, and the covariance matrix determines whether a multi-label representation is necessary for a given pixel. The representation is iteratively predicted within a GRU framework. In each iteration, we first predict the update step for the mean parameters and then use both the update step and the updated mean parameters to estimate the covariance matrix. We also synthesize a dataset containing 10 scenes and 89 objects to validate the performance of transparent scene depth estimation. The experiments show that our method greatly improves the performance on transparent surfaces while preserving the background information for scene reconstruction. Code is available at https://github.com/BFZD233/TranScene.
Long videos contain a vast amount of information, making video-text retrieval an essential and challenging task in multimodal learning. However, existing benchmarks suffer from limited video duration, low-quality captions, and coarse annotation granularity, which hinder the evaluation of advanced video-text retrieval methods. To address these limitations, we introduce LoVR, a benchmark specifically designed for long video-text retrieval. LoVR contains 467 long videos and over 40,804 fine-grained clips with high-quality captions. To overcome the issue of poor machine-generated annotations, we propose an efficient caption generation framework that integrates VLM automatic generation, caption quality scoring, and dynamic refinement. This pipeline improves annotation accuracy while maintaining scalability. Furthermore, we introduce a semantic fusion method to generate coherent full-video captions without losing important contextual information. Our benchmark introduces longer videos, more detailed captions, and a larger-scale dataset, presenting new challenges for video understanding and retrieval. Extensive experiments on various advanced embedding models demonstrate that LoVR is a challenging benchmark, revealing the limitations of current approaches and providing valuable insights for future research. We release the code and dataset link at https://github.com/TechNomad-ds/LoVR-benchmark
3D Gaussian Splatting (3DGS) has gained significant attention in streamable dynamic novel view synthesis (DNVS) for its photorealistic rendering capability and computational efficiency. Despite much progress in improving rendering quality and optimization strategies, 3DGS-based streamable dynamic scene reconstruction still suffers from flickering artifacts and storage inefficiency, and struggles to model the emerging objects. To tackle this, we introduce MGStream which employs the motion-related 3D Gaussians (3DGs) to reconstruct the dynamic and the vanilla 3DGs for the static. The motion-related 3DGs are implemented according to the motion mask and the clustering-based convex hull algorithm. The rigid deformation is applied to the motion-related 3DGs for modeling the dynamic, and the attention-based optimization on the motion-related 3DGs enables the reconstruction of the emerging objects. As the deformation and optimization are only conducted on the motion-related 3DGs, MGStream avoids flickering artifacts and improves the storage efficiency. Extensive experiments on real-world datasets N3DV and MeetRoom demonstrate that MGStream surpasses existing streaming 3DGS-based approaches in terms of rendering quality, training/storage efficiency and temporal consistency. Our code is available at: https://github.com/pcl3dv/MGStream.
Sign Language Recognition (SLR) systems primarily focus on manual gestures, but non-manual features such as mouth movements, specifically mouthing, provide valuable linguistic information. This work directly classifies mouthing instances to their corresponding words in the spoken language while exploring the potential of transfer learning from Visual Speech Recognition (VSR) to mouthing recognition in German Sign Language. We leverage three VSR datasets: one in English, one in German with unrelated words and one in German containing the same target words as the mouthing dataset, to investigate the impact of task similarity in this setting. Our results demonstrate that multi-task learning improves both mouthing recognition and VSR accuracy as well as model robustness, suggesting that mouthing recognition should be treated as a distinct but related task to VSR. This research contributes to the field of SLR by proposing knowledge transfer from VSR to SLR datasets with limited mouthing annotations.
Quantifying similarity between population spike patterns is essential for understanding how neural dynamics encode information. Traditional approaches, which combine kernel smoothing, PCA, and CCA, have limitations: smoothing kernel bandwidths are often empirically chosen, CCA maximizes alignment between patterns without considering the variance explained within patterns, and baseline correlations from stochastic spiking are rarely corrected. We introduce ReBaCCA-ss (Relevance-Balanced Continuum Correlation Analysis with smoothing and surrogating), a novel framework that addresses these challenges through three innovations: (1) balancing alignment and variance explanation via continuum canonical correlation; (2) correcting for noise using surrogate spike trains; and (3) selecting the optimal kernel bandwidth by maximizing the difference between true and surrogate correlations. ReBaCCA-ss is validated on both simulated data and hippocampal recordings from rats performing a Delayed Nonmatch-to-Sample task. It reliably identifies spatio-temporal similarities between spike patterns. Combined with Multidimensional Scaling, ReBaCCA-ss reveals structured neural representations across trials, events, sessions, and animals, offering a powerful tool for neural population analysis.
The problem of data non-stationarity is commonly addressed in data stream processing. In a dynamic environment, methods should continuously be ready to analyze time-varying data -- hence, they should enable incremental training and respond to concept drifts. An equally important variability typical for non-stationary data stream environments is the emergence of new, previously unknown classes. Often, methods focus on one of these two phenomena -- detection of concept drifts or detection of novel classes -- while both difficulties can be observed in data streams. Additionally, concerning previously unknown observations, the topic of open set of classes has become particularly important in recent years, where the goal of methods is to efficiently classify within known classes and recognize objects outside the model competence. This article presents a strategy for synthetic data stream generation in which both concept drifts and the emergence of new classes representing unknown objects occur. The presented research shows how unsupervised drift detectors address the task of detecting novelty and concept drifts and demonstrates how the generated data streams can be utilized in the open set recognition task.
We introduce $\textit{Backward Conformal Prediction}$, a method that guarantees conformal coverage while providing flexible control over the size of prediction sets. Unlike standard conformal prediction, which fixes the coverage level and allows the conformal set size to vary, our approach defines a rule that constrains how prediction set sizes behave based on the observed data, and adapts the coverage level accordingly. Our method builds on two key foundations: (i) recent results by Gauthier et al. [2025] on post-hoc validity using e-values, which ensure marginal coverage of the form $\mathbb{P}(Y_{\rm test} \in \hat C_n^{\tilde{\alpha}}(X_{\rm test})) \ge 1 - \mathbb{E}[\tilde{\alpha}]$ up to a first-order Taylor approximation for any data-dependent miscoverage $\tilde{\alpha}$, and (ii) a novel leave-one-out estimator $\hat{\alpha}^{\rm LOO}$ of the marginal miscoverage $\mathbb{E}[\tilde{\alpha}]$ based on the calibration set, ensuring that the theoretical guarantees remain computable in practice. This approach is particularly useful in applications where large prediction sets are impractical such as medical diagnosis. We provide theoretical results and empirical evidence supporting the validity of our method, demonstrating that it maintains computable coverage guarantees while ensuring interpretable, well-controlled prediction set sizes.