38 accepted papers
State Space Models (SSMs) have emerged as a powerful and efficient alternative to Transformers, demonstrating linear-time complexity and exceptional sequence modeling capabilities. However, their application to vision tasks remains challenging. First, existing vision SSMs largely depend on manually …
Electroencephalography (EEG), with its broad range of applications, necessitates models that can generalize effectively across various tasks and datasets. Large EEG Models (LEMs) address this by pretraining encoder-centric architectures on large-scale unlabeled data to extract universal representati…
Electroencephalography (EEG)-based multimodal learning integrates brain signals with complementary modalities to improve mental state assessment, providing great clinical potential. The effectiveness of such paradigms largely depends on the representation learning on heterogeneous modalities. For EE…
Large-scale EEG foundation models have shown strong generalization across a range of downstream tasks, but their training remains resource-intensive due to the volume and variable quality of EEG data. In this work, we introduce EEG-DLite, a data distillation framework that enables more efficient pre
Electroencephalography (EEG) foundation models (EFMs) have achieved strong performance across a wide range of downstream EEG tasks via pretraining and fine-tuning. Through empirical analysis, we observe that (i) no single EFM consistently dominates all tasks, yet identifying the task-specific optima…
Foley art plays a pivotal role in enhancing immersive auditory experiences in film, yet manual creation of spatio-temporal aligned audio remains labor-intensive. We propose FoleyDesigner, a novel framework inspired by professional Foley workflows, integrating film clip analysis, spatio-temporal cont
Diffusion strategies have advanced visual motor control by progressively denoising high-dimensional action sequences, providing a promising method for robot manipulation. However, as task complexity increases, the success rate of existing baseline models decreases considerably. Analysis indicates th
Electroencephalography (EEG)-based brain-computer interfaces facilitate direct communication with a computer, enabling promising applications in human-computer interactions. However, their utility is currently limited because EEG decoding often suffers from poor generalization due to distribution sh…
The neural process (NP) is a probabilistic meta learning model that learns distributions over functions via a global latent variable.It enables fast adaptation in few-shot scenarios by leveraging past experience. However, the design of latent variable structures and conditioning mechanisms in NPs re
The integration of foundation models (FMs) into robotics has accelerated real-world deployment, while introducing new safety challenges arising from open-ended semantic reasoning and embodied physical action. These challenges require safety notions beyond physical constraint satisfaction. In this po…
Large Vision-Language Models (VLMs) have achieved remarkable performance across a wide range of tasks. However, their deployment in safety-critical domains poses significant challenges. Existing safety fine-tuning methods, which focus on textual or multimodal content, fall short in addressing challe…
Current foundation models for electroencephalography (EEG) rely on architectures adapted from computer vision or natural language processing, typically treating neural signals as pixel grids or token sequences. This approach overlooks that the neural activity is activated by diverse sparse coding ac…
Solving Traveling Salesman Problem (TSP) is NP-hard yet fundamental for wide real-world applications. Classical exact methods face challenges in scaling, and heuristic methods often require domain-specific parameter calibration. While learning-based approaches have shown promise, they suffer from po…
Self-correction is essential for solving complex reasoning problems in vision–language models (VLMs), yet existing reinforcement learning (RL) methods struggle to learn it. Effective self-correction behaviors emerge only rarely during RL, making learning signals sparse. To address this challenge, we…
Brain-computer interfaces (BCIs) hold great potential for motor recovery in post-stroke patients. However, the motor imagery decoding accuracy is limited by the non-stationarity of EEG signals across subjects and sessions. We propose CAT-Net: a Co-Adaptive Transfer learning network to simultaneously…
Accurately segmenting polyp regions in colonoscopy images is crucial for the diagnosis and intervention of colorectal cancer. However, the task of polyp segmentation remains challenging due to the diverse size and shape variations among polyps, their extreme similarity to the background, and frequen…
To improve the accuracy and robustness of left ventricular segmentation, This paper proposes a diffusion probabilistic model-based left ventricular segmentation network (DPM-LVSN). DPM-LVSN integrates a U-shaped encoder-decoder for feature extraction, self-attention for semantic information, and a d…
Vision Language Models (VLMs) have become essential backbones for multi-modal intelligence, yet significant safety challenges limit their real-world application. While textual inputs can often be effectively safeguarded, adversarial visual inputs can often easily bypass VLM defense mechanisms. Exist…
Navigating domain shifts in object detection is crucial for autonomous driving systems, particularly under varying weather conditions and diverse visual perspectives. Existing Cross-Domain Object Detection methods often struggle due to their reliance on broad semantic models, which can introduce bia…
3D visual perception tasks, such as 3D detection from multi-camera images, are essential components of autonomous driving and assistance systems. However, designing computationally efficient methods remains a significant challenge. In this paper, we propose a Mamba-based framework called MamBEV, whi…
For pursuing accurate skeleton-based action recognition, many existing graph-based approaches deploy the higher-order polynomials of the skeletal adjacency matrix to model the node correlations of distant neighbours. To further capture robust graphical patterns, a novel multi-scale graph convolution…
Affective brain-computer interfaces (aBCIs) play a crucial role in personalized human–computer interaction and neurofeedback modulation. To develop practical and effective aBCI paradigms and to investigate the spatial-temporal dynamics of brain activity under emotional inducement, portable electroen…
In practical sleep stage classification, a key challenge is the variability of EEG data across different subjects and environments. Differences in physiology, age, health status, and recording conditions can lead to domain shifts between data. These domain shifts often result in decreased model accu…
Reasoning Vision-Language Models (VLMs) have shown promising performance on complex multimodal tasks. However, they still face significant challenges: they are highly sensitive to reasoning errors, require large volumes of annotated data or accurate verifiers, and struggle to generalize beyond speci…
In semi-supervised medical image segmentation, two main challenges arise. First, the quality of pseudo-labels generated by segmentation networks in data-limited scenarios is often poor, reducing segmentation accuracy. Second, many methods fail to effectively utilize the temporal context in video dat…
Large language models (LLMs) offer powerful capabilities but come with significant environmental impact, particularly in carbon emissions. Existing studies benchmark carbon emissions but lack a standardized basis for comparison across different model configurations. To address this, we introduce the…
With the emergence of strong vision language capabilities, multimodal large language models (MLLMs) have demonstrated tremendous potential for real-world applications. However, the security vulnerabilities exhibited by the visual modality pose significant challenges to deploying such models in open-
Incorporating every annotator’s perspective is crucial for unbiased data modeling. Annotator fatigue and changing opinions over time can distort dataset annotations. To combat this, we propose to learn a more accurate representation of diverse opinions by utilizing multitask learning in conjunction…
Multimodal fusion is crucial in joint decision-making systems for rendering holistic judgments. Since multimodal data changes in open environments, dynamic fusion has emerged and achieved remarkable progress in numerous applications. However, most existing dynamic multimodal fusion methods lack theo…
"Traditional fluorescence staining is phototoxic to live cells, slow, and expensive; thus, the subcellular structure prediction (SSP) from transmitted light (TL) images is emerging as a label-free, faster, low-cost alternative. However, existing approaches utilize 3D networks for one-to-one voxel le…
The inherent challenge of image fusion lies in capturing the correlation of multi-source images and comprehensively integrating effective information from different sources. Most existing techniques fail to perform dynamic image fusion while notably lacking theoretical guarantees, leading to potenti…
International audience
Global Navigation Satellite System (GNSS) is the widely used technology when it comes to outdoor positioning. But it has severe limitations with regard to safety-critical applications involving unmanned autonomous systems. Namely, the positioning performance degrades in harsh propagation environment
Imperfect labels are ubiquitous in real-world datasets. Several recent successful methods for training deep neural networks (DNNs) robust to label noise have used two primary techniques: filtering samples based on loss during a warm-up phase to curate an initial set of cleanly labeled samples, and u…
We establish finite-sample guarantees for a polynomial-time algorithm for learning a nonlinear, nonparametric directed acyclic graphical (DAG) model from data. The analysis is model-free and does not assume linearity, additivity, independent noise, or faithfulness. Instead, we impose a condition on…
In this paper, we adopt results in nonlinear time series analysis for causal inference in dynamical settings. Our motivation is policy analysis with panel data, particularly through the use of “synthetic control" methods. These methods regress pre-intervention outcomes of the treated unit to outcom…
Machine learning with missing data has been approached in many different ways, including feature imputation where missing feature values are estimated based on observed values and label prediction where downstream labels are learned directly from incomplete data. However, existing imputation models…
Gaussian process regression generally does not scale to beyond a few thousands data points without applying some sort of kernel approximation method. Most approximations focus on the high eigenvalue part of the spectrum of the kernel matrix, $K$, which leads to bad performance when the length scale…