相关论文: AVM: Towards Structure-Preserving Neural Response …

Learning continually from a stream of non-i.i.d. data is an open challenge in deep learning, even more so when working in resource-constrained environments such as embedded devices. Visual models that are continually updated through…

Recent advancements in multimodal fusion have witnessed the remarkable success of vision-language (VL) models, which excel in various multimodal applications such as image captioning and visual question answering. However, building VL…

Elucidating the functional mechanisms of the primary visual cortex (V1) remains a fundamental challenge in systems neuroscience. Current computational models face two critical limitations, namely the challenge of cross-modal integration…

Vision-Language Models (VLMs) have demonstrated strong performance on multimodal reasoning tasks, but their deployment remains challenging due to high inference latency and computational cost, particularly when processing high-resolution…

Story continuation focuses on generating the next image in a narrative sequence so that it remains coherent with both the ongoing text description and the previously observed images. A central challenge in this setting lies in utilizing…

Visual reasoning models (VRMs) have recently shown strong cross-modal reasoning capabilities by integrating visual perception with language reasoning. However, they often suffer from overthinking, producing unnecessarily long reasoning…

Accurate predictive models of the visual cortex neural response to natural visual stimuli remain a challenge in computational neuroscience. In this work, we introduce V1T, a novel Vision Transformer based architecture that learns a shared…

The Large Vision-Language Model (LVLM) integrates computer vision and natural language processing techniques, offering substantial application potential. However, these models demand extensive resources during inference. Adaptive attention…

We present Recurrent Video Masked-Autoencoders (RVM): a novel approach to video representation learning that leverages recurrent computation to model the temporal structure of video data. RVM couples an asymmetric masking objective with a…

Investigating the mapping between visual stimuli and neural responses in the visual cortex contributes to a deeper understanding of biological visual processing mechanisms. Most existing studies characterize this mapping by training models…

Encoding models that predict brain response patterns to stimuli are one way to capture this relationship between variability in bottom-up neural systems and individual's behavior or pathological state. However, they generally need a large…

The advancement of Multimodal Large Language Models (MLLMs) has driven significant progress in Visual Question Answering (VQA), evolving from Single to Multi Image VQA (MVQA). However, the increased number of images in MVQA inevitably…

While autoregressive Large Vision-Language Models (LVLMs) demonstrate remarkable proficiency in multimodal tasks, they face a "Visual Signal Dilution" phenomenon, where the accumulation of textual history expands the attention partition…

Findings in recent years on the sensitivity of convolutional neural networks to additive noise, light conditions and to the wholeness of the training dataset, indicate that this technology still lacks the robustness needed for the…

Recently, there has been a surge in the popularity of pre trained large language models (LLMs) (such as GPT-4), sweeping across the entire Natural Language Processing (NLP) and Computer Vision (CV) communities. These LLMs have demonstrated…

The support vector machines (SVM) is one of the most widely used and practical optimization based classification models in machine learning because of its interpretability and flexibility to produce high quality results. However, the big…

Different from Visual Question Answering task that requires to answer only one question about an image, Visual Dialogue involves multiple questions which cover a broad range of visual content that could be related to any objects,…

Pretrain techniques, whether supervised or self-supervised, are widely used in deep learning to enhance model performance. In real-world clinical scenarios, different sets of magnetic resonance (MR) contrasts are often acquired for…

Despite the success of Large Vision--Language Models (LVLMs), most existing architectures suffer from a representation bottleneck: they rely on static, instruction-agnostic vision encoders whose visual representations are utilized in an…

Large language models (LLMs) have demonstrated that large-scale pretraining enables systems to adapt rapidly to new problems with little supervision in the language domain. This success, however, has not translated as effectively to the…