相关论文: LIHE: Linguistic Instance-Split Hyperbolic-Euclide…

The "thinking-with-images" paradigm enables multimodal large language models (MLLMs) to actively explore visual scenes via zoom-in tools. This is essential for ultra-high-resolution (UHR) remote sensing VQA, where task-relevant cues are…

Visual hallucinations in Large Language Models (LLMs), where the model generates responses that are inconsistent with the visual input, pose a significant challenge to their reliability, particularly in contexts where precise and…

To mitigate the threat of misinformation, multimodal manipulation localization has garnered growing attention. Consider that current methods rely on costly and time-consuming fine-grained annotations, such as patch/token-level annotations.…

Autoregressive decoding with generative Large Language Models (LLMs) on accelerators (GPUs/TPUs) is often memory-bound where most of the time is spent on transferring model parameters from high bandwidth memory (HBM) to cache. On the other…

While numerous Video Violence Detection (VVD) methods have focused on representation learning in Euclidean space, they struggle to learn sufficiently discriminative features, leading to weaknesses in recognizing normal events that are…

Modeling episodic memory (EM) remains a significant challenge in both neuroscience and AI, with existing models either lacking interpretability or struggling with practical applications. This paper proposes the Vision-Language Episodic…

Wireless goal-oriented semantic communication (GSC) has emerged as a promising paradigm by directly optimizing task performance. However, existing GSC frameworks typically operate on entire images and rely on labeled data for classification…

Recent advances in unified multimodal models (UMMs) have enabled impressive progress in visual comprehension and generation. However, existing datasets and benchmarks focus primarily on single-turn interactions, failing to capture the…

Hyperbolic neural networks have emerged as a powerful tool for modeling hierarchical data across diverse modalities. Recent studies show that token distributions in foundation models exhibit scale-free properties, suggesting that hyperbolic…

Frame-level micro- and macro-expression spotting methods require time-consuming frame-by-frame observation during annotation. Meanwhile, video-level spotting lacks sufficient information about the location and number of expressions during…

Despite weakly supervised object detection (WSOD) being a promising step toward evading strong instance-level annotations, its capability is confined to closed-set categories within a single training dataset. In this paper, we propose a…

Visual grounding localizes regions (boxes or segments) in the image corresponding to given referring expressions. In this work we address image segmentation from referring expressions, a problem that has so far only been addressed in a…

Referring expression segmentation aims to segment an object described by a language expression from an image. Despite the recent progress on this task, existing models tackling this task may not be able to fully capture semantics and visual…

Given a natural language expression and an image/video, the goal of referring segmentation is to produce the pixel-level masks of the entities described by the subject of the expression. Previous approaches tackle this problem by implicit…

Existing multimodal search agents process target entities sequentially, issuing one tool call per entity and accumulating redundant interaction rounds whenever a query decomposes into independent sub-retrievals. We argue that effective…

From social networks to protein complexes to disease genomes to visual data, hypergraphs are everywhere. However, the scope of research studying deep learning on hypergraphs is still quite sparse and nascent, as there has not yet existed an…

Multimodal retrieval models fail on reasoning-intensive queries where images (diagrams, charts, screenshots) must be deeply integrated with text to identify relevant documents -- the best multimodal model achieves only 27.6 nDCG@10 on…

As an important step towards visual reasoning, visual grounding (e.g., phrase localization, referring expression comprehension/segmentation) has been widely explored Previous approaches to referring expression comprehension (REC) or…

Histology imaging is an important tool in medical diagnosis and research, enabling the examination of tissue structure and composition at the microscopic level. Understanding the underlying molecular mechanisms of tissue architecture is…

Supervision for metric learning has long been given in the form of equivalence between human-labeled classes. Although this type of supervision has been a basis of metric learning for decades, we argue that it hinders further advances in…