相关论文: Mixed Multi-Model Semantic Interaction for Graph-b…

Interactive spatial layouts empower users to synthesize information and organize findings for sensemaking. While Large Language Models (LLMs) can automate narrative generation from spatial layouts, current collage-based and re-generation…

Narratives are key interpretative devices by which humans make sense of political reality. As the significance of narratives for understanding current societal issues such as polarization and misinformation becomes increasingly evident,…

This vision paper lays the preliminary foundations for Data Narrative Management Systems (DNMS), systems that enable the storage, sharing, and manipulation of data narratives. We motivate the need for such formal foundations and introduce a…

This paper represents a neat yet effective framework, named SemanticMIM, to integrate the advantages of masked image modeling (MIM) and contrastive learning (CL) for general visual representation. We conduct a thorough comparative analysis…

While Large Language Models (LLMs) excel at generalized reasoning, standard retrieval-augmented approaches fail to address the disconnected nature of long-term agentic memory. To bridge this gap, we introduce Synapse (Synergistic…

Multimodal large language models (MLLMs) have achieved impressive progress in vision-language reasoning, yet their ability to understand temporally unfolding narratives in videos remains underexplored. True narrative understanding requires…

A 3D scene graph represents a compact scene model by capturing both the objects present and the semantic relationships between them, making it a promising structure for robotic applications. To effectively interact with users, an embodied…

Large language models (LLMs) are often portrayed as merely imitating linguistic patterns without genuine understanding. We argue that recent findings in mechanistic interpretability (MI), the emerging field probing the inner workings of…

Understanding how ML models work is a prerequisite for responsibly designing, deploying, and using ML-based systems. With interpretability approaches, ML can now offer explanations for its outputs to aid human understanding. Though these…

Visual reasoning, particularly spatial reasoning, is a challenging cognitive task that requires understanding object relationships and their interactions within complex environments, especially in robotics domain. Existing vision_language…

We offer a new model of the sensemaking process for data analysis and visualization. Whereas past sensemaking models have been grounded in positivist assumptions about the nature of knowledge, we reframe data sensemaking in critical,…

While 2D occupancy maps commonly used in mobile robotics enable safe navigation in indoor environments, in order for robots to understand and interact with their environment and its inhabitants representing 3D geometry and semantic…

Neural implicit representations are drawing a lot of attention from the robotics community recently, as they are expressive, continuous and compact. However, city-scale continual implicit dense mapping based on sparse LiDAR input is still…

We propose neural-symbolic integration for abstract concept explanation and interactive learning. Neural-symbolic integration and explanation allow users and domain-experts to learn about the data-driven decision making process of large…

Semantic mapping is the incremental process of "mapping" relevant information of the world (i.e., spatial information, temporal events, agents and actions) to a formal description supported by a reasoning engine. Current research focuses on…

Deep learning has advanced NLP, but interpretability remains limited, especially in healthcare and finance. Concept bottleneck models tie predictions to human concepts in vision, but NLP versions either use binary activations that harm text…

In our understanding, a mind-map is an adaptive engine that basically works incrementally on the fundament of existing transactional streams. Generally, mind-maps consist of symbolic cells that are connected with each other and that become…

Naturally controllable human-scene interaction (HSI) generation has an important role in various fields, such as VR/AR content creation and human-centered AI. However, existing methods are unnatural and unintuitive in their controllability,…

Frame semantic parsing is a semantic analysis task based on FrameNet which has received great attention recently. The task usually involves three subtasks sequentially: (1) target identification, (2) frame classification and (3) semantic…

Semi-supervised medical image segmentation is an effective method for addressing scenarios with limited labeled data. Existing methods mainly rely on frameworks such as mean teacher and dual-stream consistency learning. These approaches…