Related papers: Personal Visual Memory from Explicit and Implicit …

LLM-based conversational AI agents struggle to maintain coherent behavior over long horizons due to limited context. While RAG-based approaches are increasingly adopted to overcome this limitation by storing interactions in external memory…

In today's data-driven era, computational systems generate vast amounts of data that drive the digital transformation of industries, where Artificial Intelligence (AI) plays a key role. Currently, the demand for eXplainable AI (XAI) has…

Visual Language Models (VLMs) are now sufficiently advanced to support a broad range of applications, including answering complex visual questions, and are increasingly expected to interact with images in varied ways. To evaluate them,…

Vision-Language Models (VLMs) are powerful tools for processing and understanding text and images. We study the processing of visual tokens in the language model component of LLaVA, a prominent VLM. Our approach focuses on analyzing the…

This paper describes PinView, a content-based image retrieval system that exploits implicit relevance feedback collected during a search session. PinView contains several novel methods to infer the intent of the user. From relevance…

Healthcare professionals need effective ways to use, understand, and validate AI-driven clinical decision support systems. Existing systems face two key limitations: complex visualizations and a lack of grounding in scientific evidence. We…

Recent successes in visual recognition can be primarily attributed to feature representation, learning algorithms, and the ever-increasing size of labeled training data. Extensive research has been devoted to the first two, but much less…

Reasoning over ultra-long documents requires synthesizing sparse evidence scattered across distant segments under strict memory constraints. While streaming agents enable scalable processing, their passive memory update strategy often fails…

Large Language Models (LLMs), benefiting from the auto-regressive modelling approach performed on massive unannotated texts corpora, demonstrates powerful perceptual and reasoning capabilities. However, as for extending auto-regressive…

Humans excel at remembering concrete experiences along spatiotemporal contexts and performing reasoning across those events, i.e., the capacity for episodic memory. In contrast, memory in language agents remains mainly semantic, and current…

While deep learning models have shown strong performance in simulating neural responses, they often fail to clearly separate stable visual encoding from condition-specific adaptation, which limits their ability to generalize across stimuli…

While mainstream vision-language models (VLMs) have advanced rapidly in understanding image level information, they still lack the ability to focus on specific areas designated by humans. Rather, they typically rely on large volumes of…

Long-term conversational memory is a core capability for LLM-based dialogue systems, yet existing benchmarks and evaluation protocols primarily focus on surface-level factual recall. In realistic interactions, appropriate responses often…

Large Multimodal Models (LMMs) have demonstrated impressive performance in short video understanding tasks but face great challenges when applied to long video understanding. In contrast, Large Language Models (LLMs) exhibit outstanding…

Visual arguments, often used in advertising or social causes, rely on images to persuade viewers to do or believe something. Understanding these arguments requires selective vision: only specific visual stimuli within an image are relevant…

Advances in deep learning have greatly widened the scope of automatic computer vision algorithms and enable users to ask questions directly about the content in images and video. This paper explores the necessary steps towards a future…

Accurate volume estimation of objects from visual data is a long-standing challenge in computer vision with significant applications in robotics, logistics, and smart health. Existing methods often rely on complex 3D reconstruction…

Multi-modal Large Langue Models (MLLMs) often process thousands of visual tokens, which consume a significant portion of the context window and impose a substantial computational burden. Prior work has empirically explored visual token…

Imitation learning from human demonstrations has achieved significant success in robotic control, yet most visuomotor policies still condition on single-step observations or short-context histories, making them struggle with non-Markovian…

Situated visualization presents data alongside their source context (physical referent). While environmental factors influence memory recall (known as Context-Dependent Memory or CDM), how physical context affects cognition in real-world…