相关论文: Substantial, Decomposable, and Invisible: Visual C…

Compared to image-text pair data, interleaved corpora enable Vision-Language Models (VLMs) to understand the world more naturally like humans. However, such existing datasets are crawled from webpage, facing challenges like low knowledge…

Visual In-Context Learning (VICL) enables adaptively solving vision tasks by leveraging pixel demonstrations, mimicking human-like task completion through analogy. Prompt selection is critical in VICL, but current methods assume the…

In-context learning (ICL) has emerged as an effective approach to enhance the performance of large language models (LLMs). However, its effectiveness varies significantly across models and tasks, posing challenges for practitioners to…

There are substantial instructional videos on the Internet, which provide us tutorials for completing various tasks. Existing instructional video datasets only focus on specific steps at the video level, lacking experiential guidelines at…

Precise temporal and spatial alignment is critical in collaborative Augmented Reality (AR) where users rely on shared visual information to coordinate actions. System latency and object misalignment can disrupt communication, reduce task…

Recommender systems, while a powerful decision making tool, are often operationalized as black box models, such that their AI algorithms are not accessible or interpretable by human operators. This in turn can cause confusion and…

Vision-language models (VLMs) have achieved impressive performance across a wide range of multimodal reasoning tasks, but they often struggle to disentangle fine-grained visual attributes and reason about underlying causal relationships.…

Learning effective visual representations for robotic manipulation remains a fundamental challenge due to the complex body dynamics involved in action execution. In this paper, we study how visual representations that carry body-relevant…

Procedure learning involves identifying the key-steps and determining their logical order to perform a task. Existing approaches commonly use third-person videos for learning the procedure, making the manipulated object small in appearance…

Instruction following is a critical ability for Large Language Models to perform downstream tasks. The standard approach to instruction tuning has relied on a specific phase of supervised fine-tuning over curated instruction datasets,…

This study investigates the influence of Visual Guidance (VG) on user performance and human factors within Augmented Reality (AR) via a between-subjects experiment. VG is a crucial component in AR applications, serving as a bridge between…

The task of associating images and videos with a natural language description has attracted a great amount of attention recently. Rapid progress has been made in terms of both developing novel algorithms and releasing new datasets. Indeed,…

The attention mechanism has become a cornerstone of modern deep learning architectures, where keys and values are typically derived from the same underlying sequence or representation. This work explores a less conventional scenario, when…

The task of describing video content in natural language is commonly referred to as video captioning. Unlike conventional video captions, which are typically brief and widely available, long-form paragraph descriptions in natural language…

In-context learning provides a new perspective for multi-task modeling for vision and NLP. Under this setting, the model can perceive tasks from prompts and accomplish them without any extra task-specific head predictions or model…

In-context learning (ICL) enables large language models to perform few-shot learning by conditioning on labeled examples in the prompt. Despite its flexibility, ICL suffers from instability -- especially as prompt length increases with more…

Our understanding of how visual systems detect, analyze and interpret visual stimuli has advanced greatly. However, the visual systems of all animals do much more; they enable visual behaviours. How well the visual system performs while…

Recent studies have shown that Large Vision-Language Models (VLMs) tend to neglect image content and over-rely on language-model priors, resulting in errors in visually grounded tasks and hallucinations. We hypothesize that this issue…

Timelines are commonly represented on a horizontal line, which is not necessarily the most effective way to visualize temporal event sequences. However, few experiments have evaluated how timeline shape influences task performance. We…

Causality knowledge is vital to building robust AI systems. Deep learning models often perform poorly on tasks that require causal reasoning, which is often derived using some form of commonsense knowledge not immediately available in the…