Related papers: ViLPAct: A Benchmark for Compositional Generalizat…
Imitation learning (IL), particularly when leveraging high-dimensional visual inputs for policy training, has proven intuitive and effective in complex bimanual manipulation tasks. Nonetheless, the generalization capability of visuomotor…
Visual imitation learning (VIL) provides an efficient and intuitive strategy for robotic systems to acquire novel skills. Recent advancements in Vision Language Models (VLMs) have demonstrated remarkable performance in vision and language…
As an important task in sentiment analysis, Multimodal Aspect-Based Sentiment Analysis (MABSA) has attracted increasing attention in recent years. However, previous approaches either (i) use separately pre-trained visual and textual models,…
We aim to automatically identify human action reasons in online videos. We focus on the widespread genre of lifestyle vlogs, in which people perform actions while verbally describing them. We introduce and make publicly available the WhyAct…
Vision-Language Navigation (VLN) is a challenging task that requires an embodied agent to perform action-level modality alignment, i.e., make instruction-asked actions sequentially in complex visual environments. Most existing VLN agents…
Recent advancements in Large Video-Language Models (LVLMs) have led to promising results in multimodal video understanding. However, it remains unclear whether these models possess the cognitive capabilities required for high-level tasks,…
Vision-Language-Action (VLA) models have recently shown strong potential for robot learning by following language instructions. However, in practice, language alone is often insufficient to precisely convey human intent. It is difficult to…
In this paper, we leverage the human perceiving process, that involves vision and language interaction, to generate a coherent paragraph description of untrimmed videos. We propose vision-language (VL) features consisting of two modalities,…
Prompt Tuning, conditioning on task-specific learned prompt vectors, has emerged as a data-efficient and parameter-efficient method for adapting large pretrained vision-language models to multiple downstream tasks. However, existing…
Vision-Language-Action (VLA) models mark a transformative advancement in artificial intelligence, aiming to unify perception, natural language understanding, and embodied action within a single computational framework. This foundational…
Developing robust and general-purpose manipulation policies represents a fundamental objective in robotics research. While Vision-Language-Action (VLA) models have demonstrated promising capabilities for end-to-end robot control, existing…
Structured images (e.g., charts and geometric diagrams) remain challenging for multimodal large language models (MLLMs), as perceptual slips can cascade into erroneous conclusions. Intermediate visual cues can steer reasoning; however,…
Humans possess the innate ability to extract latent visuo-lingual cues to infer context through human interaction. During collaboration, this enables proactive prediction of the underlying intention of a series of tasks. In contrast,…
Understanding images and text together is an important aspect of cognition and building advanced Artificial Intelligence (AI) systems. As a community, we have achieved good benchmarks over language and vision domains separately, however…
Visual Language Models (VLMs) have emerged as pivotal tools for robotic systems, enabling cross-task generalization, dynamic environmental interaction, and long-horizon planning through multimodal perception and semantic reasoning. However,…
Long-term action anticipation (LTA) aims to predict future actions over an extended period. Previous approaches primarily focus on learning exclusively from video data but lack prior knowledge. Recent researches leverage large language…
Passive tracking methods, such as phone and wearable sensing, have become dominant in monitoring human behaviors in modern ubiquitous computing studies. While there have been significant advances in machine-learning approaches to translate…
Understanding multi-image, multi-turn scenarios is a critical yet underexplored capability for Large Vision-Language Models (LVLMs). Existing benchmarks predominantly focus on static or horizontal comparisons -- e.g., spotting visual…
Action anticipation, the task of predicting future actions from partially observed videos, is crucial for advancing intelligent systems. Unlike action recognition, which operates on fully observed videos, action anticipation must handle…
Approximately 200 million individuals around the world suffer from varying degrees of visual impairment, making it crucial to leverage AI technology to offer walking assistance for these people. With the recent progress of vision-language…