相关论文: Vision-Language Foundation Models for Comprehensiv…

Multimodal Large Language Models (MLLMs) have demonstrated strong generalization in vision-language tasks, yet their ability to understand and act within embodied environments remains underexplored. We present NavBench, a benchmark to…

Navigation guided by natural language instructions presents a challenging reasoning problem for instruction followers. Natural language instructions typically identify only a few high-level decisions and landmarks rather than complete…

Vision-language models have recently shown great potential on many tasks in computer vision. Meanwhile, prior work demonstrates prompt tuning designed for vision-language models could acquire superior performance on few-shot image…

Cooperative autonomous driving requires traffic scene understanding from both vehicle and infrastructure perspectives. While vision-language models (VLMs) show strong general reasoning capabilities, their performance in safety-critical…

Automated perception of urban roadside infrastructure is crucial for smart city management, yet general-purpose models often struggle to capture the necessary fine-grained attributes and domain rules. While Large Vision Language Models…

Large Vision-Language Models (LVLMs) offer remarkable benefits for a variety of vision-language tasks. However, a challenge hindering their application in real-world scenarios, particularly regarding safety, robustness, and reliability, is…

Multi-model learning has attracted great attention in visual-text tasks. However, visual-tabular data, which plays a pivotal role in high-stakes domains like healthcare and industry, remains underexplored. In this paper, we introduce…

Significant research efforts have been made to scale and improve vision-language model (VLM) training approaches. Yet, with an ever-growing number of benchmarks, researchers are tasked with the heavy burden of implementing each protocol,…

Visual transfer learning for unseen categories presents an active research topic yet a challenging task, due to the inherent conflict between preserving category-specific representations and acquiring transferable knowledge. Vision-Language…

Spatio-Temporal Video Grounding (STVG) aims to localize target objects in videos based on natural language descriptions. Despite recent advances in Multimodal Large Language Models, a significant gap remains between current models and…

Geo-temporal understanding, the ability to infer location, time, and contextual properties from visual input alone, underpins applications such as disaster management, traffic planning, embodied navigation, world modeling, and geography…

It is critical for vision-language models (VLMs) to comprehensively understand visual, temporal, and textual cues. However, despite rapid progress in multimodal modeling, video understanding performance still lags behind text-based…

Foundation models that incorporate language, vision, and more recently actions have revolutionized the ability to harness internet scale data to reason about useful tasks. However, one of the key challenges of training embodied foundation…

Most existing approaches formulate action quality assessment and skill proficiency estimation as discriminative prediction tasks, typically producing discrete labels or scores without explicitly modeling the reasoning process underlying the…

Visual grounding refers to the ability of a model to identify a region within some visual input that matches a textual description. Consequently, a model equipped with visual grounding capabilities can target a wide range of applications in…

Instruction-tuned large language models have revolutionized natural language processing and have shown great potential in applications such as conversational agents. These models, such as GPT-4, can not only master language but also solve…

Traditional biomedical artificial intelligence (AI) models, designed for specific tasks or modalities, often exhibit limited flexibility in real-world deployment and struggle to utilize holistic information. Generalist AI holds the…

Multilingual language models often perform unevenly across different languages due to limited generalization capabilities for some languages. This issue is significant because of the growing interest in making universal language models that…

Remote sensing (RS) large vision-language models (LVLMs) have shown strong promise across visual grounding (VG) tasks. However, existing RS VG datasets predominantly rely on explicit referring expressions-such as relative position, relative…

Vision-Language-Action (VLA) models have recently shown strong decision-making capabilities in autonomous driving. However, existing VLAs often struggle with achieving efficient inference and generalizing to novel autonomous vehicle…