相关论文: Reprogramming Vision Foundation Models for Spatio-…

Foundation models (FMs) have transformed natural language processing, but their success has not yet translated to time series forecasting. Existing time series foundation models (TSFMs), often based on transformer variants, struggle with…

Current video understanding models excel at recognizing "what" is happening but fall short in high-level cognitive tasks like causal reasoning and future prediction, a limitation rooted in their lack of commonsense world knowledge. To…

The sea surface temperature (SST), a key environmental parameter, is crucial to optimizing production planning, making its accurate prediction a vital research topic. However, the inherent nonlinearity of the marine dynamic system presents…

While Large Language Models (LLMs) dominate tasks like natural language processing and computer vision, harnessing their power for spatial-temporal forecasting remains challenging. The disparity between sequential text and complex…

Vision-language models (VLMs) have emerged as powerful tools for enabling automated traffic analysis; however, current approaches often demand substantial computational resources and struggle with fine-grained spatio-temporal understanding.…

Recent advancements in time series forecasting have explored augmenting models with text or vision modalities to improve accuracy. While text provides contextual understanding, it often lacks fine-grained temporal details. Conversely,…

Foundation models leverage large-scale pretraining to capture extensive knowledge, demonstrating generalization in a wide range of language tasks. By comparison, vision foundation models (VFMs) often exhibit uneven improvements across…

Following its success for vision and text, the "foundation model" (FM) paradigm -- pretraining large models on massive data, then fine-tuning on target tasks -- has rapidly expanded to domains in the sciences, engineering, healthcare, and…

Vision foundation models exhibit impressive power, benefiting from the extremely large model capacity and broad training data. However, in practice, downstream scenarios may only support a small model due to the limited computational…

Time Series Forecasting (TSF) is critical in many real-world domains like financial planning and health monitoring. Recent studies have revealed that Large Language Models (LLMs), with their powerful in-contextual modeling capabilities,…

The rapid development of Vision Foundation Models (VFMs), particularly Vision Transformers (ViT) and Segment Anything Model (SAM), has sparked significant advances in the field of medical image analysis. These models have demonstrated…

Time series forecasting is a long-standing and highly challenging research topic. Recently, driven by the rise of large language models (LLMs), research has increasingly shifted from purely time series methods toward harnessing textual…

Spatio-temporal deep learning models aims to utilize useful patterns in such data to support tasks like prediction. However, previous deep learning models designed for specific tasks typically require separate training for each use case,…

Vision foundation models (VFMs) have demonstrated remarkable performance across a wide range of downstream tasks. While several VFM adapters have shown promising results by leveraging the prior knowledge of VFMs, we identify two…

Vision language models (VLMs) have shown remarkable capabilities in integrating linguistic and visual reasoning but remain fundamentally limited in understanding dynamic spatiotemporal interactions. Humans effortlessly track and reason…

Executing multiple tasks simultaneously in medical image analysis, including segmentation, classification, detection, and regression, often introduces significant challenges regarding model generalizability and the optimization of shared…

Within the field of complicated multivariate time series forecasting (TSF), popular techniques frequently rely on intricate deep learning architectures, ranging from transformer-based designs to recurrent neural networks. However, recent…

Capturing spatial relationships from visual inputs is a cornerstone of human-like general intelligence. Several previous studies have tried to enhance the spatial awareness of Vision-Language Models (VLMs) by adding extra expert encoders,…

Language-aligned vision foundation models (VFMs) enable versatile visual understanding for always-on contextual AI, but their deployment on edge devices is hindered by strict latency and power constraints. We present AdaVFM, an adaptive…

The interpretation of multi-temporal remote sensing imagery is critical for monitoring Earth's dynamic processes-yet previous change detection methods, which produce binary or semantic masks, fall short of providing human-readable insights…