Related papers: Tiny but Trusted: Efficient Vision-Language Reason…

Time series anomaly detection (TSAD) is of widespread interest across many industries, including finance, healthcare, and manufacturing. Despite the development of numerous automatic methods for detecting anomalies, human oversight remains…

Ensuring robust performance on long-tail examples is an important problem for many real-world applications of machine learning, such as autonomous driving. This work focuses on the problem of identifying rare examples within a corpus of…

Existing vision-language models (VLMs) have demonstrated impressive performance in reasoning-based segmentation. However, current benchmarks are primarily constructed from high-quality images captured under idealized conditions. This raises…

Recent advances in vision-language models (VLMs) have achieved remarkable performance on standard medical benchmarks, yet their true clinical reasoning ability remains unclear. Existing datasets predominantly emphasize classification…

Vision-language models (VLMs) perform strongly on many multimodal benchmarks. However, the ability to follow complex visual paths -- a task that human observers typically find straightforward -- remains under-tested. We introduce…

Pre-trained vision-language models (VLMs) are highly adaptable to various downstream tasks through few-shot learning, making prompt-based anomaly detection a promising approach. Traditional methods depend on human-crafted prompts that…

Process-supervised reward models serve as a fine-grained function that provides detailed step-wise feedback to model responses, facilitating effective selection of reasoning trajectories for complex tasks. Despite its advantages, evaluation…

Despite significant advancements in vision-language models (VLMs), there lacks effective approaches to enhance response quality by scaling inference-time computation. This capability is known to be a core step towards the self-improving…

Vision-Language Models (VLMs) have achieved remarkable progress in complex visual understanding across scientific and reasoning tasks. While performance benchmarking has advanced our understanding of these capabilities, the critical…

Vision language models (VLMs) are designed to extract relevant visuospatial information from images. Some research suggests that VLMs can exhibit humanlike scene understanding, while other investigations reveal difficulties in their ability…

Reliable prediction by classifiers is crucial for their deployment in high security and dynamically changing situations. However, modern neural networks often exhibit overconfidence for misclassified predictions, highlighting the need for…

Although large visual-language models (LVLMs) have demonstrated strong performance in multimodal tasks, errors may occasionally arise due to biases during the reasoning process. Recently, reward models (RMs) have become increasingly pivotal…

Text anomaly detection is a critical task in natural language processing (NLP), with applications spanning fraud detection, misinformation identification, spam detection and content moderation, etc. Despite significant advances in large…

The rise of vision foundation models (VFMs) calls for systematic evaluation. A common approach pairs VFMs with large language models (LLMs) as general-purpose heads, followed by evaluation on broad Visual Question Answering (VQA)…

Comparing vision language models on videos is particularly complex, as the performances is jointly determined by the model's visual representation capacity and the frame-sampling strategy used to construct the input. Current video…

Vision-language models (VLMs) achieve remarkable success in single-image tasks. However, real-world scenarios often involve intricate multi-image inputs, leading to a notable performance decline as models struggle to disentangle critical…

Human language is grounded on multimodal knowledge including visual knowledge like colors, sizes, and shapes. However, current large-scale pre-trained language models rely on text-only self-supervised training with massive text data, which…

Detecting anomalies in time series data is crucial for finance, healthcare, sensor networks, and industrial monitoring applications. However, time series anomaly detection often suffers from sparse labels, complex temporal patterns, and…

Latent Action Models (LAMs) have rapidly gained traction as an important component in the pre-training pipelines of leading Vision-Language-Action models. However, they fail when observations contain action-correlated distractors, often…

Vision-Language Model (VLM) have gained widespread adoption in Open-Vocabulary (OV) object detection and segmentation tasks. Despite they have shown promise on OV-related tasks, their effectiveness in conventional vision tasks has thus far…