Related papers: GeoFlowVLM: Geometry-Aware Joint Uncertainty for F…

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,…

The adaptation of large-scale vision-language models (VLMs) to downstream tasks with limited labeled data remains a significant challenge. While parameter-efficient prompt learning methods offer a promising path, they often suffer from…

Learning permutations is fundamental to sorting, ranking, and matching, but existing differentiable methods based on entropy-regularized Sinkhorn produce a single softened solution and collapse under ambiguity. We present PermFlow, a…

Compared to conventional zero-shot learning (ZSL) where recognising unseen classes is the primary or only aim, the goal of generalized zero-shot learning (GZSL) is to recognise both seen and unseen classes. Most GZSL methods typically learn…

Vision-language pre-training (VLP) on large-scale image-text pairs has achieved huge success for the cross-modal downstream tasks. The most existing pre-training methods mainly adopt a two-step training procedure, which firstly employs a…

Topology is critical in tubular structures such as blood vessels, nerve fibers, and road networks, where connectivity and loop structure govern downstream functional analysis. Vision-Language Models (VLMs) are promising candidates for…

In recent times, the standard practice for developing MLLMs is to feed features from vision encoder(s) into the LLM and train with natural language supervision. This approach often causes models to lean towards language comprehension and…

Vision-language models (VLMs) can describe urban scenes in rich detail, yet consistently fail to produce reliable human preference labels in domain-specific tasks such as safety assessment and aesthetic evaluation. The standard fix,…

Vision-language models (VLMs) align images and text with remarkable success, yet the geometry of their shared embedding space remains poorly understood. To probe this geometry, we begin from the Iso-Energy Assumption, which exploits…

The robustness of Vision Language Models (VLMs) is commonly assessed through output-level invariance, implicitly assuming that stable predictions reflect stable multimodal processing. In this work, we argue that this assumption is…

Most existing vision-language pre-training (VLP) approaches adopt cross-modal masked language modeling (CMLM) to learn vision-language associations. However, we find that CMLM is insufficient for this purpose according to our observations:…

Integrating Pre-trained Language Models (PLMs) with Graph Neural Networks (GNNs) remains a central challenge in text-rich heterophilic graph learning. We propose a novel integration framework that enables effective fusion between powerful…

Multimodal large language models (MLLMs) have achieved significant progress in image and language tasks due to the strong reasoning capability of large language models (LLMs). Nevertheless, most MLLMs suffer from limited spatial reasoning…

Information retrieval is indispensable for today's Internet applications, yet traditional semantic matching techniques often fall short in capturing the fine-grained cross-modal interactions required for complex queries. Although…

Large Vision-Language Models (LVLMs) have shown impressive capabilities across a range of tasks that integrate visual and textual understanding, such as image captioning and visual question answering. These models are trained on large-scale…

Video anomaly detection is a challenging task because most anomalies are scarce and non-deterministic. Many approaches investigate the reconstruction difference between normal and abnormal patterns, but neglect that anomalies do not…

The success of VLMs often relies on the dynamic high-resolution schema that adaptively augments the input images to multiple crops, so that the details of the images can be retained. However, such approaches result in a large number of…

Multi-Task Learning (MTL) seeks to boost statistical power and learning efficiency by discovering structure shared across related tasks. State-of-the-art MTL representation methods, however, usually treat the latent representation matrix as…

We present hidden fluid mechanics (HFM), a physics informed deep learning framework capable of encoding an important class of physical laws governing fluid motions, namely the Navier-Stokes equations. In particular, we seek to leverage the…

When VLMs answer correctly, do they genuinely rely on visual information? We introduce a Tri-Layer Diagnostic Framework with three per-sample metrics: Latent Anomaly Detection, Visual Necessity Score, and Competition Score, which…