Related papers: The Telephone Game: Evaluating Semantic Drift in U…

This paper proposes an introspective deep metric learning (IDML) framework for uncertainty-aware comparisons of images. Conventional deep metric learning methods produce confident semantic distances between images regardless of the…

Evaluating whether vision-language models (VLMs) reason consistently across representations is challenging because modality comparisons are typically confounded by task differences and asymmetric information. We introduce SEAM, a benchmark…

Existing end-to-end autonomous driving models rely heavily on purely data-driven inductive reasoning. This "black-box" nature leads to a lack of interpretability and absolute safety guarantees in complex, long-tail scenarios. To overcome…

Recent advancements in multimodal techniques open exciting possibilities for models excelling in diverse tasks involving text, audio, and image processing. Models like GPT-4V, blending computer vision and language modeling, excel in complex…

A number of high-level languages and libraries have been proposed that offer novel and simple to use abstractions for concurrent, asynchronous, and distributed programming. The execution models that realise them, however, often change over…

3D object detection task from lidar or camera sensors is essential for autonomous driving. Pioneer attempts at multi-modality fusion complement the sparse lidar point clouds with rich semantic texture information from images at the cost of…

Next-generation automotive applications require vehicular edge computing (VEC), but current management systems are essentially fixed and reactive. They are suboptimal in extremely dynamic vehicular environments because they are constrained…

Text-to-image (T2I) models are capable of generating visually impressive images, yet they often fail to accurately capture specific attributes in user prompts, such as the correct number of objects with the specified colors. The diversity…

We propose Unified-IO, a model that performs a large variety of AI tasks spanning classical computer vision tasks, including pose estimation, object detection, depth estimation and image generation, vision-and-language tasks such as region…

The integration of machine learning tools into telecom networks, has led to two prevailing paradigms, namely, language-based systems, such as Large Language Models (LLMs), and physics-based systems, such as Digital Twins (DTs). While…

Recent advances in unified multimodal models (UMM) have demonstrated remarkable progress in both understanding and generation tasks. However, whether these two capabilities are genuinely aligned and integrated within a single model remains…

A common practice in metric learning is to train and test an embedding model for each dataset. This dataset-specific approach fails to simulate real-world scenarios that involve multiple heterogeneous distributions of data. In this regard,…

Prompt tuning, a parameter- and data-efficient transfer learning paradigm that tunes only a small number of parameters in a model's input space, has become a trend in the vision community since the emergence of large vision-language models…

Progress in Text-to-Image (T2I) models has significantly improved the generation of images from textual descriptions. However, existing evaluation metrics do not adequately assess the models' ability to handle a diverse range of textual…

Existing 3D human motion generation and understanding methods often exhibit limited interpretability, restricting effective mutual enhancement between these inherently related tasks. While current unified frameworks based on large language…

In Model-Driven Engineering (MDE), the Unified Modeling Language (UML) 2.0 specification includes a metamodel that defines the language concepts and a user model that defines how the language concepts are represented. In UML 2.0, an…

Ultra-low bitrate image compression is a challenging and demanding topic. With the development of Large Multimodal Models (LMMs), a Cross Modality Compression (CMC) paradigm of Image-Text-Image has emerged. Compared with traditional codecs,…

Vision-language models (VLMs) unify computer vision and natural language processing in a single architecture capable of interpreting and describing images. Most state-of-the-art systems rely on two computationally intensive components:…

State-of-the-art text-to-image models produce high-quality images, but inference remains expensive as generation requires several sequential ODE or denoising steps. Native one-step models aim to reduce this cost by mapping noise to an image…

As modern networks grow increasingly complex--driven by diverse devices, encrypted protocols, and evolving threats--network traffic analysis has become critically important. Existing machine learning models often rely only on a single…