Related papers: Agentic metasurface design with self-correcting la…
While diffusion models excel at generating high-quality images, they often struggle with accurate counting, attributes, and spatial relationships in complex multi-object scenes. One potential solution involves employing Multimodal Large…
Self-improving AI systems aim to reduce reliance on human engineering by learning to improve their own learning and problem-solving processes. Existing approaches to self-improvement rely on fixed, handcrafted meta-level mechanisms,…
Several Multi-Agent System (MAS) metamodels and languages have been proposed in the literature to support the development of agent-based applications. MAS metamodels are used to capture a collection of concepts the relevant entities and…
Designing realistic multi-object scenes requires not only generating images, but also planning spatial layouts that respect semantic relations and physical plausibility. On one hand, while recent advances in diffusion models have enabled…
Visual compliance verification is a critical yet underexplored problem in computer vision, especially in domains such as media, entertainment, and advertising where content must adhere to complex and evolving policy rules. Existing methods…
Deepfakes utilise Artificial Intelligence (AI) techniques to create synthetic media where the likeness of one person is replaced with another. There are growing concerns that deepfakes can be maliciously used to create misleading and…
Deep reasoning is fundamental for solving complex tasks, especially in vision-centric scenarios that demand sequential, multimodal understanding. However, existing benchmarks typically evaluate agents with fully synthetic, single-turn…
Adjusting the photo color to associate with some design elements is an essential way for a graphic design to effectively deliver its message and make it aesthetically pleasing. However, existing tools and previous works face a dilemma…
Metasurfaces are generally designed by placing scatterers in periodic or pseudo-periodic grids. We propose and discuss design rules for functional metasurfaces with randomly placed anisotropic elements. By analyzing the focusing performance…
We present the first loss agent, dubbed LossAgent, for low-level image processing tasks, e.g., image super-resolution and restoration, intending to achieve any customized optimization objectives of low-level image processing in different…
Electromagnetic metasurfaces have attracted significant interest recently due to their low profile and advantageous applications. Practically, many metasurface designs start with a set of constraints for the radiated far-field, such as…
Finite element (FE) analysis guides the design and verification of nearly all manufactured objects. It is at the core of computational engineering, enabling simulation of complex physical systems, from fluids and solids to multiphysics…
Vision-Language Models (VLMs) often yield inconsistent descriptions of the same object across viewpoints, hindering the ability of embodied agents to construct consistent semantic representations over time. Previous methods resolved…
In analogy with electromagnetic networks which connect multiple input-output ports, metasurfaces can be considered as multi-port devices capable of providing different functionalities for waves of different polarizations illuminating the…
Molecular editing and optimization are multi-step problems that require iteratively improving properties while keeping molecules chemically valid and structurally similar. We frame both tasks as sequential, tool-guided decisions and…
Current Large Language Model (LLM) agents demonstrate strong reasoning and tool use capabilities, but often lack self-awareness, failing to balance these approaches effectively. This imbalance leads to Tool Overuse, where models…
Tunable metasurfaces are ultra-thin, artificial electromagnetic components that provide engineered and externally adjustable functionalities. The programmable metasurface, the HyperSurFace, concept consists in integrating controllers within…
In the recent years, metasurfaces, being flat and lightweight, have been designed to replace bulky optical components with various functions. We demonstrate a monolithic Micro-Electro-Mechanical System (MEMS) integrated with a…
Metareasoning, a branch of AI, focuses on reasoning about reasons. It has the potential to enhance robots' decision-making processes in unexpected situations. However, the concept has largely been confined to theoretical discussions and…
Artificial Intelligence is moving from models that only generate text to Agentic AI, where systems behave as autonomous entities that can perceive, reason, plan, and act. Large Language Models (LLMs) are no longer used only as passive…