14 accepted papers
The rapid evolution of Large Language Models (LLMs) has empowered even non-programmers to create visually appealing frontend mini-games with a single instruction. However, open-source models significantly lag behind proprietary counterparts in this domain. The core bottleneck is the lack of an evalu…
Building reliable computer-use agents requires grounding: accurately connecting natural language instructions to the correct on-screen elements. While large datasets exist for web and mobile interactions, high-quality resources for desktop environments are limited. To address this gap, we introduce…
Dataset Distillation (DD) seeks to create a compact dataset from a large, real-world dataset. While recent methods often rely on heuristic approaches to balance efficiency and quality, the fundamental relationship between original and synthetic data remains underexplored. This paper revisits knowled…
Web applications are prime targets for cyberattacks due to their role as entry points to vital services and sensitive data repositories. Traditional penetration testing is expensive and requires specialized expertise, creating scalability challenges for securing the expanding web ecosystem. While la…
This paper presents a complete quadrotor aerial docking system that utilizes both vision and magnetic field guidance to achieve high-precision docking. Visual guidance is implemented using a combination of a forward-facing camera and an upward-facing camera, which provide feedback on the local and r
The proliferation of multimodal memes in the social media era demands that multimodal Large Language Models (mLLMs) effectively understand meme harmfulness. Existing benchmarks for assessing mLLMs on harmful meme understanding rely on accuracy-based, model-agnostic evaluations using static datasets.…
Fine-tuning large language models (LLMs) on task-specific data is essential for their effective deployment. As dataset sizes grow, efficiently selecting optimal subsets for training becomes crucial to balancing performance and computational costs. Traditional data selection methods often require fin…
The ability of critique is vital for models to self-improve and serve as reliable AI assistants. While extensively studied in language-only settings, multimodal critique of Large Multimodal Models (LMMs) remains underexplored despite their growing capabilities in tasks like captioning and visual rea
The proliferation of memes on social media necessitates the capabilities of multimodal Large Language Models (mLLMs) to effectively understand multimodal harmfulness. Existing evaluation approaches predominantly focus on mLLMs’ detection accuracy for binary classification tasks, which often fail to
Imagine a future when we can Zoom-call a robot to manage household chores remotely. This work takes one step in this direction. Robi Butler is a new household robot assistant that enables seamless multimodal remote interaction. It allows the human user to monitor its environment from a first-person
Graphical User Interface (GUI) agents have made substantial strides in understanding and executing user instructions across diverse platforms. Yet, grounding these instructions to precise interface elements remains challenging—especially in complex, high-resolution, professional environments. Tradit…
Data synthesis has become a crucial research area in large language models (LLMs), especially for generating high-quality instruction fine-tuning data to enhance downstream performance. In code generation, a key application of LLMs, manual annotation of code instruction data is costly. Recent method…
This letter presents a novel tilt-rotor octocopter that can generate tiltable thrust without the need for servo-driven mechanisms. The octocopter's eight rotors are divided into pairs and each pair is mounted on an arm, which is connected to the airframe through passive hinges. Each pair is also equ
Programming often involves converting detailed and complex specifications into code, a process during which developers typically utilize visual aids to more effectively convey concepts. While recent developments in Large Multimodal Models have demonstrated remarkable abilities in visual reasoning an…