Tootfinder

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem
Yanxu Mao, Tiehan Cui, Peipei Liu, Datao You, Hongsong Zhu
https://arxiv.org/abs/2506.15170

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem
Large language models (LLMs) are rapidly evolving from single-modal systems to multimodal LLMs and intelligent agents, significantly expanding their capabilities while introducing increasingly severe security risks. This paper presents a systematic survey of the growing complexity of jailbreak attacks and corresponding defense mechanisms within the expanding LLM ecosystem. We first trace the developmental trajectory from LLMs to MLLMs and Agents, highlighting the core security challenges emergi…

Demystifying the Visual Quality Paradox in Multimodal Large Language Models
Shuo Xing, Lanqing Guo, Hongyuan Hua, Seoyoung Lee, Peiran Li, Yufei Wang, Zhangyang Wang, Zhengzhong Tu
https://arxiv.org/abs/2506.15645

Demystifying the Visual Quality Paradox in Multimodal Large Language Models
Recent Multimodal Large Language Models (MLLMs) excel on benchmark vision-language tasks, yet little is known about how input visual quality shapes their responses. Does higher perceptual quality of images already translate to better MLLM understanding? We conduct the first systematic study spanning leading MLLMs and a suite of vision-language benchmarks, applying controlled degradations and stylistic shifts to each image. Surprisingly, we uncover a visual-quality paradox: model, task, and even…

GRIM: Task-Oriented Grasping with Conditioning on Generative Examples
Shailesh, Alok Raj, Nayan Kumar, Priya Shukla, Andrew Melnik, Micheal Beetz, Gora Chand Nandi
https://arxiv.org/abs/2506.15607

GRIM: Task-Oriented Grasping with Conditioning on Generative Examples
Task-Oriented Grasping (TOG) presents a significant challenge, requiring a nuanced understanding of task semantics, object affordances, and the functional constraints dictating how an object should be grasped for a specific task. To address these challenges, we introduce GRIM (Grasp Re-alignment via Iterative Matching), a novel training-free framework for task-oriented grasping. Initially, a coarse alignment strategy is developed using a combination of geometric cues and principal component ana…

A look at China's efforts to grow its "low-altitude economy", or airspace below 1,000 meters, by leveraging its strengths in drone production and R&D (William Langley/Financial Times)
https://www.ft.com/content/65e4bb30-b04c-4f0e-8686-effb96398999…

China made millions of drones. Now it has to find uses for them
Authorities bet ‘low-altitude economy’ will be next driver of growth

Exploring MLLMs Perception of Network Visualization Principles
Jacob Miller, Markus Wallinger, Ludwig Felder, Timo Brand, Henry F\"orster, Johannes Zink, Chunyang Chen, Stephen Kobourov
https://arxiv.org/abs/2506.14611

Exploring MLLMs Perception of Network Visualization Principles
In this paper, we test whether Multimodal Large Language Models (MLLMs) can match human-subject performance in tasks involving the perception of properties in network layouts. Specifically, we replicate a human-subject experiment about perceiving quality (namely stress) in network layouts using GPT-4o and Gemini-2.5. Our experiments show that giving MLLMs exactly the same study information as trained human participants results in a similar performance to human experts and exceeds the performanc…

Contractive upper triangular matrices with prescribed diagonals and superdiagonals
Axel Renard
https://arxiv.org/abs/2506.15444 https://

Contractive upper triangular matrices with prescribed diagonals and superdiagonals
A characterization of the matrix representation of the compressed shift acting on a finite-dimensional model space endowed with the Takenaka-Malmquist-Walsh basis, among all upper triangular matrices, is proved. For a fixed dimension, this matrix is the unique matrix with spectral norm no greater than one and with a prescribed diagonal and superdiagonal. We also discuss an extension to the setting of infinite matrices.

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval
Ruofan Hu, Yan Xia, Minjie Hong, Jieming Zhu, Bo Chen, Xiaoda Yang, Minghui Fang, Tao Jin
https://arxiv.org/abs/2506.14445

Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval
Multimodal large language models (MLLMs) have seen substantial progress in recent years. However, their ability to represent multimodal information in the acoustic domain remains underexplored. In this work, we introduce Vela, a novel framework designed to adapt MLLMs for the generation of universal multimodal embeddings. By leveraging MLLMs with specially crafted prompts and selected in-context learning examples, Vela effectively bridges the modality gap across various modalities. We then prop…

FEAST: A Flexible Mealtime-Assistance System Towards In-the-Wild Personalization
Rajat Kumar Jenamani, Tom Silver, Ben Dodson, Shiqin Tong, Anthony Song, Yuting Yang, Ziang Liu, Benjamin Howe, Aimee Whitneck, Tapomayukh Bhattacharjee
https://arxiv.org/abs/2506.14968

FEAST: A Flexible Mealtime-Assistance System Towards In-the-Wild Personalization
Physical caregiving robots hold promise for improving the quality of life of millions worldwide who require assistance with feeding. However, in-home meal assistance remains challenging due to the diversity of activities (e.g., eating, drinking, mouth wiping), contexts (e.g., socializing, watching TV), food items, and user preferences that arise during deployment. In this work, we propose FEAST, a flexible mealtime-assistance system that can be personalized in-the-wild to meet the unique needs …

DesignCoder: Hierarchy-Aware and Self-Correcting UI Code Generation with Large Language Models
Yunnong Chen, Shixian Ding, YingYing Zhang, Wenkai Chen, Jinzhou Du, Lingyun Sun, Liuqing Chen
https://arxiv.org/abs/2506.13663

DesignCoder: Hierarchy-Aware and Self-Correcting UI Code Generation with Large Language Models
Multimodal large language models (MLLMs) have streamlined front-end interface development by automating code generation. However, these models also introduce challenges in ensuring code quality. Existing approaches struggle to maintain both visual consistency and functional completeness in the generated components. Moreover, they lack mechanisms to assess the fidelity and correctness of the rendered pages. To address these issues, we propose DesignCoder, a novel hierarchical-aware and self-corr…

Zero-Shot Scene Understanding with Multimodal Large Language Models for Automated Vehicles
Mohammed Elhenawy, Shadi Jaradat, Taqwa I. Alhadidi, Huthaifa I. Ashqar, Ahmed Jaber, Andry Rakotonirainy, Mohammad Abu Tami
https://arxiv.org/abs/2506.12232

Zero-Shot Scene Understanding with Multimodal Large Language Models for Automated Vehicles
Scene understanding is critical for various downstream tasks in autonomous driving, including facilitating driver-agent communication and enhancing human-centered explainability of autonomous vehicle (AV) decisions. This paper evaluates the capability of four multimodal large language models (MLLMs), including relatively small models, to understand scenes in a zero-shot, in-context learning setting. Additionally, we explore whether combining these models using an ensemble approach with majority…