The increasing deployment of AI models in critical applications has exposed them to significant risks from adversarial attacks. While adversarial vulnerabilities in 2D vision models have been extensively studied, the threat landscape for 3D generative models, such as Neural Radiance Fields (NeRF), remains underexplored. This work introduces \textit{AdvIRL}, a novel framework for crafting adversarial NeRF models using Instant Neural Graphics Primitives (Instant-NGP) and Reinforcement Learning. Unlike prior methods, \textit{AdvIRL} generates adversarial noise that remains robust under diverse 3D transformations, including rotations and scaling, enabling effective black-box attacks in real-world scenarios. Our approach is validated across a wide range of scenes, from small objects (e.g., bananas) to large environments (e.g., lighthouses). Notably, targeted attacks achieved high-confidence misclassifications, such as labeling a banana as a slug and a truck as a cannon, demonstrating the practical risks posed by adversarial NeRFs. Beyond attacking, \textit{AdvIRL}-generated adversarial models can serve as adversarial training data to enhance the robustness of vision systems. The implementation of \textit{AdvIRL} is publicly available at \url{https://github.com/Tommy-Nguyen-cpu/AdvIRL/tree/MultiView-Clean}, ensuring reproducibility and facilitating future research.

This paper explores the concept of reflexive actuation, examining how robots may leverage both internal and external stimuli to trigger changes in the motion, performance, or physical characteristics of the robot, such as its size, shape, or configuration, and so on. These changes themselves may in turn be sequentially re-used as input to drive further adaptations. Drawing inspiration from biological systems, where reflexes are an essential component of the response to environmental changes, reflexive actuation is critical to enable robots to adapt to diverse situations and perform complex tasks. The underlying principles of reflexive actuation are analyzed, with examples provided from existing implementations such as contact-sensitive reflexive arms, physical counters, and their applications. The paper also outlines future directions and challenges for advancing this research area, emphasizing its significance in the development of adaptive, responsive robotic systems.

In the advanced field of bio-inspired robotics, the emergence of cyborgs represents the successful integration of engineering and biological systems. Building on previous research that showed how electrical stimuli could initiate and speed up a jellyfish's movement, this study presents a groundbreaking approach that explores how the natural embodied intelligence of the animal can be harnessed to address pivotal challenges such as spontaneous exploration, navigation in various environments, control of whole-body motion, and real-time predictions of behavior. We have developed a comprehensive data acquisition system and a unique setup for stimulating jellyfish, allowing for a detailed study of their movements. Through careful analysis of both spontaneous behaviors and behaviors induced by targeted stimulation, we have identified subtle differences between natural and induced motion patterns. By using a machine learning method called physical reservoir computing, we have successfully shown that future behaviors can be accurately predicted by directly measuring the jellyfish's body shape when the stimuli align with the animal's natural dynamics. Our findings also reveal significant advancements in motion control and real-time prediction capabilities of jellyfish cyborgs. In summary, this research provides a comprehensive roadmap for optimizing the capabilities of jellyfish cyborgs, with potential implications in marine reconnaissance and sustainable ecological interventions.

Preservation of the Nasca geoglyphs at the UNESCO World Heritage Site in Peru is urgent as natural and human impact accelerates. More frequent weather extremes such as flashfloods threaten Nasca artifacts. We demonstrate that runoff models based on (sub-)meter scale, LiDAR-derived digital elevation data can highlight AI-detected geoglyphs that are in danger of erosion. We recommend measures of mitigation to protect the famous "lizard", "tree", and "hand" geoglyphs located close by, or even cut by the Pan-American Highway.

This paper presents a novel universal perturbation method for generating robust multi-view adversarial examples in 3D object recognition. Unlike conventional attacks limited to single views, our approach operates on multiple 2D images, offering a practical and scalable solution for enhancing model scalability and robustness. This generalizable method bridges the gap between 2D perturbations and 3D-like attack capabilities, making it suitable for real-world applications. Existing adversarial attacks may become ineffective when images undergo transformations like changes in lighting, camera position, or natural deformations. We address this challenge by crafting a single universal noise perturbation applicable to various object views. Experiments on diverse rendered 3D objects demonstrate the effectiveness of our approach. The universal perturbation successfully identified a single adversarial noise for each given set of 3D object renders from multiple poses and viewpoints. Compared to single-view attacks, our universal attacks lower classification confidence across multiple viewing angles, especially at low noise levels. A sample implementation is made available at https://github.com/memoatwit/UniversalPerturbation.

Large Language Model (LLM) based Generative AI systems have seen significant progress in recent years. Integrating a knowledge retrieval architecture allows for seamless integration of private data into publicly available Generative AI systems using pre-trained LLM without requiring additional model fine-tuning. Moreover, Retrieval-Centric Generation (RCG) approach, a promising future research direction that explicitly separates roles of LLMs and retrievers in context interpretation and knowledge memorization, potentially leads to more Figure 1: Retrieval-Centric Generation (RCG) approach efficient implementation. SimplyRetrieve is an presents an innovative concept that leverages the mutually open-source tool with the goal of providing beneficial interaction between LLMs and retrievers a localized, lightweight, and user-friendly interface for more efficient context interpretation and knowledge to these sophisticated advancements to memorization. Increased clarity in role-separation between the machine learning community. SimplyRetrieve context interpretation and knowledge memorization features a GUI and API based RCG platform, can potentially boost the performance of generative assisted by a Private Knowledge Base AI systems.

In robotics, an end effector is a device at the end of a robotic arm that is designed to physically interact with objects in the environment or with the environment itself. Effectively, it serves as the hand of the robot, carrying out tasks on behalf of humans. But could we turn this concept on its head and consider using living organisms themselves as end effectors? This paper introduces a novel idea of using whole living organisms as end effectors for robotics. We showcase this by demonstrating that pill bugs and chitons -- types of small, harmless creatures -- can be utilized as functional grippers. Crucially, this method does not harm these creatures, enabling their release back into nature after use. How this concept may be expanded to other organisms and applications is also discussed.

Scalar inferences (SI) are a signature example of how humans interpret language based on unspoken alternatives. While empirical studies have demonstrated that human SI rates are highly variable -- both within instances of a single scale, and across different scales -- there have been few proposals that quantitatively explain both cross- and within-scale variation. Furthermore, while it is generally assumed that SIs arise through reasoning about unspoken alternatives, it remains debated whether humans reason about alternatives as linguistic forms, or at the level of concepts. Here, we test a shared mechanism explaining SI rates within and across scales: context-driven expectations about the unspoken alternatives. Using neural language models to approximate human predictive distributions, we find that SI rates are captured by the expectedness of the strong scalemate as an alternative. Crucially, however, expectedness robustly predicts cross-scale variation only under a meaning-based view of alternatives. Our results suggest that pragmatic inferences arise from context-driven expectations over alternatives, and these expectations operate at the level of concepts.

Automated Driving Systems (ADS) open up a new domain for the automotive industry and offer new possibilities for future transportation with higher efficiency and comfortable experiences. However, autonomous driving under adverse weather conditions has been the problem that keeps autonomous vehicles (AVs) from going to level 4 or higher autonomy for a long time. This paper assesses the influences and challenges that weather brings to ADS sensors in an analytic and statistical way, and surveys the solutions against inclement weather conditions. State-of-the-art techniques on perception enhancement with regard to each kind of weather are thoroughly reported. External auxiliary solutions, weather conditions coverage in currently available datasets, simulators, and experimental facilities with weather chambers are distinctly sorted out. Additionally, potential future ADS sensors candidates and approaches beyond common senses are provided. By looking into all kinds of major weather problems the autonomous driving field is currently facing, and reviewing both hardware and computer science solutions in recent years, this survey points out the main moving trends of adverse weather problems in autonomous driving, i.e., advanced sensor fusions, more sophisticated networks, and V2X & IoT technologies; and also the limitations brought by emerging 1550 nm LiDARs. In general, this work contributes a holistic overview of the obstacles and directions of ADS development in terms of adverse weather driving conditions.

In recent years, neural models learned through self-supervised pretraining on large scale multilingual text or speech data have exhibited promising results for underresourced languages, especially when a relatively large amount of data from related language(s) is available. While the technology has a potential for facilitating tasks carried out in language documentation projects, such as speech transcription, pretraining a multilingual model from scratch for every new language would be highly impractical. We investigate the possibility for adapting an existing multilingual wav2vec 2.0 model for a new language, focusing on actual fieldwork data from a critically endangered tongue: Ainu. Specifically, we (i) examine the feasibility of leveraging data from similar languages also in fine-tuning; (ii) verify whether the model's performance can be improved by further pretraining on target language data. Our results show that continued pretraining is the most effective method to adapt a wav2vec 2.0 model for a new language and leads to considerable reduction in error rates. Furthermore, we find that if a model pretrained on a related speech variety or an unrelated language with similar phonological characteristics is available, multilingual fine-tuning using additional data from that language can have positive impact on speech recognition performance when there is very little labeled data in the target language.