A squadron of six Chinese Chengdu J-10 jets took off towards an overcast sky in front of thousands of spectators at an airfield in southern China's coastal city of Zhuhai in mid-November. Flying low in a close V-shaped formation, the jets circled back and as they approached a cluster of buildings near the spectators, trails of red, blue, yellow and white smoke suddenly poured from each plane, bringing a cheer from onlookers that was almost as loud as the roar from the warplanes' engines. Seconds later, the J-10s broke their close formation to show off a series of even more impressive acrobatic manoeuvres. But the aerial show by the seasoned pilots was far from the only demonstration of prowess at the China International Aviation & Aerospace Exhibition, better known as Airshow China or the Zhuhai Airshow, which is held biennially and named after the city in southern China where it is held. A wide array of new equipment and aircraft available to the Chinese military – known as the People's Liberation Army (PLA) – was unveiled for the first time at the airshow, held from November 12 to 17.

Effective prompting of generative AI is challenging for many users, particularly in expressing context for comprehension tasks such as explaining spreadsheet formulas, Python code, and text passages. Prompt middleware aims to address this barrier by assisting in prompt construction, but barriers remain for users in expressing adequate control so that they can receive AI-responses that match their preferences. We conduct a formative survey (n=38) investigating user needs for control over AI-generated explanations in comprehension tasks, which uncovers a trade-off between standardized but predictable support for prompting, and adaptive but unpredictable support tailored to the user and task. To explore this trade-off, we implement two prompt middleware approaches: Dynamic Prompt Refinement Control (Dynamic PRC) and Static Prompt Refinement Control (Static PRC). The Dynamic PRC approach generates context-specific UI elements that provide prompt refinements based on the user's prompt and user needs from the AI, while the Static PRC approach offers a preset list of generally applicable refinements. We evaluate these two approaches with a controlled user study (n=16) to assess the impact of these approaches on user control of AI responses for crafting better explanations. Results show a preference for the Dynamic PRC approach as it afforded more control, lowered barriers to providing context, and encouraged exploration and reflection of the tasks, but that reasoning about the effects of different generated controls on the final output remains challenging. Drawing on participant feedback, we discuss design implications for future Dynamic PRC systems that enhance user control of AI responses. Our findings suggest that dynamic prompt middleware can improve the user experience of generative AI workflows by affording greater control and guide users to a better AI response.

With the wide application of deep neural network models in various computer vision tasks, there has been a proliferation of adversarial example generation strategies aimed at deeply exploring model security. However, existing adversarial training defense models, which rely on single or limited types of attacks under a one-time learning process, struggle to adapt to the dynamic and evolving nature of attack methods. Therefore, to achieve defense performance improvements for models in long-term applications, we propose a novel Sustainable Self-Evolution Adversarial Training (SSEAT) framework. Specifically, we introduce a continual adversarial defense pipeline to realize learning from various kinds of adversarial examples across multiple stages. Additionally, to address the issue of model catastrophic forgetting caused by continual learning from ongoing novel attacks, we propose an adversarial data replay module to better select more diverse and key relearning data. Furthermore, we design a consistency regularization strategy to encourage current defense models to learn more from previously trained ones, guiding them to retain more past knowledge and maintain accuracy on clean samples. Extensive experiments have been conducted to verify the efficacy of the proposed SSEAT defense method, which demonstrates superior defense performance and classification accuracy compared to competitors.

Multimodal large language models (LLMs) have demonstrated impressive capabilities in generating high-quality images from textual instructions. However, their performance in generating scientific images--a critical application for accelerating scientific progress--remains underexplored. In this work, we address this gap by introducing ScImage, a benchmark designed to evaluate the multimodal capabilities of LLMs in generating scientific images from textual descriptions. ScImage assesses three key dimensions of understanding: spatial, numeric, and attribute comprehension, as well as their combinations, focusing on the relationships between scientific objects (e.g., squares, circles). We evaluate five models, GPT-4o, Llama, AutomaTikZ, Dall-E, and StableDiffusion, using two modes of output generation: code-based outputs (Python, TikZ) and direct raster image generation. Additionally, we examine four different input languages: English, German, Farsi, and Chinese. Our evaluation, conducted with 11 scientists across three criteria (correctness, relevance, and scientific accuracy), reveals that while GPT-4o produces outputs of decent quality for simpler prompts involving individual dimensions such as spatial, numeric, or attribute understanding in isolation, all models face challenges in this task, especially for more complex prompts.

Bias detection and mitigation is an active area of research in machine learning. This work extends previous research done by the authors to provide a rigorous and more complete analysis of the bias found in AI predictive models. Admissions data spanning six years was used to create an AI model to determine whether a given student would be directly admitted into the School of Science under various scenarios at a large urban research university. During this time, submission of standardized test scores as part of an application became optional which led to interesting questions about the impact of standardized test scores on admission decisions. We developed and analyzed AI models to understand which variables are important in admissions decisions, and how the decision to exclude test scores affects the demographics of the students who are admitted. We then evaluated the predictive models to detect and analyze biases these models may carry with respect to three variables chosen to represent sensitive populations: gender, race, and whether a student was the first in his or her family to attend college. We also extended our analysis to show that the biases detected were persistent. Finally, we included several fairness metrics in our analysis and discussed the uses and limitations of these metrics.

We present VISTA (Visualization of Internal States and Their Associations), a novel pipeline for visually exploring and interpreting neural network representations. VISTA addresses the challenge of analyzing vast multidimensional spaces in modern machine learning models by mapping representations into a semantic 2D space. The resulting collages visually reveal patterns and relationships within internal representations. We demonstrate VISTA's utility by applying it to sparse autoencoder latents uncovering new properties and interpretations. We review the VISTA methodology, present findings from our case study ( https://got.drib.net/latents/ ), and discuss implications for neural network interpretability across various domains of machine learning.

Local clustering aims to find a compact cluster near the given starting instances. This work focuses on graph local clustering, which has broad applications beyond graphs because of the internal connectivities within various modalities. While most existing studies on local graph clustering adopt the discrete graph setting (i.e., unweighted graphs without self-loops), real-world graphs can be more complex. In this paper, we extend the non-approximating Andersen-Chung-Lang ("ACL") algorithm beyond discrete graphs and generalize its quadratic optimality to a wider range of graphs, including weighted, directed, and self-looped graphs and hypergraphs. Specifically, leveraging PageRank, we propose two algorithms: GeneralACL for graphs and HyperACL for hypergraphs. We theoretically prove that, under two mild conditions, both algorithms can identify a quadratically optimal local cluster in terms of conductance with at least 1/2 probability. On the property of hypergraphs, we address a fundamental gap in the literature by defining conductance for hypergraphs from the perspective of hypergraph random walks. Additionally, we provide experiments to validate our theoretical findings.

Recently, utilizing large language models (LLMs) for metaphor detection has achieved promising results. However, these methods heavily rely on the capabilities of closed-source LLMs, which come with relatively high inference costs and latency. To address this, we propose a method for metaphor detection by fine-tuning open-source LLMs, effectively reducing inference costs and latency with a single inference step. Furthermore, metaphor detection suffers from a severe data scarcity problem, which hinders effective fine-tuning of LLMs. To tackle this, we introduce Curriculum-style Data Augmentation (CDA). Specifically, before fine-tuning, we evaluate the training data to identify correctly predicted instances for fine-tuning, while incorrectly predicted instances are used as seed data for data augmentation. This approach enables the model to quickly learn simpler knowledge and progressively acquire more complex knowledge, thereby improving performance incrementally. Experimental results demonstrate that our method achieves state-of-the-art performance across all baselines. Additionally, we provide detailed ablation studies to validate the effectiveness of CDA.

Sycophancy refers to the tendency of a large language model to align its outputs with the user's perceived preferences, beliefs, or opinions, in order to look favorable, regardless of whether those statements are factually correct. This behavior can lead to undesirable consequences, such as reinforcing discriminatory biases or amplifying misinformation. Given that sycophancy is often linked to human feedback training mechanisms, this study explores whether sycophantic tendencies negatively impact user trust in large language models or, conversely, whether users consider such behavior as favorable. To investigate this, we instructed one group of participants to answer ground-truth questions with the assistance of a GPT specifically designed to provide sycophantic responses, while another group used the standard version of ChatGPT. Initially, participants were required to use the language model, after which they were given the option to continue using it if they found it trustworthy and useful. Trust was measured through both demonstrated actions and self-reported perceptions. The findings consistently show that participants exposed to sycophantic behavior reported and exhibited lower levels of trust compared to those who interacted with the standard version of the model, despite the opportunity to verify the accuracy of the model's output.

This paper addresses the problem of thrust estimation and control for the rotors of small-sized multirotors Uncrewed Aerial Vehicles (UAVs). Accurate control of the thrust generated by each rotor during flight is one of the main challenges for robust control of quadrotors. The most common approach is to approximate the mapping of rotor speed to thrust with a simple quadratic model. This model is known to fail under non-hovering flight conditions, introducing errors into the control pipeline. One of the approaches to modeling the aerodynamics around the propellers is the Blade Element Momentum Theory (BEMT). Here, we propose a novel BEMT-based closed-loop thrust estimator and control to eliminate the laborious calibration step of finding several aerodynamic coefficients. We aim to reuse known values as a baseline and fit the thrust estimate to values closest to the real ones with a simple test bench experiment, resulting in a single scaling value. A feedforward PID thrust control was implemented for each rotor, and the methods were validated by outdoor experiments with two multirotor UAV platforms: 250mm and 500mm. A statistical analysis of the results showed that the thrust estimation and control provided better robustness under aerodynamically varying flight conditions compared to the quadratic model.