Systems that answer questions by reviewing the scientific literature are becoming increasingly feasible. To draw reliable conclusions, these systems should take into account the quality of available evidence, placing more weight on studies that use a valid methodology. We present a benchmark for measuring the methodological strength of biomedical papers, drawing on the risk-of-bias framework used for systematic reviews. The four benchmark tasks, drawn from more than 500 papers, cover the analysis of research study methodology, followed by evaluation of risk of bias in these studies. The benchmark contains 2000 expert-generated bias annotations, and a human-validated pipeline for fine-grained alignment with research paper content. We evaluate a range of large language models on the benchmark, and find that these models fall significantly short of expert-level performance. By providing a standardized tool for measuring judgments of study quality, the benchmark can help to guide systems that perform large-scale aggregation of scientific data.

Language-conditioned robot models (i.e., robotic foundation models) enable robots to perform a wide range of tasks based on natural language instructions. Despite strong performance on existing benchmarks, evaluating the safety and effectiveness of these models is challenging due to the complexity of testing all possible language variations. Current benchmarks have two key limitations: they rely on a limited set of human-generated instructions, missing many challenging cases, and they focus only on task performance without assessing safety, such as avoiding damage. To address these gaps, we introduce Embodied Red Teaming (ERT), a new evaluation method that generates diverse and challenging instructions to test these models. ERT uses automated red teaming techniques with Vision Language Models (VLMs) to create contextually grounded, difficult instructions. Experimental results show that state-of-the-art models frequently fail or behave unsafely on ERT tests, underscoring the shortcomings of current benchmarks in evaluating real-world performance and safety. Code and videos are available at: https://sites.google.com/view/embodiedredteam.

The common theory is that human pilot's performance degrades when responsible for an increased number of uncrewed aircraft systems (UAS). This theory was developed in the early 2010's for ground robots and not highly autonomous UAS. It has been shown that increasing autonomy can mitigate some performance impacts associated with increasing the number of UAS. Overall, the Oregon State University-Wing collaboration seeks to understand what factors negatively impact a pilot's ability to maintain responsibility and control over an assigned set of active UAS. The Phase I evaluation establishes baseline data focused on the number of UAS and the number of nests increase. This evaluation focuses on nominal operations as well as crewed aircraft encounters and adverse weather changes. The results demonstrate that the pilots were actively engaged and had very good situation awareness. Manipulation of the conditions did not result in any significant differences in overall workload. The overall results debunk the theory that increasing the number of UAS is detrimental to pilot's performance.

As events progress, news articles often update with new information: if we are not cautious, we risk propagating outdated facts. In this work, we hypothesize that linguistic features indicate factual fluidity, and that we can predict which facts in a news article will update using solely the text of a news article (i.e. not external resources like search engines). We test this hypothesis, first, by isolating fact-updates in large news revisions corpora. News articles may update for many reasons (e.g. factual, stylistic, narrative). We introduce the NewsEdits 2.0 taxonomy, an edit-intentions schema that separates fact updates from stylistic and narrative updates in news writing. We annotate over 9,200 pairs of sentence revisions and train high-scoring ensemble models to apply this schema. Then, taking a large dataset of silver-labeled pairs, we show that we can predict when facts will update in older article drafts with high precision. Finally, to demonstrate the usefulness of these findings, we construct a language model question asking (LLM-QA) abstention task. We wish the LLM to abstain from answering questions when information is likely to become outdated. Using our predictions, we show, LLM absention reaches near oracle levels of accuracy.

Self-driving cars increasingly rely on deep neural networks to achieve human-like driving. However, the opacity of such black-box motion planners makes it challenging for the human behind the wheel to accurately anticipate when they will fail, with potentially catastrophic consequences. Here, we introduce concept-wrapper network (i.e., CW-Net), a method for explaining the behavior of black-box motion planners by grounding their reasoning in human-interpretable concepts. We deploy CW-Net on a real self-driving car and show that the resulting explanations refine the human driver's mental model of the car, allowing them to better predict its behavior and adjust their own behavior accordingly. Unlike previous work using toy domains or simulations, our study presents the first real-world demonstration of how to build authentic autonomous vehicles (AVs) that give interpretable, causally faithful explanations for their decisions, without sacrificing performance. We anticipate our method could be applied to other safety-critical systems with a human in the loop, such as autonomous drones and robotic surgeons. Overall, our study suggests a pathway to explainability for autonomous agents as a whole, which can help make them more transparent, their deployment safer, and their usage more ethical.

We introduce GaussianSpeech, a novel approach that synthesizes high-fidelity animation sequences of photo-realistic, personalized 3D human head avatars from spoken audio. To capture the expressive, detailed nature of human heads, including skin furrowing and finer-scale facial movements, we propose to couple speech signal with 3D Gaussian splatting to create realistic, temporally coherent motion sequences. We propose a compact and efficient 3DGS-based avatar representation that generates expression-dependent color and leverages wrinkle- and perceptually-based losses to synthesize facial details, including wrinkles that occur with different expressions. To enable sequence modeling of 3D Gaussian splats with audio, we devise an audio-conditioned transformer model capable of extracting lip and expression features directly from audio input. Due to the absence of high-quality datasets of talking humans in correspondence with audio, we captured a new large-scale multi-view dataset of audio-visual sequences of talking humans with native English accents and diverse facial geometry. GaussianSpeech consistently achieves state-of-the-art performance with visually natural motion at real time rendering rates, while encompassing diverse facial expressions and styles.

This study addresses a critical gap in the literature regarding the use of Swarm Intelligence Optimization (SI) algorithms for client selection in Federated Learning (FL), with a focus on cybersecurity applications. Existing research primarily explores optimization techniques for centralized machine learning, leaving the unique challenges of client diveristy, non-IID data distributions, and adversarial noise in decentralized FL largely unexamined. To bridge this gap, we evaluate nine SI algorithms-Grey Wolf Optimization (GWO), Particle Swarm Optimization (PSO), Cuckoo Search, Bat Algorithm, Bee Colony, Ant Colony Optimization, Fish Swarm, Glow Worm, and Intelligent Water Droplet-across four experimental scenarios: fixed client participation, dynamic participation patterns, hetergeneous non-IID data distributions, and adversarial noise conditions. Results indicate that GWO exhibits superior adaptability and robustness, achieving the highest accuracy, recall and F1-scoress across all configurations, while PSO and Cuckoo Search also demonstrate strong performance. These findings underscore the potential of SI algorithms to address decentralized and adversarial FL challenges, offereing scalable and resilient solutions for cybersecurity applications, including intrusion detection in IoT and large-scale networks.

Supervised deep learning requires massive labeled datasets, but obtaining annotations is not always easy or possible, especially for dense tasks like semantic segmentation. To overcome this issue, numerous works explore Unsupervised Domain Adaptation (UDA), which uses a labeled dataset from another domain (source), or Semi-Supervised Learning (SSL), which trains on a partially labeled set. Despite the success of UDA and SSL, reaching supervised performance at a low annotation cost remains a notoriously elusive goal. To address this, we study the promising setting of Semi-Supervised Domain Adaptation (SSDA). We propose a simple SSDA framework that combines consistency regularization, pixel contrastive learning, and self-training to effectively utilize a few target-domain labels. Our method outperforms prior art in the popular GTA-to-Cityscapes benchmark and shows that as little as 50 target labels can suffice to achieve near-supervised performance. Additional results on Synthia-to-Cityscapes, GTA-to-BDD and Synthia-to-BDD further demonstrate the effectiveness and practical utility of the method. Lastly, we find that existing UDA and SSL methods are not well-suited for the SSDA setting and discuss design patterns to adapt them.

Understanding the attack patterns associated with a cyberattack is crucial for comprehending the attacker's behaviors and implementing the right mitigation measures. However, majority of the information regarding new attacks is typically presented in unstructured text, posing significant challenges for security analysts in collecting necessary information. In this paper, we present a sentence classification system that can identify the attack techniques described in natural language sentences from cyber threat intelligence (CTI) reports. We propose a new method for utilizing auxiliary data with the same labels to improve classification for the low-resource cyberattack classification task. The system first trains the model using the augmented training data and then trains more using only the primary data. We validate our model using the TRAM data1 and the MITRE ATT&CK framework. Experiments show that our method enhances Macro-F1 by 5 to 9 percentage points and keeps Micro-F1 scores competitive when compared to the baseline performance on the TRAM dataset.

Physics-informed deep operator networks (DeepONets) have emerged as a promising approach toward numerically approximating the solution of partial differential equations (PDEs). In this work, we aim to develop further understanding of what is being learned by physics-informed DeepONets by assessing the universality of the extracted basis functions and demonstrating their potential toward model reduction with spectral methods. Results provide clarity about measuring the performance of a physics-informed DeepONet through the decays of singular values and expansion coefficients. In addition, we propose a transfer learning approach for improving training for physics-informed DeepONets between parameters of the same PDE as well as across different, but related, PDEs where these models struggle to train well. This approach results in significant error reduction and learned basis functions that are more effective in representing the solution of a PDE.