As language models improve and become capable of performing more complex tasks across modalities, evaluating them automatically becomes increasingly challenging. Developing strong and robust task-specific automatic metrics gets harder, and human-annotated test sets -- which are expensive to create -- saturate more quickly. A compelling alternative is to design reliable strategies to automate the creation of test data and evaluation, but previous attempts either rely on pre-existing data, or focus solely on individual tasks. We present Zero-shot Benchmarking (ZSB), a framework for creating high-quality benchmarks for any task by leveraging language models for both synthetic test data creation and evaluation. ZSB is simple and flexible: it requires only the creation of a prompt for data generation and one for evaluation; it is scalable to tasks and languages where collecting real-world data is costly or impractical; it is model-agnostic, allowing the creation of increasingly challenging benchmarks as models improve. To assess the effectiveness of our framework, we create benchmarks for five text-only tasks and a multi-modal one: general capabilities in four languages (English, Chinese, French, and Korean), translation, and general vision-language capabilities in English. We then rank a broad range of open and closed systems on our benchmarks. ZSB rankings consistently correlate strongly with human rankings, outperforming widely-adopted standard benchmarks. Through ablations, we find that strong benchmarks can be created with open models, and that judge model size and dataset variety are crucial drivers of performance. We release all our benchmarks, and code to reproduce our experiments and to produce new benchmarks.

Since safe control of ego-vehicles depends on accurately predicting the future states of surrounding dynamic agents, numerous motion forecasting models [1, 2] have been developed to forecast an agent's future motions from historical data. Nevertheless, these predictions remain inherently prone to error, primarily because they lack information about hidden contexts or intents--such as agents' goals, velocity preferences, or even social relationships among human agents. To address these limitations, conformal prediction (CP) [3, 4] has been employed to reliably assess the models' predictive capabilities. The method offers a principled yet straightforward procedure for calibrating the models. At test time, the calibration results can be used to construct a confidence set that contains the true future states of the environment, assuming that the test and calibration data are exchangeable (i.e., their joint distribution is symmetric). Consequently, CP has been successfully applied to a variety of problems, including reinforcement learning [5, 6], linear This work was supported in part by the Information and Communications Technology Planning and Evaluation (IITP) grants funded by MSIT No. 2022-0-00124, No. 2022-0-00480 and No. RS-2021-II211343, Artificial Intelligence Graduate School Program (Seoul National University). The authors are with the Department of Electrical and Computer Engineering, ASRI, Seoul National University, Seoul 08826, South Korea,{sju5379, jungbbal, insoonyang }@snu.ac.kr arXiv:2504.00447v1

Despite numerous efforts to mitigate their biases, ML systems continue to harm already-marginalized people. While predominant ML approaches assume bias can be removed and fair models can be created, we show that these are not always possible, nor desirable, goals. We reframe the problem of ML bias by creating models to identify biased language, drawing attention to a dataset's biases rather than trying to remove them. Then, through a workshop, we evaluated the models for a specific use case: workflows of information and heritage professionals. Our findings demonstrate the limitations of ML for identifying bias due to its contextual nature, the way in which approaches to mitigating it can simultaneously privilege and oppress different communities, and its inevitability. We demonstrate the need to expand ML approaches to bias and fairness, providing a mixed-methods approach to investigating the feasibility of removing bias or achieving fairness in a given ML use case.

Humans can continuously acquire new skills and knowledge by exploiting existing ones for improved learning, without forgetting them. Similarly, 'continual learning' in machine learning aims to learn new information while preserving the previously acquired knowledge. Existing research often overlooks the nature of human learning, where tasks are interleaved due to human choice or environmental constraints. So, almost never do humans master one task before switching to the next. To investigate to what extent human-like learning can benefit the learner, we propose a method that interleaves tasks based on their 'learning progress' and energy consumption. From a machine learning perspective, our approach can be seen as a multi-task learning system that balances learning performance with energy constraints while mimicking ecologically realistic human task learning. To assess the validity of our approach, we consider a robot learning setting in simulation, where the robot learns the effect of its actions in different contexts. The conducted experiments show that our proposed method achieves better performance than sequential task learning and reduces energy consumption for learning the tasks.

All the images in this paper are best viewed in color on a computer screen at 200% zoom. Abstract -- Autonomous aerial robots are becoming commonplace in our lives. Hands-on aerial robotics courses are pivotal in training the next-generation workforce to meet the growing market demands. Such an efficient and compelling course depends on a reliable testbed. We utilize pose from an external localization system to hallucinate real-time and photorealistic visual sensors using 3D Gaussian Splatting. This enables stress-free testing of autonomy algorithms on aerial robots without the risk of crashing into obstacles. We achieve over 100Hz of system update rate. Lastly, we build upon our past experiences of offering hands-on aerial robotics courses and propose a new open-source and open-hardware curriculum based on VizFlyt for the future. We test our framework on various course projects in real-world HITL experiments and present the results showing the efficacy of such a system and its large potential use cases. Code, datasets, hardware guides and demo videos are available at https://pear .wpi.edu/research/vizflyt.html

Large Language models (LLMs) have been prominent for language translation, including low-resource languages. There has been limited study about the assessment of the quality of translations generated by LLMs, including Gemini, GPT and Google Translate. In this study, we address this limitation by using semantic and sentiment analysis of selected LLMs for Indian languages, including Sanskrit, Telugu and Hindi. We select prominent texts that have been well translated by experts and use LLMs to generate their translations to English, and then we provide a comparison with selected expert (human) translations. Our findings suggest that while LLMs have made significant progress in translation accuracy, challenges remain in preserving sentiment and semantic integrity, especially in figurative and philosophical contexts. The sentiment analysis revealed that GPT-4o and GPT-3.5 are better at preserving the sentiments for the Bhagavad Gita (Sanskrit-English) translations when compared to Google Translate. We observed a similar trend for the case of Tamas (Hindi-English) and Maha P (Telugu-English) translations. GPT-4o performs similarly to GPT-3.5 in the translation in terms of sentiments for the three languages. We found that LLMs are generally better at translation for capturing sentiments when compared to Google Translate.

AI tools will soon be in use in classrooms across England, but the education secretary, Bridget Phillipson, has one big question she wants answered: will they save time? Attending a Department for Education-sponsored hackathon in central London last week, Phillipson listened as developers explained how their tools could compile pupil reports, improve writing samples and even assess the quality of soldering done by trainee electrical engineers. After listening to one developer extol their AI writing analysis tool as "superhuman", able to aggregate all the writing a pupil had ever done, Phillipson asked bluntly: "Do you know how much time it will have saved?" That will be our next step, the developer admitted, less confidently. In an interview with the Guardian, Phillipson said her interest in AI was less futuristic and more practical.

Meta-Continual Learning (Meta-CL) has emerged as a promising approach to minimize manual labeling efforts and system resource requirements by enabling Continual Learning (CL) with limited labeled samples. However, while existing methods have shown success in image-based tasks, their effectiveness remains unexplored for sequential time-series data from sensor systems, particularly audio inputs. To address this gap, we conduct a comprehensive benchmark study evaluating six representative Meta-CL approaches using three network architectures on five datasets from both image and audio modalities. We develop MetaCLBench, an end-to-end Meta-CL benchmark framework for edge devices to evaluate system overheads and investigate trade-offs among performance, computational costs, and memory requirements across various Meta-CL methods. Our results reveal that while many Meta-CL methods enable to learn new classes for both image and audio modalities, they impose significant computational and memory costs on edge devices. Also, we find that pre-training and meta-training procedures based on source data before deployment improve Meta-CL performance. Finally, to facilitate further research, we provide practical guidelines for researchers and machine learning practitioners implementing Meta-CL on resource-constrained environments and make our benchmark framework and tools publicly available, enabling fair evaluation across both accuracy and system-level metrics.

--Federated Learning (FL) enables distributed training on edge devices but faces significant challenges due to resource constraints in edge environments, impacting both communication and computational efficiency. Existing iterative pruning techniques improve communication efficiency but are limited by their centralized design, which struggles with FL's decentralized and data-imbalanced nature, resulting in suboptimal sparsity levels. T o address these issues, we propose FedPaI, a novel efficient FL framework that leverages Pruning at Initialization (PaI) to achieve extreme sparsity. FedPaI identifies optimal sparse connections at an early stage, maximizing model capacity and significantly reducing communication and computation overhead by fixing sparsity patterns at the start of training. T o adapt to diverse hardware and software environments, FedPaI supports both structured and unstructured pruning. Additionally, we introduce personalized client-side pruning mechanisms for improved learning capacity and sparsity-aware server-side aggregation for enhanced efficiency. Experimental results demonstrate that FedPaI consistently outperforms existing efficient FL that applies conventional iterative pruning with significant leading in efficiency and model accuracy. For the first time, our proposed FedPaI achieves an extreme sparsity level of up to 98% without compromising the model accuracy compared to unpruned baselines, even under challenging non-IID settings. By employing our FedPaI with joint optimization of model learning capacity and sparsity, FL applications can benefit from faster convergence and accelerate the training by 6.4 to 7.9 . Federated Learning (FL) [1], [2] has emerged as a promising approach for decentralized machine learning on edge devices, which are rapidly growing in number and capability.

-- Domain randomization (DR) enables sim-to-real transfer by training controllers on a distribution of simulated environments, with the goal of achieving robust performance in the real world. Although DR is widely used in practice and is often solved using simple policy gradient (PG) methods, understanding of its theoretical guarantees remains limited. T oward addressing this gap, we provide the first convergence analysis of PG methods for domain-randomized linear quadratic regulation (LQR). We show that PG converges globally to the minimizer of a finite-sample approximation of the DR objective under suitable bounds on the heterogeneity of the sampled systems. We also quantify the sample-complexity associated with achieving a small performance gap between the sample-average and population-level objectives. Additionally, we propose and analyze a discount-factor annealing algorithm that obviates the need for an initial jointly stabilizing controller, which may be challenging to find. Empirical results support our theoretical findings and highlight promising directions for future work, including risk-sensitive DR formulations and stochastic PG algorithms. Domain randomization (DR) has emerged as a dominant paradigm to enable transfer of policies optimized in simulation to the real world by randomizing simulator parameters during training [1-3]. In doing so, just as with robust control, DR accounts for discrepancies between the model used in simulation to synthesize a policy and the system that it is deployed on. Since DR does not solely focus on optimizing the worst-case performance, it can result in less conservative controller performance while still ensuring robust stability with high probability. Furthermore, DR can be easily implemented via first order methods. This makes it straightforward to incorporate into a wide variety of reinforcement learning schemes and to benefit from the increasing availability of parallel computation. Despite the ease with which DR can be implemented using first order methods, ensuring convergence of these methods remains a critical challenge, with practitioners relying upon complex scheduling of various hyperparameters in the optimization procedure [3].