The Deep operator network (DeepONet) is a powerful yet simple neural operator architecture that utilizes two deep neural networks to learn mappings between infinite-dimensional function spaces. This architecture is highly flexible, allowing the evaluation of the solution field at any location within the desired domain. However, it imposes a strict constraint on the input space, requiring all input functions to be discretized at the same locations; this limits its practical applications. In this work, we introduce a Resolution Independent Neural Operator (RINO) that provides a framework to make DeepONet resolution-independent, enabling it to handle input functions that are arbitrarily, but sufficiently finely, discretized. To this end, we propose a dictionary learning algorithm to adaptively learn a set of appropriate continuous basis functions, parameterized as implicit neural representations (INRs), from the input data. These basis functions are then used to project arbitrary input function data as a point cloud onto an embedding space (i.e., a vector space of finite dimensions) with dimensionality equal to the dictionary size, which can be directly used by DeepONet without any architectural changes. In particular, we utilize sinusoidal representation networks (SIRENs) as our trainable INR basis functions. We demonstrate the robustness and applicability of RINO in handling arbitrarily (but sufficiently richly) sampled input functions during both training and inference through several numerical examples.

This survey offers a comprehensive overview of recent advancements in Large Language Model (LLM) serving systems, focusing on research since the year 2023. We specifically examine system-level enhancements that improve performance and efficiency without altering the core LLM decoding mechanisms. By selecting and reviewing high-quality papers from prestigious ML and system venues, we highlight key innovations and practical considerations for deploying and scaling LLMs in real-world production environments. This survey serves as a valuable resource for LLM practitioners seeking to stay abreast of the latest developments in this rapidly evolving field.

The advances of large foundation models necessitate wide-coverage, low-cost, and zero-contamination benchmarks. Despite continuous exploration of language model evaluations, comprehensive studies on the evaluation of Large Multi-modal Models (LMMs) remain limited. In this work, we introduce LMMS-EVAL, a unified and standardized multimodal benchmark framework with over 50 tasks and more than 10 models to promote transparent and reproducible evaluations. Although LMMS-EVAL offers comprehensive coverage, we find it still falls short in achieving low cost and zero contamination. To approach this evaluation trilemma, we further introduce LMMS-EVAL LITE, a pruned evaluation toolkit that emphasizes both coverage and efficiency. Additionally, we present Multimodal LIVEBENCH that utilizes continuously updating news and online forums to assess models' generalization abilities in the wild, featuring a low-cost and zero-contamination evaluation approach. In summary, our work highlights the importance of considering the evaluation trilemma and provides practical solutions to navigate the trade-offs in evaluating large multi-modal models, paving the way for more effective and reliable benchmarking of LMMs. We opensource our codebase and maintain leaderboard of LIVEBENCH at https://github.com/EvolvingLMMs-Lab/lmms-eval and https://huggingface.co/spaces/lmms-lab/LiveBench.

Walk along: An Experiment on Controlling the Mobile Robot'Spot' with Voice and Gestures Abstract Robots are becoming increasingly intelligent and can autonomously perform tasks such as navigating between locations. However, human oversight remains crucial. This study compared two handsfree methods for directing mobile robots: voice control and gesture control. These methods were tested with the human stationary and walking freely. We hypothesized that walking with the robot would lead to higher intuitiveness ratings and better task performance due to increased stimulus-response compatibility, assuming humans align themselves with the robot. In a 2 2 within-subject design, 218 participants guided the quadrupedal robot Spot using 90 rotation and walk-forward commands. After each trial, participants rated the intuitiveness of the command mapping, while post-experiment interviews were used to gather the participants' preferences. Results showed that voice control combined with walking with Spot was the most favored and intuitive, while gesture control while standing caused confusion for left/right commands. Despite this, 29% of participants preferred gesture control, citing task engagement and visual congruence as reasons. An odometry-based analysis revealed that participants aligned behind Spot, particularly in the gesture control condition, when allowed to walk. In conclusion, voice control with walking produced the best outcomes. Improving physical ergonomics and adjusting gesture types could improve the effectiveness of gesture control. Introduction Robots have traditionally been viewed as devices designed to efficiently perform repetitive tasks, mainly in industrial settings and logistical operations. However, with the advancement of AI, robots increasingly take on new roles. Modern robots can understand and adapt to their surroundings, paving the way for mobile robotics. The human-machine interface (HMI) plays a vital role in the control of mobile robots, as these robots are not yet capable of fully autonomous operation in open-ended environments (e.g., Endsley, 2017; Ezenkwu & Starkey, 2019; Hatanaka et al., 2023; Pianca & Santucci, 2023).

This study performed an extensive evaluation of the performances of all configurations of YOLOv8, YOLOv9, and YOLOv10 object detection algorithms for fruitlet (of green fruit) detection in commercial orchards. Additionally, this research performed and validated in-field counting of fruitlets using an iPhone and machine vision sensors in 5 different apple varieties (Scifresh, Scilate, Honeycrisp, Cosmic crisp & Golden delicious). This comprehensive investigation of total 17 different configurations (5 for YOLOv8, 6 for YOLOv9 and 6 for YOLOv10) revealed that YOLOv9 outperforms YOLOv10 and YOLOv8 in terms of mAP@50, while YOLOv10x outperformed all 17 configurations tested in terms of precision and recall. Specifically, YOLOv9 Gelan-e achieved the highest mAP@50 of 0.935, outperforming YOLOv10n's 0.921 and YOLOv8s's 0.924. In terms of precision, YOLOv10x achieved the highest precision of 0.908, indicating superior object identification accuracy compared to other configurations tested (e.g. YOLOv9 Gelan-c with a precision of 0.903 and YOLOv8m with 0.897. In terms of recall, YOLOv10s achieved the highest in its series (0.872), while YOLOv9 Gelan m performed the best among YOLOv9 configurations (0.899), and YOLOv8n performed the best among the YOLOv8 configurations (0.883). Meanwhile, three configurations of YOLOv10: YOLOv10b, YOLOv10l, and YOLOv10x achieved superior post-processing speeds of 1.5 milliseconds, outperforming all other configurations within the YOLOv9 and YOLOv8 families. Specifically, YOLOv9 Gelan-e recorded a post-processing speed of 1.9 milliseconds, and YOLOv8m achieved 2.1 milliseconds. Furthermore, YOLOv8n exhibited the highest inference speed among all configurations tested, achieving a processing time of 4.1 milliseconds while YOLOv9 Gelan-t and YOLOv10n also demonstrated comparatively slower inference speeds of 9.3 ms and 5.5 ms, respectively.

This paper presents a practical approach for the optimization of topological simplification, a central pre-processing step for the analysis and visualization of scalar data. Given an input scalar field f and a set of "signal" persistence pairs to maintain, our approach produces an output field g that is close to f and which optimizes (i) the cancellation of "non-signal" pairs, while (ii) preserving the "signal" pairs. In contrast to pre-existing simplification algorithms, our approach is not restricted to persistence pairs involving extrema and can thus address a larger class of topological features, in particular saddle pairs in three-dimensional scalar data. Our approach leverages recent generic persistence optimization frameworks and extends them with tailored accelerations specific to the problem of topological simplification. Extensive experiments report substantial accelerations over these frameworks, thereby making topological simplification optimization practical for real-life datasets. Our approach enables a direct visualization and analysis of the topologically simplified data, e.g., via isosurfaces of simplified topology (fewer components and handles). We apply our approach to the extraction of prominent filament structures in three-dimensional data. Specifically, we show that our pre-simplification of the data leads to practical improvements over standard topological techniques for removing filament loops. We also show how our approach can be used to repair genus defects in surface processing. Finally, we provide a C++ implementation for reproducibility purposes.

2023 was the year the world woke up to generative AI, and 2024 is the year policymakers are responding more firmly. Importantly, this policy momentum is taking place alongside real world creation and distribution of synthetic media. Social media platforms, news organizations, dating apps, image generation companies, and more are already navigating a world of AI-generated visuals and sounds, already changing hearts and minds, as policymakers try to catch up. How, then, can AI governance capture the complexity of the synthetic media landscape? How can it attend to synthetic media's myriad uses, ranging from storytelling to privacy preservation, to deception, fraud, and defamation, taking into account the many stakeholders involved in its development, creation, and distribution? And what might it mean to govern synthetic media in a manner that upholds the truth while bolstering freedom of expression? What follows is the first known collection of diverse examples of the implementation of synthetic media governance that responds to these questions, specifically through Partnership on AI's (PAI) Responsible Practices for Synthetic Media - a voluntary, normative Framework for creating, distributing, and building technology for synthetic media responsibly, launched in February 2023. In this paper, we present a case bank of real world examples that help operationalize the Framework - highlighting areas synthetic media governance can be applied, augmented, expanded, and refined for use, in practice. Read together, the cases emphasize distinct elements of AI policymaking and seven emergent best practices supporting transparency, safety, expression, and digital dignity online: consent, disclosure, and differentiation between harmful and creative use cases.

For the last couple of years, the tech community has tested no-strings-attached payments of 500 or 1,000 a month to those in dire need. Some of these experiments have happened in the heart of Silicon Valley, where a one-bedroom apartment rents for 3,000 a month and a modest house is often an unaffordable luxury. Silicon Valley's backing of these efforts has propelled the idea of a guaranteed income -- also known as cash transfers, unconditional cash and, in its most utopian form, universal basic income -- into the mainstream. But a bipartisan political consensus around the movement is fracturing even though the data seems to show that the programs are effective. In recent months, the Texas attorney general went to court to prevent public funds from being used in a basic income program in Houston.

Plans to put a human colony on the moon took a promising step forward this week as scientists in Italy revealed they've found the first lunar cave. It could be a site for a lunar base, as it offers shelter from'the harsh surface environment' and could support long-term human exploration of the moon. It comes as NASA continues with its ambition to set up its'Artemis Base Camp' in the lunar south region within the decade – but what could this look like? MailOnline spoke to experts to find out how the first settlers could set up camp on our lunar satellite and what sort of facilities it may have. Moondwellers could live and sleep in 3D-printed houses, or eventually play football on laser-cut pitches in their Prada spacesuits.

Hong Kong's government is testing the city's own ChatGPT -style tool for its employees, with plans to eventually make it available to the public, its innovation minister said after OpenAI took extra steps to block access from the city and other unsupported regions. Secretary for Innovation, Technology and Industry Sun Dong said on a Saturday radio show that his bureau was trying out the artificial intelligence program, whose Chinese name translates to "document assistance application for civil servants," to further improve its capabilities. He plans to have it available for the rest of the government this year. The program was developed by a generative AI research and development center led by the Hong Kong University of Science and Technology in collaboration with several other universities. Sun said the model would provide functions like graphics and video design in the future.