Search

Crop biomass offers crucial insights into plant health and yield, making it essential for crop science, farming systems, and agricultural research. However, current measurement methods, which are labor-intensive, destructive, and imprecise, hinder large-scale quantification of this trait. To address this limitation, we present a biomass prediction network (BioNet), designed for adaptation across different data modalities, including point clouds and drone imagery. Our BioNet, utilizing a sparse 3D convolutional neural network (CNN) and a transformer-based prediction module, processes point clouds and other 3D data representations to predict biomass. To further extend BioNet for drone imagery, we integrate a neural feature field (NeFF) module, enabling 3D structure reconstruction and the transformation of 2D semantic features from vision foundation models into the corresponding 3D surfaces. For the point cloud modality, BioNet demonstrates superior performance on two public datasets, with an approximate 6.1% relative improvement (RI) over the state-of-the-art. In the RGB image modality, the combination of BioNet and NeFF achieves a 7.9% RI. Additionally, the NeFF-based approach utilizes inexpensive, portable drone-mounted cameras, providing a scalable solution for large field applications.

Many printed electronic applications require strain-independent electrical properties to ensure deformation-independent performance. Thus, developing printed, flexible devices using 2D and other nanomaterials will require an understanding of the effect of strain on the electrical properties of nano-networks. Here we introduce novel AC electrical techniques to fully characterise the effect of strain on the resistance of high mobility printed networks, fabricated from of electrochemically exfoliated MoS2 nanosheets. These devices were initially characterised using DC piezoresistance measurements and showed good cyclability and a linear strain response, consistent with a low gauge factor of G~3. However, AC impedance spectroscopy measurements, performed as a function of strain, allowed the measurement of the effects of strain on both the nanosheets and the inter-nanosheet junctions separately. The junction resistance was found to increase linearly with strain, while the nanosheet resistance remained constant. This response is consistent with strain-induced sliding of the highly-aligned nanosheets past one another, without any strain being transferred to the sheets themselves. Our approach allows us to individually estimate the contributions of dimensional factors (G~1.4) and intrinsic factors (G~1.9) to the total gauge factor. This novel technique may provide insight into other piezoresistive systems., Comment: 3 Figures

Solution-processable 2D materials are promising candidates for a range of printed electronics applications. Yet maximising their potential requires solution-phase processing of nanosheets into high-quality networks with carrier mobility ({\mu}Net) as close as possible to that of individual nanosheets ({\mu}NS). In practise, the presence of inter-nanosheet junctions generally limits electronic conduction, such that the ratio of junction resistance (RJ) to nanosheet resistance (RNS), determines the network mobility via . Hence, achieving RJ/RNS<1 is a crucial step for implementation of 2D materials in printed electronics applications. In this work, we utilise an advanced liquid-interface deposition process to maximise nanosheet alignment and network uniformity, thus reducing RJ. We demonstrate the approach using graphene and MoS2 as model materials, achieving low RJ/RNS values of 0.5 and 0.2, respectively. The resultant graphene networks show a high conductivity of {\sigma}Net = 5 \times 104 S/m while our semiconducting MoS2 networks demonstrate record mobility of {\mu}Net = 30 cm2/Vs, both at extremely low network thickness (tNet <10 nm). Finally, we show that the deposition process is compatible with non-layered quasi-2D materials such as silver nanosheets (AgNS), achieving network conductivity close to bulk silver for networks <100 nm thick. We believe this work is the first to report nanosheet networks with RJ/RNS<1 and serves to guide future work in 2D materials-based printed electronics.

Science is increasingly global, with international collaboration playing a crucial role in advancing scientific development and knowledge exchange across borders. However, the processes that regulate how scientific labor is distributed among countries remain underexplored, leading to challenges in ensuring both effective collaboration and equitable participation across diverse scientific communities. Here, we leverage three million internationally coauthored publications produced by countries worldwide to examine the division of scientific labor in international collaboration, identify the factors that shape this distribution, and assess its broader consequences. Our findings uncover a persistent hierarchical structure in international collaboration, with researchers from scientifically advanced countries tend to occupy leading roles, while those from less-developed countries are often relegated to supportive roles, even after controlling for various influential factors. This hierarchy is also reflected in the research content, as countries with lower scientific capacity tend to participate in international collaborations that deviate from their domestic science. By analyzing the labor division within international collaborations, we demonstrate that researchers from less-developed countries face systematic disadvantages, which not only limit their contributions to the global scientific community but also prevent them from fully benefiting from international collaborations., Comment: 35 pages, 7 figures, 3 tables

Delayed processes are ubiquitous throughout biology. These delays may arise through maturation processes or as the result of complex multi-step networks, and mathematical models with distributed delays are increasingly used to capture the heterogeneity present in these delayed processes. Typically, these distributed delay differential equations are simulated by discretizing the distributed delay and using existing tools for the resulting multi-delay delay differential equations or by using an equivalent representation under additional assumptions on the delayed process. Here, we use the existing framework of functional continuous Runge-Kutta methods to confirm the convergence of this common approach. Our analysis formalizes the intuition that the least accurate numerical method dominates the error. We give a number of examples to illustrate the predicted convergence, derive a new class of equivalences between distributed delay and discrete delay differential equations, and give conditions for the existence of breaking points in the distributed delay differential equation. Finally, our work shows how recently reported multi-delay complexity collapse arises naturally from the convergence of equations with multiple discrete delays to equations with distributed delays, offering insight into the dynamics of the Mackey-Glass equation., Comment: 18 pages, 2 figures

Algorithmic fairness in recommender systems requires close attention to the needs of a diverse set of stakeholders that may have competing interests. Previous work in this area has often been limited by fixed, single-objective definitions of fairness, built into algorithms or optimization criteria that are applied to a single fairness dimension or, at most, applied identically across dimensions. These narrow conceptualizations limit the ability to adapt fairness-aware solutions to the wide range of stakeholder needs and fairness definitions that arise in practice. Our work approaches recommendation fairness from the standpoint of computational social choice, using a multi-agent framework. In this paper, we explore the properties of different social choice mechanisms and demonstrate the successful integration of multiple, heterogeneous fairness definitions across multiple data sets.

Chronic wounds and associated complications present ever growing burdens for clinics and hospitals world wide. Venous, arterial, diabetic, and pressure wounds are becoming increasingly common globally. These conditions can result in highly debilitating repercussions for those affected, with limb amputations and increased mortality risk resulting from infection becoming more common. New methods to assist clinicians in chronic wound care are therefore vital to maintain high quality care standards. This paper presents an improved HarDNet segmentation architecture which integrates a contrast-eliminating component in the initial layers of the network to enhance feature learning. We also utilise a multi-colour space tensor merging process and adjust the harmonic shape of the convolution blocks to facilitate these additional features. We train our proposed model using wound images from light-skinned patients and test the model on two test sets (one set with ground truth, and one without) comprising only darker-skinned cases. Subjective ratings are obtained from clinical wound experts with intraclass correlation coefficient used to determine inter-rater reliability. For the dark-skin tone test set with ground truth, we demonstrate improvements in terms of Dice similarity coefficient (+0.1221) and intersection over union (+0.1274). Qualitative analysis showed high expert ratings, with improvements of >3% demonstrated when comparing the baseline model with the proposed model. This paper presents the first study to focus on darker-skin tones for chronic wound segmentation using models trained only on wound images exhibiting lighter skin. Diabetes is highly prevalent in countries where patients have darker skin tones, highlighting the need for a greater focus on such cases. Additionally, we conduct the largest qualitative study to date for chronic wound segmentation.

Synthetic data is a useful resource for algorithmic research. It allows for the evaluation of systems under a range of conditions that might be difficult to achieve in real world settings. In recommender systems, the use of synthetic data is somewhat limited; some work has concentrated on building user-item interaction data at large scale. We believe that fairness-aware recommendation research can benefit from simulated data as it allows the study of protected groups and their interactions without depending on sensitive data that needs privacy protection. In this paper, we propose a novel type of data for fairness-aware recommendation: synthetic recommender system outputs that can be used to study re-ranking algorithms.

Teleoperation is an important technology to enable supervisors to control agricultural robots remotely. However, environmental factors in dense crop rows and limitations in network infrastructure hinder the reliability of data streamed to teleoperators. These issues result in delayed and variable frame rate video feeds that often deviate significantly from the robot's actual viewpoint. We propose a modular learning-based vision pipeline to generate delay-compensated images in real-time for supervisors. Our extensive offline evaluations demonstrate that our method generates more accurate images compared to state-of-the-art approaches in our setting. Additionally, we are one of the few works to evaluate a delay-compensation method in outdoor field environments with complex terrain on data from a real robot in real-time. Additional videos are provided at https://sites.google.com/illinois.edu/comp-teleop., Comment: 8 pages, 4 figures, 3 tables

In this work, we introduce Gemma 2, a new addition to the Gemma family of lightweight, state-of-the-art open models, ranging in scale from 2 billion to 27 billion parameters. In this new version, we apply several known technical modifications to the Transformer architecture, such as interleaving local-global attentions (Beltagy et al., 2020a) and group-query attention (Ainslie et al., 2023). We also train the 2B and 9B models with knowledge distillation (Hinton et al., 2015) instead of next token prediction. The resulting models deliver the best performance for their size, and even offer competitive alternatives to models that are 2-3 times bigger. We release all our models to the community.

Social technology research today largely focuses on mitigating the negative impacts of technology and, therefore, often misses the potential of technology to enhance human connections and well-being. However, we see a potential to shift towards a holistic view of social technology's impact on human flourishing. We introduce Positive Social Technology (Positech), a framework that shifts emphasis toward leveraging social technologies to support and augment human flourishing. This workshop is organized around three themes relevant to Positech: 1) "Exploring Relevant and Adjacent Research" to define and widen the Positech scope with insights from related fields, 2) "Projecting the Landscape of Positech" for participants to outline the domain's key aspects and 3) "Envisioning the Future of Positech," anchored around strategic planning towards a sustainable research community. Ultimately, this workshop will serve as a platform to shift the narrative of social technology research towards a more positive, human-centric approach. It will foster research that goes beyond fixing technologies to protect humans from harm, to also pursue enriching human experiences and connections through technology.

Seams are areas of overlapping fabric formed by stitching two or more pieces of fabric together in the cut-and-sew apparel manufacturing process. In SeamPose, we repurposed seams as capacitive sensors in a shirt for continuous upper-body pose estimation. Compared to previous all-textile motion-capturing garments that place the electrodes on the clothing surface, our solution leverages existing seams inside of a shirt by machine-sewing insulated conductive threads over the seams. The unique invisibilities and placements of the seams afford the sensing shirt to look and wear similarly as a conventional shirt while providing exciting pose-tracking capabilities. To validate this approach, we implemented a proof-of-concept untethered shirt with 8 capacitive sensing seams. With a 12-participant user study, our customized deep-learning pipeline accurately estimates the relative (to the pelvis) upper-body 3D joint positions with a mean per joint position error (MPJPE) of 6.0 cm. SeamPose represents a step towards unobtrusive integration of smart clothing for everyday pose estimation.

Intratumour phenotypic heterogeneity is nowadays understood to play a critical role in disease progression and treatment failure. Accordingly, there has been increasing interest in the development of mathematical models capable of capturing its role in cancer cell adaptation. This can be systematically achieved by means of models comprising phenotype-structured nonlocal partial differential equations, tracking the evolution of the phenotypic density distribution of the cell population, which may be compared to gene and protein expression distributions obtained experimentally. Nevertheless, given the high analytical and computational cost of solving these models, much is to be gained from reducing them to systems of ordinary differential equations for the moments of the distribution. We propose a generalised method of model-reduction, relying on the use of a moment generating function, Taylor series expansion and truncation closure, to reduce a nonlocal reaction-advection-diffusion equation, with general phenotypic drift and proliferation rate functions, to a system of moment equations up to arbitrary order. Our method extends previous results in the literature, which we address via two examples, by removing any \textit{a priori} assumption on the shape of the distribution, and provides a flexible framework for mathematical modellers to account for the role of phenotypic heterogeneity in cancer adaptive dynamics, in a simpler mathematical framework., Comment: 23 pages, 1 figure

The rapid emergence of generative Language Models (LMs) has led to growing concern about the impacts that their unexamined adoption may have on the social well-being of diverse user groups. Meanwhile, LMs are increasingly being adopted in K-20 schools and one-on-one student settings with minimal investigation of potential harms associated with their deployment. Motivated in part by real-world/everyday use cases (e.g., an AI writing assistant) this paper explores the potential psychosocial harms of stories generated by five leading LMs in response to open-ended prompting. We extend findings of stereotyping harms analyzing a total of 150K 100-word stories related to student classroom interactions. Examining patterns in LM-generated character demographics and representational harms (i.e., erasure, subordination, and stereotyping) we highlight particularly egregious vignettes, illustrating the ways LM-generated outputs may influence the experiences of users with marginalized and minoritized identities, and emphasizing the need for a critical understanding of the psychosocial impacts of generative AI tools when deployed and utilized in diverse social contexts., Comment: Presented in Impact of GenAI on Social and Individual Well-being at AAAI 2024 Spring Symposium Series (2024)

Crop biomass, a critical indicator of plant growth, health, and productivity, is invaluable for crop breeding programs and agronomic research. However, the accurate and scalable quantification of crop biomass remains inaccessible due to limitations in existing measurement methods. One of the obstacles impeding the advancement of current crop biomass prediction methodologies is the scarcity of publicly available datasets. Addressing this gap, we introduce a new dataset in this domain, i.e. Multi-modality dataset for crop biomass estimation (MMCBE). Comprising 216 sets of multi-view drone images, coupled with LiDAR point clouds, and hand-labelled ground truth, MMCBE represents the first multi-modality one in the field. This dataset aims to establish benchmark methods for crop biomass quantification and foster the development of vision-based approaches. We have rigorously evaluated state-of-the-art crop biomass estimation methods using MMCBE and ventured into additional potential applications, such as 3D crop reconstruction from drone imagery and novel-view rendering. With this publication, we are making our comprehensive dataset available to the broader community., Comment: 10 pages, 10 figures, 3 tables

The rapid deployment of generative language models (LMs) has raised concerns about social biases affecting the well-being of diverse consumers. The extant literature on generative LMs has primarily examined bias via explicit identity prompting. However, prior research on bias in earlier language-based technology platforms, including search engines, has shown that discrimination can occur even when identity terms are not specified explicitly. Studies of bias in LM responses to open-ended prompts (where identity classifications are left unspecified) are lacking and have not yet been grounded in end-consumer harms. Here, we advance studies of generative LM bias by considering a broader set of natural use cases via open-ended prompting. In this "laissez-faire" setting, we find that synthetically generated texts from five of the most pervasive LMs (ChatGPT3.5, ChatGPT4, Claude2.0, Llama2, and PaLM2) perpetuate harms of omission, subordination, and stereotyping for minoritized individuals with intersectional race, gender, and/or sexual orientation identities (AI/AN, Asian, Black, Latine, MENA, NH/PI, Female, Non-binary, Queer). We find widespread evidence of bias to an extent that such individuals are hundreds to thousands of times more likely to encounter LM-generated outputs that portray their identities in a subordinated manner compared to representative or empowering portrayals. We also document a prevalence of stereotypes (e.g. perpetual foreigner) in LM-generated outputs that are known to trigger psychological harms that disproportionately affect minoritized individuals. These include stereotype threat, which leads to impaired cognitive performance and increased negative self-perception. Our findings highlight the urgent need to protect consumers from discriminatory harms caused by language models and invest in critical AI education programs tailored towards empowering diverse consumers., Comment: 16 pages (43 if including supplementals), 8 figures (23 if including supplementals)

We introduce RecurrentGemma, a family of open language models which uses Google's novel Griffin architecture. Griffin combines linear recurrences with local attention to achieve excellent performance on language. It has a fixed-sized state, which reduces memory use and enables efficient inference on long sequences. We provide two sizes of models, containing 2B and 9B parameters, and provide pre-trained and instruction tuned variants for both. Our models achieve comparable performance to similarly-sized Gemma baselines despite being trained on fewer tokens.

This work introduces Gemma, a family of lightweight, state-of-the art open models built from the research and technology used to create Gemini models. Gemma models demonstrate strong performance across academic benchmarks for language understanding, reasoning, and safety. We release two sizes of models (2 billion and 7 billion parameters), and provide both pretrained and fine-tuned checkpoints. Gemma outperforms similarly sized open models on 11 out of 18 text-based tasks, and we present comprehensive evaluations of safety and responsibility aspects of the models, alongside a detailed description of model development. We believe the responsible release of LLMs is critical for improving the safety of frontier models, and for enabling the next wave of LLM innovations.

We unveil that a previously-unreported vicious cycle can be created when bus queues form at curbside stops along a corridor. Buses caught in this cycle exhibit growing variation in headways as they travel from stop to stop. Bus (and patron) delays accumulate in like fashion and can grow large on long, busy corridors. We show that this damaging cycle can be abated in simple ways. Present solutions entail holding buses at a corridor entrance and releasing them as per various strategies proposed in the literature. We introduce a modest variant to the simplest of these strategies. It releases buses at headways that are slightly less than, or equal to, the scheduled values. It turns out that periodically releasing buses at slightly smaller headways can substantially reduce bus delays caused by holding so that benefits can more readily outweigh costs in corridors that contain a sufficient number of serial bus stops. The simple variant is shown to perform about as well as, or better than, other bus-holding strategies in terms of saving delays, and is more effective than other strategies in regularizing bus headways. We also show that grouping buses from across multiple lines and holding them by group can be effective when patrons have the flexibility to choose buses from across all lines in a group. Findings come by formulating select models of bus-corridor dynamics and using these to simulate part of the Bus Rapid Transit corridor in Guangzhou, China.

Because it is difficult to precisely specify complex objectives, reinforcement learning policies are often optimized using flawed proxy rewards that seem to capture the true objective. However, optimizing proxy rewards frequently leads to reward hacking: the optimized reward function ceases to be a good proxy, and the resulting policy performs poorly with respect to the unspecified true reward. Principled solutions to reward hacking have been impeded by the lack of a good definition for the problem. To address this, we introduce a definition of reward hacking based on the correlation between proxy and true rewards for states and actions seen by a "base policy" that breaks down under optimization. We show that this definition captures reward hacking behavior across several realistic settings, including in reinforcement learning from human feedback (RLHF). We then show theoretically that regularization to the base policy can effectively prevent reward hacking. While current RLHF approaches apply a KL penalty between the action distributions of policies, our theory suggests that it is more effective to regularize using the $\chi^2$ divergence between the policies' occupancy measures. We intuitively show why this type of regularization is superior and demonstrate that it better mitigates reward hacking in practice across four realistic domains, including RLHF for LLMs. Our code is available at https://github.com/cassidylaidlaw/orpo.

This report describes and synthesizes implementation determinants and strategies to promote uptake and sustained implementation of comprehensive school mental health and trauma-sensitive practices in schools. The present synthesis of studies and reports emphasizes use of relevant and efficient practices with empirical support at the state, district, and school levels to promote comprehensive school mental health and trauma-sensitive practices.

Youth mental health concerns are on the rise and can have serious implications for student well-being and success (Clayborne et al., 2019). Consequently, more educators and mental health professionals are identifying mental health as an important student need (American Academy of Pediatrics, 2021). This report summarizes the key principles underlying comprehensive school mental health and trauma sensitive schools. The present synthesis of studies and reports emphasizes core features, key principles, and associated core components. [This report was co-produced by the Wisconsin Evaluation Collaborative and originally prepared for the Wisconsin Department of Public Instruction (DPI).]

We give a model of how to infer natural language rules by doing experiments. The model integrates Large Language Models (LLMs) with Monte Carlo algorithms for probabilistic inference, interleaving online belief updates with experiment design under information-theoretic criteria. We conduct a human-model comparison on a Zendo-style task, finding that a critical ingredient for modeling the human data is to assume that humans also consider fuzzy, probabilistic rules, in addition to assuming that humans perform approximately-Bayesian belief updates. We also compare with recent algorithms for using LLMs to generate and revise hypotheses, finding that our online inference method yields higher accuracy at recovering the true underlying rule, and provides better support for designing optimal experiments.

The US higher education system concentrates the production of science and scientists within a few institutions. This has implications for minoritized scholars and the topics with which they are disproportionately associated. This paper examines topical alignment between institutions and authors of varying intersectional identities, and the relationship with prestige and scientific impact. We observe a Howard-Harvard effect, in which the topical profile of minoritized scholars are amplified in mission-driven institutions and decreased in prestigious institutions. Results demonstrate a consistent pattern of inequality in topics and research impact. Specifically, we observe statistically significant differences between minoritized scholars and White men in citations and journal impact. The aggregate research profile of prestigious US universities is highly correlated with the research profile of White men, and highly negatively correlated with the research profile of minoritized women. Furthermore, authors affiliated with more prestigious institutions are associated with increasing inequalities in both citations and journal impact. Academic institutions and funders are called to create policies to mitigate the systemic barriers that prevent the United States from achieving a fully robust scientific ecosystem.

An algorithm for efficiently calculating the expected size of single-seed cascade dynamics on networks is proposed and tested. The expected size is a time-dependent quantity and so enables the identification of nodes who are the most influential early or late in the spreading process. The measure is accurate for both critical and subcritical dynamic regimes and so generalises the nonbacktracking centrality that was previously shown to successfully identify the most influential single spreaders in a model of critical epidemics on networks., Comment: 16 pages, 5 figures

This paper develops a theory of how tradeoffs govern comparison complexity, and how this complexity generates systematic mistakes in choice. In our model, options are easier to compare when they involve less pronounced tradeoffs, in particular when they are 1) more similar feature-by-feature and 2) closer to dominance. These two postulates yield tractable measures of comparison complexity in the domains of multiattribute, lottery, and intertemporal choice. We show how our model organizes a range of behavioral regularities in choice and valuation, such as context effects, preference reversals, and apparent probability weighting and hyperbolic discounting. We test our model experimentally by varying the strength and nature of tradeoffs. First, we show that our complexity measures predict choice errors, choice inconsistency, and cognitive uncertainty in binary choice data across all three domains. Second, we document that manipulations of comparison complexity can reverse classic behavioral regularities, in line with the predictions of the theory. We apply our theory to study strategic obfuscation by firms in a pricing game.

This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consists of Ultra, Pro, and Nano sizes, suitable for applications ranging from complex reasoning tasks to on-device memory-constrained use-cases. Evaluation on a broad range of benchmarks shows that our most-capable Gemini Ultra model advances the state of the art in 30 of 32 of these benchmarks - notably being the first model to achieve human-expert performance on the well-studied exam benchmark MMLU, and improving the state of the art in every one of the 20 multimodal benchmarks we examined. We believe that the new capabilities of the Gemini family in cross-modal reasoning and language understanding will enable a wide variety of use cases. We discuss our approach toward post-training and deploying Gemini models responsibly to users through services including Gemini, Gemini Advanced, Google AI Studio, and Cloud Vertex AI.

Inverse reinforcement learning (IRL) is computationally challenging, with common approaches requiring the solution of multiple reinforcement learning (RL) sub-problems. This work motivates the use of potential-based reward shaping to reduce the computational burden of each RL sub-problem. This work serves as a proof-of-concept and we hope will inspire future developments towards computationally efficient IRL.