Showing 1–50 of 583 results for author: Smith, A

Cyber-Physical Systems for Accessibility and Ability Augmentation: Bridging Diverse Communities

Authors: Shuchang Xu, Riku Arakawa, Mina Huh, Nandi Zhang, Tianyu Zhang, Wazeer Zulfikar, Ruei-Che Chang, Yotam Sechayk, Huamin Qu, Amy Pavel, Franklin Mingzhe Li, Yukang Yan, Brian A. Smith, Pattie Maes

Abstract: The powerful convergence of wearables, robotics, extended reality, and smart environments is expanding the design space for cyber-physical systems (CPS) that support and augment human abilities in daily life. By sensing real-world contexts, modeling user needs, and providing situated assistance, these systems can improve accessibility for people with disabilities while enhancing broader human abil… ▽ More The powerful convergence of wearables, robotics, extended reality, and smart environments is expanding the design space for cyber-physical systems (CPS) that support and augment human abilities in daily life. By sensing real-world contexts, modeling user needs, and providing situated assistance, these systems can improve accessibility for people with disabilities while enhancing broader human abilities such as perception, memory, learning, and mobility. However, realizing this potential requires addressing key challenges in context sensing, user modeling, adaptive interaction, privacy, and evaluation to ensure that CPS are reliable and effective in real-world contexts. This workshop will bring together researchers and practitioners across HCI, AI, wearables, robotics, XR, smart environments, accessibility, and ability augmentation to examine shared strategies and challenges for designing accessibility- and ability-centered CPS. Through panel discussions, interactive demos, and mixed-group design activities, participants will identify recurring design principles, technical challenges, and future directions for CPS that support and augment human abilities in real-world settings. For details, please visit: https://cps4all.github.io. △ Less

Submitted 19 August, 2026; originally announced August 2026.

Comments: UIST 26 Workshop

Longitudinal Relational Publics and their Discursive Overlap with Issue Publics

Authors: Alyssa Hasegawa Smith, Judith Gilsbach, Ahana Bhattacharya, Holliday Sims, Kenneth Joseph

Abstract: Online discussions of political issues do not always happen in places explicitly dedicated to political talk; they also arise in online spaces focused on at least nominally apolitical interests, identities, and/or places. Whatever one's normative view of politics entering these ``online third spaces,'' understanding who brings political issues into them, and when, requires studying these spaces at… ▽ More Online discussions of political issues do not always happen in places explicitly dedicated to political talk; they also arise in online spaces focused on at least nominally apolitical interests, identities, and/or places. Whatever one's normative view of politics entering these ``online third spaces,'' understanding who brings political issues into them, and when, requires studying these spaces at scale. In turn, studying these spaces at scale requires a construct that captures both who is speaking and who is listening, and that holds up over time. Building on Bruns' distinction between participant-centered personal publics and post-centered issue publics, we introduce the longitudinal relational networked public (or, simply, the longitudinal public): the coupling of discourse produced by a socially connected set of creators with the durable attention their shared audience gives it. The longitudinal public departs from related relational constructs in three ways: it is anchored in the attention patterns of a non-elite, population-level audience; it treats within-public structure as an object of analysis rather than assuming homogeneity; and it incorporates the audience as a force that shapes creator discourse. In a case study, we identify 150 longitudinal publics from the following ties of a panel of Twitter/X users matched to U.S. voter records, then measure their discursive overlap with the electoral politics and Black Lives Matter issue publics across 2020, a period spanning the murder of George Floyd and the general election. We find that the spaces that best fit the idea of a third space have the most politically heterogeneous audiences, and thus the most potential room for cross-partisan talk. This result, among several others, shows how a relational, audience-aware construct can reveal where and through whom political talk enters everyday online life. △ Less

Submitted 18 August, 2026; originally announced August 2026.

On the Pseudo-Mixing of Kac's Walk

Authors: Natesh S. Pillai, Aaron Smith, Vinod Vaikuntanathan

Abstract: Motivated by a conjecture of Vaikuntanathan and Zamir, we study the pseudo-mixing of Kac's walk on $\mathrm{SO}(n)$: whether short trajectories are indistinguishable from Haar measure by low-complexity tests. We prove that the first $k$ columns mix in Wasserstein distance in $O(n(k+\log n)\log n)$ steps for fixed accuracy, resolving a conjecture of Oliveira. Combining this with a representation-th… ▽ More Motivated by a conjecture of Vaikuntanathan and Zamir, we study the pseudo-mixing of Kac's walk on $\mathrm{SO}(n)$: whether short trajectories are indistinguishable from Haar measure by low-complexity tests. We prove that the first $k$ columns mix in Wasserstein distance in $O(n(k+\log n)\log n)$ steps for fixed accuracy, resolving a conjecture of Oliveira. Combining this with a representation-theoretic variance bound, we show that if $T=ω(nk(k+\log n)\log n)$, then every degree-$k$ polynomial normalized to have unit Haar variance has expectation under the $T$-step law within $o(1)$ of its Haar expectation. As an application, we show that this pseudo-mixing estimate can be used to prove the effectiveness of a fast Johnson--Lindenstrauss transform with the usual target dimension. △ Less

Submitted 18 August, 2026; originally announced August 2026.

Comments: 48 pages

MSC Class: 60J05

H2H Music Improv: A Communication Model and Audio-Visual Dataset for Music Improvisation

Authors: Aleksandra Teng Ma, Anthony Cammarota, Jiayi Wang, Alexandria Smith, Cheng-Zhi Anna Huang, Jeffrey Albert, Alexander Lerch

Abstract: Current real-time AI improvisation systems lack the communication awareness human musicians rely on: rather than treating communication as a foundational algorithm design concern, most systems layer interaction strategies post-hoc onto generative algorithms through explicit controls and predefined modes. This gap persists in part because no formalized, machine-readable communication model with mus… ▽ More Current real-time AI improvisation systems lack the communication awareness human musicians rely on: rather than treating communication as a foundational algorithm design concern, most systems layer interaction strategies post-hoc onto generative algorithms through explicit controls and predefined modes. This gap persists in part because no formalized, machine-readable communication model with musicians exists. To address this, we study how expert musicians communicate in free (non-idiomatic) improvisation, unconstrained by prior discussion or agreement. Through a collaborative co-design process with expert improvisers, we derive a communication model that (1) captures how free improvisers negotiate musical ideas and enter stable musical spaces, and (2) is formalized as a machine-readable annotation scheme. We further present the H2H (Human-to-Human) Music Improvisation dataset: six hours of audio-visual expert duo improvisations with clean per-player stems and per-player annotations of both their own intentions and their perception of their partner's intentions. To our knowledge, this is the first such dataset for free improvisation. Together, the communication model and the dataset offer a new lens and resource for studying musician communication and may in future inform the design of AI musical partners that communicate by design. △ Less

Submitted 14 August, 2026; originally announced August 2026.

Comments: Published in the Proceedings of the Society for Music Information Retrieval Conference (ISMIR) 2026

A foundation-model approach to pediatric headache classification from rs-fMRI

Authors: Guilherme S. Imai Aldeia, Clara Moon, Julie Shulman, Navil Sethna, Allison Smith, Alyssa Lebel, William G. La Cava, Scott Holmes

Abstract: Headache is the most common neurological disorder in children and substantially affects quality of life. We investigated whether resting-state functional MRI (rs-fMRI) can support pediatric headache classification using machine learning. We encoded rs-fMRI data using NeuroSTORM, a recent foundation model, and fine-tuned it to distinguish healthy controls from children with headache and subsequentl… ▽ More Headache is the most common neurological disorder in children and substantially affects quality of life. We investigated whether resting-state functional MRI (rs-fMRI) can support pediatric headache classification using machine learning. We encoded rs-fMRI data using NeuroSTORM, a recent foundation model, and fine-tuned it to distinguish healthy controls from children with headache and subsequently classify headache subtypes. We compared NeuroSTORM with a standard neuroscience approach using functional-connectivity (FC) matrices derived from brain activity as predictors. Using 189 rs-fMRI scans from 110 individuals collected across two visits (prevalence of any headache: 74%), NeuroSTORM achieved an area under the receiver operating characteristic curve (AUROC) of 0.82 (95% CI, 0.82-0.82) and an area under the precision-recall curve (AUPRC) of 0.93 (95% CI, 0.93-0.94) for discriminating headache from non-headache. In contrast, models trained on FC matrices showed lower performance (AUROC, 0.67 [95% CI, 0.67-0.67]; AUPRC, 0.85 [95% CI, 0.85-0.85]). In multiclass classification of healthy controls, chronic migraine, and non-chronic headaches (e.g., post-viral headache, new daily persistent headache, post-traumatic headache), NeuroSTORM achieved a macro-AUROC of 0.69 (95% CI, 0.68-0.69). Results suggest that the approach can distinguish chronic migraine but has difficulty differentiating other headache subtypes from chronic migraine. Overall, under limited-data conditions, NeuroSTORM appears to capture latent rs-fMRI representations that transfer to headache-related tasks without relying on FC features. These findings provide proof of concept for fMRI-based prediction of pediatric headache and highlight potential future utility for subtype identification and individualized treatment strategies. △ Less

Submitted 7 August, 2026; originally announced August 2026.

Comments: 22 pages, 6 figures. In Proceedings of Machine Learning Research, Volume 340, 2026 (Machine Learning for Healthcare Conference)

MameLoshnLM: Yiddish Language Model and Evaluation Benchmark

Authors: Uri Katz, Omer Goldman, Tomasz Limisiewicz, Reut Tsarfaty, Noah A. Smith

Abstract: We present MameLoshnLM, the first open-source 8B-parameter language model built specifically for Yiddish. Despite Yiddish's rich textual tradition, its limited digital presence and the scarcity of reliable evaluation resources have constrained progress in Yiddish language modeling. Existing multilingual corpora and benchmarks are often poor proxies for the language, containing substantial amounts… ▽ More We present MameLoshnLM, the first open-source 8B-parameter language model built specifically for Yiddish. Despite Yiddish's rich textual tradition, its limited digital presence and the scarcity of reliable evaluation resources have constrained progress in Yiddish language modeling. Existing multilingual corpora and benchmarks are often poor proxies for the language, containing substantial amounts of noisy, machine-translated, and misclassified text. We address these gaps by introducing Oytser, a high-quality Yiddish pretraining corpus that combines contemporary web-native sources with literary materials, and Kashes, a multi-task benchmark spanning translation, linguistic analysis, information extraction, and language understanding. Using these resources, we continue pretraining Llama 3.1 8B to obtain MameLoshnLM. Across the tasks in the benchmark, MameLoshnLM outperforms open baselines of similar scale. Our analyses show that these gains are not only quantitative: relative to general-purpose multilingual models, MameLoshnLM better captures language-defining lexical and morphological patterns, pointing to a broader failure mode of noisy web-scale multilingual data for low-resource languages. Our results provide both a foundation for Yiddish NLP and a practical template for language model development in historically rich but digitally underrepresented languages. △ Less

Submitted 6 August, 2026; originally announced August 2026.

Comments: Accepted at the Conference on Language Modeling (COLM) 2026

Investigating Click Behaviors On Google Search Result Pages That Produce an AI Overview

Authors: Athena Chapekis, Anna Lieb, Sono Shah, Aaron Smith

Abstract: In 2024, Google introduced "AI Overviews," a feature that displays an AI-generated result summary at the top of many Google search pages. This study investigates the role of AI in Google search using one month of web browsing data from a representative panel of 900 U.S. adults. Our analysis of the panelists' Google searches sheds light on AI Overviews, when they appear in Google search results, an… ▽ More In 2024, Google introduced "AI Overviews," a feature that displays an AI-generated result summary at the top of many Google search pages. This study investigates the role of AI in Google search using one month of web browsing data from a representative panel of 900 U.S. adults. Our analysis of the panelists' Google searches sheds light on AI Overviews, when they appear in Google search results, and what user behaviors are associated with AI Overviews. We identify several attributes that make a search query more likely to generate an AI Overview, including the length of a query, whether the query begins with a question word, and whether the query contains both a noun and verb. When it comes to user behavior, we find that clicks to sources cited in AI Overviews are very rare, occurring in only about 1% of visits to AI Overviews. We also find that AI Overviews are associated with fewer clicks and higher rates of ending browsing sessions. Importantly, results from a mixed-effects logistic regression model indicate that these associations hold when controlling for random effects by panelist and query attributes that make AI Overviews more likely to appear. △ Less

Submitted 5 August, 2026; originally announced August 2026.

Comments: Presented at IC2S2 2026

A Dual Evaluation for Music Transcription

Authors: Ping Wang, Guang Yang, Nazif Can Tamer, Victoria Ebert, Noah A. Smith

Abstract: Automatic music transcription systems produce sheet music that can be read and played back. We argue that these two targets call for complementary evaluations of notation similarity to a reference score and playback similarity to the original performance, respectively. Our study considers notation similarity metrics from the optical music recognition literature and a wide range of playback-similar… ▽ More Automatic music transcription systems produce sheet music that can be read and played back. We argue that these two targets call for complementary evaluations of notation similarity to a reference score and playback similarity to the original performance, respectively. Our study considers notation similarity metrics from the optical music recognition literature and a wide range of playback-similarity methods validated through a listening study across over 100 participants and 230 piano recordings covering 23 works, 30 performers, and six composers. We find, fortuitously, that the playback similarity metric that correlates best with human judgments, CLEWS, is also the cheapest to run. We also find that the two evaluation dimensions favor different systems among a collection of 24 pipelines formed by pairing eight audio-to-MIDI models with three MIDI-to-score converters, with the latter component systematically determining the favored objective. The complementarity between metrics also holds when adding to the pool Rubato, a new end-to-end system that offers substantially improved notation similarity while remaining competitive, though not the best, on playback similarity. △ Less

Submitted 6 August, 2026; v1 submitted 5 August, 2026; originally announced August 2026.

A large-scale corpus of religious radio broadcast transcripts from webstream recordings in the United States

Authors: Samuel Bestvater, Athena Chapekis, Skyler Seets, Anna Lieb, Sono Shah, Aaron Smith

Abstract: Religious radio is a widespread but understudied form of mass communication in the United States, and content-level analysis of it has been constrained by the absence of large-scale transcript data. This Data Descriptor presents a corpus of transcribed English-language religious radio broadcasts captured from live webstreams over a one-month period in July 2025. Fifteen-minute segments were record… ▽ More Religious radio is a widespread but understudied form of mass communication in the United States, and content-level analysis of it has been constrained by the absence of large-scale transcript data. This Data Descriptor presents a corpus of transcribed English-language religious radio broadcasts captured from live webstreams over a one-month period in July 2025. Fifteen-minute segments were recorded on a rolling schedule from 785 distinct streams, which together rebroadcast the signals of more than two thousand AM and FM stations, yielding over 700,000 recordings and more than 60 million diarized lines of speech. Each recording was transcribed and speaker-diarized with an automated pipeline, and segmented and labeled by programming format and topic using a large language model. The corpus is organized as linked tables of stream metadata, recording metadata, and transcript lines. It supports descriptive study of religious broadcasting across regions and traditions, analysis of how social and political issues are discussed in religious media, and speech-processing research in an underrepresented domain. △ Less

Submitted 28 July, 2026; originally announced July 2026.

Comments: Presented at IC2S2 2026

Sonic Stage: Auto-Generating Interactive Spatial Soundscapes to Facilitate Dialogue Video Comprehension for Blind Viewers

Authors: Shuchang Xu, Xiaofu Jin, Gaurav Jain, Wenshuo Zhang, Huamin Qu, Brian A. Smith, Yukang Yan

Abstract: Audio description (AD) makes film and television accessible to blind and low-vision (BLV) audiences by narrating characters' actions. However, in scenes with lots of dialogue, AD often omits important actions because it is constrained not to overlap with speech. It is not yet known how to convey characters' actions during dialogue. We present Sonic Stage, a system that transforms dialogue videos i… ▽ More Audio description (AD) makes film and television accessible to blind and low-vision (BLV) audiences by narrating characters' actions. However, in scenes with lots of dialogue, AD often omits important actions because it is constrained not to overlap with speech. It is not yet known how to convey characters' actions during dialogue. We present Sonic Stage, a system that transforms dialogue videos into interactive spatial soundscapes, enabling BLV audiences to intuitively understand characters' actions and movements through immersive auditory cues. Sonic Stage conveys essential visual information during dialogue through three auditory techniques: (1) spatialized dialogue to represent spatial layout, (2) diegetic sound to convey character actions, and (3) interactive descriptions to provide context-specific visual details. Evaluation with 12 BLV viewers showed that Sonic Stage significantly improved video comprehension, spatial presence, and narrative engagement. We highlight opportunities for enhancing video accessibility across diverse genres through immersive, interactive audio representations. △ Less

Submitted 29 July, 2026; v1 submitted 22 July, 2026; originally announced July 2026.

Comments: accepted to UIST 2026

Pretraining Data Can Be Poisoned through Computational Propaganda

Authors: Victoria Graf, Hannaneh Hajishirzi, Noah A. Smith, David Kohlbrenner, Kyle Lo

Abstract: Poisoning pretraining data can introduce harmful behaviors to LMs that are difficult to detect and mitigate. Prior work on poisoning pretraining data has largely exploited established data sources such as Wikipedia, which do not represent the large scale and heterogeneity typical of pretraining corpora, and has ignored the interaction between poisoned data and data curation pipelines. We demonstra… ▽ More Poisoning pretraining data can introduce harmful behaviors to LMs that are difficult to detect and mitigate. Prior work on poisoning pretraining data has largely exploited established data sources such as Wikipedia, which do not represent the large scale and heterogeneity typical of pretraining corpora, and has ignored the interaction between poisoned data and data curation pipelines. We demonstrate that poisoning attacks on pretraining data are feasible beyond this limited setting through an existing web-scale content injection mechanism: public discussion interfaces. Additionally, to measure whether malicious content is included after web crawling and data curation, we introduce HalfLife, a novel analysis for estimating adversarial content inclusion in web-crawl based LM training data. We use HalfLife to explore the feasibility of poisoning pretraining corpora at web scale through open discussion interfaces. Our analysis demonstrates the importance of estimating whether poison injections are included in pretraining data, and establishes third-party webpage content as a possible vector for attacking language model pretraining. △ Less

Submitted 16 July, 2026; originally announced July 2026.

Extending Xenakis: From Architectural Geometry to Sonification of the Philips Pavilion

Authors: Changda Ma, Sunshiyu Wang, Canting Zhu, Alexandria Smith

Abstract: Architecture and music have been linked through proportion and temporal structure, yet architectural geometry is rarely viewed as a source of generative music. Revisiting Xenakis' one-directional transformation from string glissandi in Metastaseis to the ruled surfaces of the Philips Pavilion, we invert this workflow and sonify the completed Pavilion as a temporal composition. We reconstruct the P… ▽ More Architecture and music have been linked through proportion and temporal structure, yet architectural geometry is rarely viewed as a source of generative music. Revisiting Xenakis' one-directional transformation from string glissandi in Metastaseis to the ruled surfaces of the Philips Pavilion, we invert this workflow and sonify the completed Pavilion as a temporal composition. We reconstruct the Pavilion as nine ruled surfaces, extract their governing ruling lines, and subdivide each surface into structural lines and spatial sampling points. Four evenly spaced ruling lines per surface generate continuous string glissandi, while 3357 sampled points develop five density-based energy blocks and a sparse brass and woodwind subsequence. Implemented in Python, the system produces MIDI rendered in Ableton Live, accompanied by a real-time 3D visualization that reveals architectural motion, stasis, and structural contrast through sound and image. In general, this work paves the way for the transfer of architectural geometry as a performable musical structure, extending Xenakis's architectural and musical thinking to sonification and interactive music practice. △ Less

Submitted 6 July, 2026; originally announced July 2026.

Comments: Accepted to the International Computer Music Conference (ICMC) 2026

Journal ref: Proceedings of the 51st International Computer Music Conference (ICMC 2026), Hamburg, Germany, 2026

LEGATO 2: Toward Multimodal Sheet Music Recognition and Understanding

Authors: Guang Yang, Brian Siyuan Zheng, Victoria Ebert, Noah A. Smith

Abstract: We propose a novel pipeline, Legato 2, for extracting symbolic notation and semantic knowledge from images of sheet music. Legato 2 features the first large-scale neural model for optical music recognition (OMR) to operate sequentially on a system-by-system basis, following the horizontal lines of notation as they are read on the page, rather than treating the page as an undifferentiated image, en… ▽ More We propose a novel pipeline, Legato 2, for extracting symbolic notation and semantic knowledge from images of sheet music. Legato 2 features the first large-scale neural model for optical music recognition (OMR) to operate sequentially on a system-by-system basis, following the horizontal lines of notation as they are read on the page, rather than treating the page as an undifferentiated image, enabling better scaling to arbitrarily long inputs. It is also the first OMR model capable of generating symbolic transcriptions that include embedded textual content, such as titles and annotations. The pipeline combines system-level segmentation with an autoregressive vision-LM to capture both local notation details and score structure. Across multiple datasets, Legato 2 consistently outperforms prior state of the art. We also show that symbolic transcriptions complement visual inputs for frontier language models, improving their interpretation of dense musical documents. Legato 2 establishes new state-of-the-art performance in both OMR and downstream sheet music understanding. △ Less

Submitted 6 July, 2026; originally announced July 2026.

Comments: 23 pages. Equal contribution: Guang Yang and Brian Siyuan Zheng

Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models

Authors: Hongyu Li, Wanjia Fu, Xiaoyan Cong, Zekun Li, Binghao Huang, Hanxiao Jiang, Xintong He, Yiqing Liang, Rao Fu, Tao Lu, Srinath Sridhar, Kevin A. Smith, George Konidaris, Yunzhu Li

Abstract: Predicting object dynamics (i.e., world modeling) is a fundamental challenge for robotic manipulation, and modeling deformable objects presents a particularly difficult case due to their high-dimensional state spaces and complex material properties. While current world models approach this through two distinct paradigms: learning the dynamics over the 2D pixel space or more explicit 3D geometric s… ▽ More Predicting object dynamics (i.e., world modeling) is a fundamental challenge for robotic manipulation, and modeling deformable objects presents a particularly difficult case due to their high-dimensional state spaces and complex material properties. While current world models approach this through two distinct paradigms: learning the dynamics over the 2D pixel space or more explicit 3D geometric space. A systematic understanding of their relative strengths and limitations remains elusive due to the lack of diverse, large-scale real-world data. To address this, we present Deform360, a large-scale visuotactile dataset featuring 198 daily-life objects, 1,980 interaction sequences, and over 215 hours of observations from 41 surround-view cameras and bimanual tactile grippers to capture both global motion and contact-induced local deformations. Leveraging a novel markerless visuotactile 3D tracking pipeline to extract dense geometry and motion, we systematically evaluate current state-of-the-art world models, comparing 2D video models against 3D particle models. Finally, we provide a preliminary demonstration indicating the real-world applicability of our dataset by performing robot planning tasks on deformable objects. Our analysis reveals key insights into the trade-offs between structural priors and scalability, providing a solid benchmark for future research in generalizable deformable object-centric world modeling. Project website: https://deform360.lhy.xyz △ Less

Submitted 6 July, 2026; originally announced July 2026.

Comments: Accepted by ECCV 2026

Decision-Value Attribution in Predict-then-Optimize Systems

Authors: Konstantinos Ziliaskopoulos, Alexander Vinel, Alice E. Smith

Abstract: Predictive models are increasingly embedded in operational decision-making, yet standard explanation methods typically explain forecasts rather than the decisions those forecasts induce. This distinction is important in predict-then-optimize systems: large forecast changes may leave the optimizer's action unchanged, while small changes can alter the selected decision and its realized value. We pro… ▽ More Predictive models are increasingly embedded in operational decision-making, yet standard explanation methods typically explain forecasts rather than the decisions those forecasts induce. This distinction is important in predict-then-optimize systems: large forecast changes may leave the optimizer's action unchanged, while small changes can alter the selected decision and its realized value. We propose Decision Value Attribution (DVA), a Shapley-based framework for attributing the value of a fixed prediction--optimization pipeline. The framework defines cooperative games whose payoff is the downstream decision value, allowing the players to be information sources, optimization or design parameters, or both. We present three variants: InfoDVA attributes value to features, DesignDVA attributes value to operational configurations, and Decision-Value Interactions (DVI) quantifies how information and design jointly create value. We further distinguish post-DVA, which evaluates decisions using realized outcomes, from pre-DVA, which evaluates decisions under the model's full prediction. This separation turns attribution into a decision-level diagnostic of whether the model's operational beliefs align with realized performance. The resulting attributions are expressed in the units of the operational objective and decompose the gain or loss relative to a baseline. Case studies in electricity storage arbitrage and emergency medical service coverage show that predictive explanations can be poor proxies for operational value, that DVA can guide targeted information-control interventions, and that optimization configurations determine when predictive information is decision-relevant. △ Less

Submitted 29 June, 2026; originally announced June 2026.

Compute-Optimal Network Design for Echocardiography Myocardial Segmentation and Perfusion Quantification using Neural Scaling Laws

Authors: Clara Rodrigo González, Matthieu Toulemonde, Lasha Gvinianidze, Cameron A. B. Smith, Oscar Bates, Roxy Senior, Fu Siong Ng, Meng-Xing Tang

Abstract: Myocardial perfusion quantification using contrast-enhanced ultrasound offers a bedside non-ionizing alternative to nuclear imaging modalities. However, its clinical adoption is hindered by time-consuming manual labelling. Automated segmentation has proved challenging due to a paucity of in-domain training data. Adapting strategies currently used to optimise large language models for large dataset… ▽ More Myocardial perfusion quantification using contrast-enhanced ultrasound offers a bedside non-ionizing alternative to nuclear imaging modalities. However, its clinical adoption is hindered by time-consuming manual labelling. Automated segmentation has proved challenging due to a paucity of in-domain training data. Adapting strategies currently used to optimise large language models for large datasets, we apply neural scaling laws to predict network performance for myocardial segmentation. We extrapolate performance on subsets of the data to determine optimal network size on the CAMUS echocardiography dataset and a 25-patient contrast-enhanced ultrasound (CEUS) dataset. Finally, we validate the clinical utility of our models by comparing the final myocardial perfusion parameters with those obtained by a senior cardiologist. Extrapolation based on the scaling law is predictive of test loss at the full dataset size, allowing us to select two networks that obtained state-of-the-art performance on CAMUS with a 240-fold reduction in parameter count. We observe the gradient of the scaling law transfers from CAMUS to the CEUS dataset with a bias in the predicted losses. The automatically segmented masks perform equivalently to a senior cardiologist in myocardial perfusion quantification. These results establish neural scaling laws as a practical tool for data-driven compute-optimal model design for small imaging datasets. △ Less

Submitted 4 June, 2026; originally announced June 2026.

Comments: 15 pages, 4 figures, 5 tables, journal

Closed-Loop Molecular Design with Calibrated Deference

Authors: Newman Cheng, Gordon Broadbent IV, Jason Dong, Syed Mohammed Ali Hussaini, Farman Ullah, Morris Sharp, Gabrielle Barnes, Nanlin Guo, Deyu Zou, Karin Strauss, William Chappell, David G. Kwabi, Bichlien H. Nguyen, Jake A. Smith

Abstract: We present Cognitive Loop via In-Situ Optimization (CLIO), an agent that couples a continuously-updated belief-state graph with a recursive plan-then-act loop. The result is a reasoning agent that can contribute something qualitatively different, which we term \emph{calibrated deference}: the capacity to recognize when its own tools or assumptions are failing, to adapt its strategy in response, an… ▽ More We present Cognitive Loop via In-Situ Optimization (CLIO), an agent that couples a continuously-updated belief-state graph with a recursive plan-then-act loop. The result is a reasoning agent that can contribute something qualitatively different, which we term \emph{calibrated deference}: the capacity to recognize when its own tools or assumptions are failing, to adapt its strategy in response, and to generate mechanistic hypotheses that guide experimental revision. We tested CLIO in a closed-loop human-AI campaign to design an aqueous organic redox flow battery (AORFB) negolyte, with CLIO leading proposal and interpretation in close partnership with chemists who synthesized, characterized, and weighed in on design choices. Across 17 candidates over three rounds, CLIO converged on a top phosphonate candidate; characterization confirmed a 130~mV improvement in redox potential over the literature baseline. Characterization then revealed unexpectedly poor electrochemical reversibility -- a regression no property predictor had flagged. CLIO generated competing mechanistic hypotheses, prioritized discriminating diagnostics, traced the failure to phosphonate-potassium ion pairing, and prescribed a sulfonate replacement. The resulting compound showed substantially improved electrochemical reversibility and maintained a 90~mV improvement in redox potential, closing the design-make-test-redesign loop. △ Less

Submitted 27 May, 2026; originally announced June 2026.

Rubato: Transcribing Piano Music with Timestamps

Authors: Nazif Can Tamer, Victoria Ebert, Guang Yang, Noah A. Smith

Abstract: We consider the conversion of musical recordings into human-readable sheet music annotated with timestamps. Such output lets a listener clearly visualize rubato (temporally expressive playing), a learner diagnose ensemble precision and timing choices against the written music, and a musicology scholar compare performance styles across recordings of the same work. We introduce (1) a prompt-conditio… ▽ More We consider the conversion of musical recordings into human-readable sheet music annotated with timestamps. Such output lets a listener clearly visualize rubato (temporally expressive playing), a learner diagnose ensemble precision and timing choices against the written music, and a musicology scholar compare performance styles across recordings of the same work. We introduce (1) a prompt-conditioned encoder-decoder model, named Rubato, trained to output (2) a new textual representation for polyphonic music, named InterMo, which we designed for compatibility with sequence-to-sequence training. Our experiments demonstrate that Rubato produces timestamped piano sheet music from audio with higher notational accuracy than the best existing approaches, which are based on cascades. We find that even if the cascade is given ground-truth MIDI instead of audio, Rubato performs better, suggesting that the ceiling of existing approaches is primarily representational, not acoustic. Further, because Rubato is trained on several related tasks (with prompts), it competes with or outperforms the best single-task systems on related but simpler tasks like MIDI note grounding and beat/downbeat detection. A demo is available at https://nctamer.github.io/rubato-transcription . △ Less

Submitted 22 May, 2026; originally announced May 2026.

Comments: 18 pages, 7 figures, 5 tables

Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety

Authors: Piercosma Bisconti, Matteo Prandi, Federico Pierucci, Federico Sartore, Enrico Panai, Laura Caroli, Yue Zhu, Adam Leon Smith, Luca Nannini, Marcello Galisai, Susanna Cifani, Francesco Giarrusso, Marcantonio Bracale Syrnikov, Daniele Nardi

Abstract: Background. Traditional safety benchmarks for language models evaluate generated text: whether a model outputs toxic language, reproduces bias, or follows harmful instructions. When models are deployed as agents, the safety-relevant object shifts from what the system says to what it does within an environment, and evaluating model responses under prompting is no longer sufficient to address the sa… ▽ More Background. Traditional safety benchmarks for language models evaluate generated text: whether a model outputs toxic language, reproduces bias, or follows harmful instructions. When models are deployed as agents, the safety-relevant object shifts from what the system says to what it does within an environment, and evaluating model responses under prompting is no longer sufficient to address the safety challenges posed by artificial intelligence. Recent developments have seen the rise of benchmarks that evaluate large language models as agents. We contribute to this strand of research. Approach. We introduce Boiling the Frog, a benchmark that evaluates whether tool-using AI models deployed in corporate and office settings are susceptible to incremental attacks. Each scenario begins with benign workspace edits and later introduces a risk-bearing request. The benchmark focuses on stateful multi-turn evaluation: chains expose a persistent workspace, place the risk-bearing payload at controlled positions in the turn sequence, and score whether the resulting artifact state becomes unsafe. Scenarios are organized through a three-level operational risk taxonomy grounded in the Boiling the Frog risks, the AI Act Annex I and Annex III high-risk contexts, and EU AI Act's Code of Practice on General-Purpose AI (GPAI). Results. Across a nine-model panel, aggregate strict attack success rate (ASR) is 44.4%. Model-level ASR ranges from 20.5% for Claude Haiku 4.5 to 92.9% for Gemini 3.1 Flash Lite, with Seed 2.0 Lite also above 80%. Average chain category-level ASR reaches 93.3% for Code of Practice loss-of-control scenarios. △ Less

Submitted 22 May, 2026; v1 submitted 21 May, 2026; originally announced May 2026.

Robust Statistical Estimators with Bounded Empirical Sensitivity

Authors: Valentio Iverson, Gautam Kamath, Argyris Mouzakis, Adam Smith

Abstract: We introduce a new measure of robustness for statistical estimators, which we call \emph{empirical sensitivity}. An estimator $\hat θ$ has bounded empirical sensitivity if, with high probability over a dataset $X = (X_1, \dots, X_n) \sim \mathcal{D}^{\otimes n}$, for any dataset $Y$ obtained by modifying at most $ηn$ points in $X$, we have that $\hat θ(Y)$ is close to $\hat θ(X)$. We study bound… ▽ More We introduce a new measure of robustness for statistical estimators, which we call \emph{empirical sensitivity}. An estimator $\hat θ$ has bounded empirical sensitivity if, with high probability over a dataset $X = (X_1, \dots, X_n) \sim \mathcal{D}^{\otimes n}$, for any dataset $Y$ obtained by modifying at most $ηn$ points in $X$, we have that $\hat θ(Y)$ is close to $\hat θ(X)$. We study bounds on this quantity for the prototypical problem of Gaussian mean estimation. We prove new lower bounds, showing that for any estimator $\hat μ$ which achieves an optimal $\ell_2$-error bound of $O\left(\sqrt{d/n}\right)$, the empirical sensitivity is at least $Ω\left(η+ \sqrt{ηd/n}\right)$. The two terms arise due to obstructions on the mean and variance (via an Efron-Stein argument) of such an estimator. We show that this bound is tight up to logarithmic factors, by employing recent results for robust empirical mean estimation. △ Less

Submitted 20 May, 2026; originally announced May 2026.

Music of Changing Lines: Toward a Culturally Situated Approach to the I-Ching

Authors: Ling Qi, Aleksandra Teng Ma, Alexandria Smith

Abstract: The I-Ching is one of the most influential texts in Chinese intellectual history, integrating divination, cosmology, and ethical reflection. While Western experimental music, most notably John Cage, has drawn on the I-Ching as a source of chance operation, such appropriations have often detached its formal mechanisms from the interpretive and philosophical processes that give the text meaning. Thi… ▽ More The I-Ching is one of the most influential texts in Chinese intellectual history, integrating divination, cosmology, and ethical reflection. While Western experimental music, most notably John Cage, has drawn on the I-Ching as a source of chance operation, such appropriations have often detached its formal mechanisms from the interpretive and philosophical processes that give the text meaning. This work, Music of Changing Lines, presents an interactive system that re-centers the I-Ching as a meaning-bearing framework rather than a neutral randomizer. Users perform Wen Wang Fa coin casting, which is accompanied in real time through probabilistic musical processes. The resulting hexagrams and changing lines are interpreted by a large language model, Gemini, in relation to the user's inquiry. This textual interpretation is then translated into a prompt for a generative music model, Lyria, producing a responsive musical realization. By situating AI as an interpretive intermediary rather than a compositional authority, the system foregrounds the I-Ching's ritual, interpretation, and participation as the primary sonic materials. Music of Changing Lines extends process-driven traditions in computer music by demonstrating how generative AI can support participatory, meaning-driven musical processes without prescribing musical structure or replacing human agency. △ Less

Submitted 19 May, 2026; originally announced May 2026.

Comments: Published and presented at the International Computer Music Conference (ICMC) 2026

Digital Twins as Synthetic Controls in Single-Arm Trials

Authors: Daniele Bertolini, Franklin Fuller, Aaron M. Smith, Jonathan R. Walsh, Run Zhuang

Abstract: Single-arm trials are an important study design for evaluating drug efficacy and safety without enrolling patients into a control arm. Although they do not provide the gold-standard evidence of randomized controlled trials, they are increasingly used in clinical development as they offer an efficient, ethical, and practical alternative. A wide variety of approaches can be used to construct control… ▽ More Single-arm trials are an important study design for evaluating drug efficacy and safety without enrolling patients into a control arm. Although they do not provide the gold-standard evidence of randomized controlled trials, they are increasingly used in clinical development as they offer an efficient, ethical, and practical alternative. A wide variety of approaches can be used to construct control comparators and estimate treatment effects, from fixed comparators informed by clinical knowledge to data-based and model-based patient-level comparators, also known as synthetic controls. Powerful and flexible machine learning models can allow outcome-model-based synthetic controls to overcome key limitations of direct data-based approaches, yield more robust estimates of treatment effects, and provide a principled way to incorporate corrections or encode additional assumptions when external data are not directly comparable. In this work, we argue that outcome-model-based synthetic control arms are an important tool for single-arm trials. We focus on digital twins, personalized predictions of disease progression generated from machine learning models trained on historical datasets, which naturally leverage these flexible approaches. We review doubly robust estimators, present power and sample size formulas, and discuss trade-offs in selecting historical data for training and analysis. We also outline practical considerations for deploying digital twins within the framework of recent FDA draft guidance on the use of artificial intelligence in drug development. Finally, we reanalyze data from trials in amyotrophic lateral sclerosis and Huntington's disease to demonstrate the proposed methods. △ Less

Submitted 12 May, 2026; originally announced May 2026.

The Capacity to Care: Designing Social Technology for Sustained Engagement With Societal Challenges

Authors: JaeWon Kim, Lindsay Popowski, Louisa Conwill, Elizabeth `Lizzie' Li, Meryl Ye, Jiaying `Lizzy' Liu, Jose A. Guridi, Theia Henderson, Bingxu Han, Dennis Wang, Angel Hsing-Chi Hwang, Susan Wyche, Yasmine Kotturi, Gillian R. Hayes, Angela D. R. Smith

Abstract: People care about climate change, injustice, and humanitarian crises. The challenge is not apathy but capacity: sustained engagement with large-scale problems is psychologically costly, and social media architecture often amplifies awareness while providing few pathways to meaningful action. The result is rising distress, overwhelm, and disengagement -- particularly among young people who encounte… ▽ More People care about climate change, injustice, and humanitarian crises. The challenge is not apathy but capacity: sustained engagement with large-scale problems is psychologically costly, and social media architecture often amplifies awareness while providing few pathways to meaningful action. The result is rising distress, overwhelm, and disengagement -- particularly among young people who encounter global suffering through platforms designed for attention capture rather than constructive response. This workshop examines how social technology design shapes the conditions for sustained engagement with societal challenges. Drawing on Tronto's care ethics framework and research in moral psychology and platform studies, we ask why caring at scale is difficult and how social media can both exacerbate and potentially mitigate this difficulty. Tronto's framework shows that good care requires more than awareness: it demands responsibility, competence, and community. Dominant social media architectures stall the caring process at its earliest phase. We invite researchers and designers to identify platform designs that deplete or support the capacity to care, and to develop design directions for sustainable care: engagement that people can maintain over time without burning out. △ Less

Submitted 22 May, 2026; v1 submitted 7 May, 2026; originally announced May 2026.

The Hidden Cost of Thinking: Energy Use and Environmental Impact of LMs Beyond Pretraining

Authors: Jacob Morrison, Noah A. Smith, Emma Strubell

Abstract: Modern language model development extends far beyond pretraining, yet environmental reporting remains narrowly focused on the cost of training a single final model. In this work, we provide the first detailed breakdown of the environmental impact of a full model development pipeline, from pretraining through supervised fine-tuning, preference optimization, and reinforcement learning, for Olmo 3, a… ▽ More Modern language model development extends far beyond pretraining, yet environmental reporting remains narrowly focused on the cost of training a single final model. In this work, we provide the first detailed breakdown of the environmental impact of a full model development pipeline, from pretraining through supervised fine-tuning, preference optimization, and reinforcement learning, for Olmo 3, a family of 7 billion and 32 billion parameter models in both instruction-following and reasoning variants. We find that reasoning models are 17x more expensive to post-train than their instruction-tuned counterparts in terms of datacenter energy, driven by reinforcement learning rollout generation. Development costs (including experimentation, failed runs, and ablations) account for 82.2% of total compute, a roughly 65% increase over the ~50% reported for pretraining-focused pipelines in prior work. In total, we estimate our model development process consumed ~12.3 GWh of datacenter energy, emitted 4,251 tCO2eq, and consumed 15,887 kL of water, with water consumption driven entirely by power generation infrastructure rather than data center cooling. These costs, which are almost entirely unreported by model developers, are growing rapidly as post-training pipelines become more complex, and must be accounted for in environmental reporting standards and by the research community working to reduce AI's environmental impact. △ Less

Submitted 1 May, 2026; originally announced May 2026.

Task Switching Without Forgetting via Proximal Decoupling

Authors: Pourya Shamsolmoali, Masoumeh Zareapoor, Eric Granger, William A. P. Smith, Yue Lu

Abstract: In continual learning, the primary challenge is to learn new information without forgetting old knowledge. A common solution addresses this trade-off through regularization, penalizing changes to parameters critical for previous tasks. In most cases, this regularization term is directly added to the training loss and optimized with standard gradient descent, which blends learning and retention sig… ▽ More In continual learning, the primary challenge is to learn new information without forgetting old knowledge. A common solution addresses this trade-off through regularization, penalizing changes to parameters critical for previous tasks. In most cases, this regularization term is directly added to the training loss and optimized with standard gradient descent, which blends learning and retention signals into a single update and does not explicitly separate essential parameters from redundant ones. As task sequences grow, this coupling can over-constrain the model, limiting forward transfer and leading to inefficient use of capacity. We propose a different approach that separates task learning from stability enforcement via operator splitting. The learning step focuses on minimizing the current task loss, while a proximal stability step applies a sparse regularizer to prune unnecessary parameters and preserve task-relevant ones. This turns the stability-plasticity into a negotiated update between two complementary operators, rather than a conflicting gradient. We provide theoretical justification for the splitting method on the continual-learning objective, and demonstrate that our proposed solver achieves state-of-the-art results on standard benchmarks, improving both stability and adaptability without the need for replay buffers, Bayesian sampling, or meta-learning components. △ Less

Submitted 20 April, 2026; originally announced April 2026.

Comments: Submitted to IEEE TPAMI January 2026

Skillful Global Ocean Emulation and the Role of Correlation-Aware Loss

Authors: Niraj Agarwal, Timothy A. Smith, Sergey Frolov, Laura C. Slivinski

Abstract: Machine learning emulators have shown extraordinary skill in forecasting atmospheric states, and their application to global ocean dynamics offers similar promise. Here, we adapt the GraphCast architecture into a dedicated ocean-only emulator, driven by prescribed atmospheric conditions, for medium-range predictions. The emulator is trained on NOAA's UFS-Replay dataset. Using a 24 hour time step,… ▽ More Machine learning emulators have shown extraordinary skill in forecasting atmospheric states, and their application to global ocean dynamics offers similar promise. Here, we adapt the GraphCast architecture into a dedicated ocean-only emulator, driven by prescribed atmospheric conditions, for medium-range predictions. The emulator is trained on NOAA's UFS-Replay dataset. Using a 24 hour time step, single initial condition, and without using autoregressive training, we produce an emulator that provides skillful forecasts for 10-15 day lead times. We further demonstrate the use of Mahalanobis distance as loss that improves the forecast skill compared to the Mean Squared Error loss by explicitly accounting for the correlations between tendencies of the target variables. Using spatial correlation analysis of the forecasted fields, we also show that the proposed correlation-aware loss acts as a statistical-dynamical regularizer for the slow, correlated dynamics of the global oceans, offering a better background forecast for downstream tasks like data assimilation. △ Less

Submitted 20 April, 2026; originally announced April 2026.

Comments: 13 pages, 4 figures

Beyond One Output: Visualizing and Comparing Distributions of Language Model Generations

Authors: Emily Reif, Claire Yang, Jared Hwang, Deniz Nazar, Noah A. Smith, Jeff Heer

Abstract: Users typically interact with and evaluate language models via single outputs, but each output is just one sample from a broad distribution of possible completions. This interaction hides distributional structure such as modes, uncommon edge cases, and sensitivity to small prompt changes, leading users to over-generalize from anecdotes when iterating on prompts for open-ended tasks. Informed by a… ▽ More Users typically interact with and evaluate language models via single outputs, but each output is just one sample from a broad distribution of possible completions. This interaction hides distributional structure such as modes, uncommon edge cases, and sensitivity to small prompt changes, leading users to over-generalize from anecdotes when iterating on prompts for open-ended tasks. Informed by a formative study with researchers who use LMs (n=13) examining when stochasticity matters in practice, how they reason about distributions over language, and where current workflows break down, we introduce GROVE. GROVE is an interactive visualization that represents multiple LM generations as overlapping paths through a text graph, revealing shared structure, branching points, and clusters while preserving access to raw outputs. We evaluate across three crowdsourced user studies (N=47, 44, and 40 participants) targeting complementary distributional tasks. Our results support a hybrid workflow: graph summaries improve structural judgments such as assessing diversity, while direct output inspection remains stronger for detail-oriented questions. △ Less

Submitted 31 July, 2026; v1 submitted 20 April, 2026; originally announced April 2026.

Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts

Authors: Jacob Morrison, Sanjay Adhikesaven, Akshita Bhagia, Matei Zaharia, Noah A. Smith, Sewon Min

Abstract: Extending a fully post-trained language model with new domain capabilities is fundamentally limited by monolithic training paradigms: retraining from scratch is expensive and scales poorly, while continued training often degrades existing capabilities. We present BAR (Branch-Adapt-Route), which trains independent domain experts, each through its own mid-training, supervised finetuning, and reinfor… ▽ More Extending a fully post-trained language model with new domain capabilities is fundamentally limited by monolithic training paradigms: retraining from scratch is expensive and scales poorly, while continued training often degrades existing capabilities. We present BAR (Branch-Adapt-Route), which trains independent domain experts, each through its own mid-training, supervised finetuning, and reinforcement learning pipeline, and composes them via a Mixture-of-Experts architecture with lightweight router training. Unlike retraining approaches that mix all domains and require full reprocessing for any update (with cost scaling quadratically), BAR enables updating individual experts independently with linear cost scaling and no degradation to existing domains. At the 7B scale, with experts for math, code, tool use, and safety, BAR achieves an overall score of 49.1 (averaged across 7 evaluation categories), matching or exceeding re-training baselines (47.8 without mid-training, 50.5 with). We further show that modular training provides a structural advantage: by isolating each domain, it avoids the catastrophic forgetting that occurs when late-stage RL degrades capabilities from earlier training stages, while significantly reducing the cost and complexity of updating or adding a domain. Together, these results suggest that decoupled, expert-based training is a scalable alternative to monolithic retraining for extending language models. △ Less

Submitted 20 April, 2026; originally announced April 2026.

Comments: 9 content pages, 23 pages overall, 3 figures

Differentially Private Modeling of Disease Transmission within Human Contact Networks

Authors: Shlomi Hod, Debanuj Nayak, Jason R. Gantenberg, Iden Kalemaj, Thomas A. Trikalinos, Adam Smith

Abstract: Epidemiologic studies of infectious diseases often rely on models of contact networks to capture the complex interactions that govern disease spread, and ongoing projects aim to vastly increase the scale at which such data can be collected. However, contact networks may include sensitive information, such as sexual relationships or drug use behavior. Protecting individual privacy while maintaining… ▽ More Epidemiologic studies of infectious diseases often rely on models of contact networks to capture the complex interactions that govern disease spread, and ongoing projects aim to vastly increase the scale at which such data can be collected. However, contact networks may include sensitive information, such as sexual relationships or drug use behavior. Protecting individual privacy while maintaining the scientific usefulness of the data is crucial. We propose a privacy-preserving pipeline for disease spread simulation studies based on a sensitive network that integrates differential privacy (DP) with statistical network models such as stochastic block models (SBMs) and exponential random graph models (ERGMs). Our pipeline comprises three steps: (1) compute network summary statistics using \emph{node-level} DP (which corresponds to protecting individuals' contributions); (2) fit a statistical model, like an ERGM, using these summaries, which allows generating synthetic networks reflecting the structure of the original network; and (3) simulate disease spread on the synthetic networks using an agent-based model. We evaluate the effectiveness of our approach using a simple Susceptible-Infected-Susceptible (SIS) disease model under multiple configurations. We compare both numerical results, such as simulated disease incidence and prevalence, as well as qualitative conclusions such as intervention effect size, on networks generated with and without differential privacy constraints. Our experiments are based on egocentric sexual network data from the ARTNet study (a survey about HIV-related behaviors). Our results show that the noise added for privacy is small relative to other sources of error (sampling and model misspecification). This suggests that, in principle, curators of such sensitive data can provide valuable epidemiologic insights while protecting privacy. △ Less

Submitted 8 April, 2026; originally announced April 2026.

AI Agents Under EU Law

Authors: Luca Nannini, Adam Leon Smith, Michele Joshua Maggini, Enrico Panai, Sandra Feliciano, Aleksandr Tiulkanov, Elena Maran, James Gealy, Piercosma Bisconti

Abstract: AI agents - i.e. AI systems that autonomously plan, invoke external tools, and execute multi-step action chains with reduced human involvement - are being deployed at scale across enterprise functions ranging from customer service and recruitment to clinical decision support and critical infrastructure management. The EU AI Act (Regulation 2024/1689) regulates these systems through a risk-based fr… ▽ More AI agents - i.e. AI systems that autonomously plan, invoke external tools, and execute multi-step action chains with reduced human involvement - are being deployed at scale across enterprise functions ranging from customer service and recruitment to clinical decision support and critical infrastructure management. The EU AI Act (Regulation 2024/1689) regulates these systems through a risk-based framework, but it does not operate in isolation: providers face simultaneous obligations under the GDPR, the Cyber Resilience Act, the Digital Services Act, the Data Act, the Data Governance Act, sector-specific legislation, the NIS2 Directive, and the revised Product Liability Directive. This paper provides the first systematic regulatory mapping for AI agent providers integrating (a) draft harmonised standards under Standardisation Request M/613 to CEN/CENELEC JTC 21 as of January 2026, (b) the GPAI Code of Practice published in July 2025, (c) the CRA harmonised standards programme under Mandate M/606 accepted in April 2025, and (d) the Digital Omnibus proposals of November 2025. We present a practical taxonomy of nine agent deployment categories mapping concrete actions to regulatory triggers, identify agent-specific compliance challenges in cybersecurity, human oversight, transparency across multi-party action chains, and runtime behavioral drift. We propose a twelve-step compliance architecture and a regulatory trigger mapping connecting agent actions to applicable legislation. We conclude that high-risk agentic systems with untraceable behavioral drift cannot currently satisfy the AI Act's essential requirements, and that the provider's foundational compliance task is an exhaustive inventory of the agent's external actions, data flows, connected systems, and affected persons. △ Less

Submitted 6 April, 2026; originally announced April 2026.

Comments: Working Paper - April 2026, subject to updates (EC M/613, M/606, Digital Omnibus proposals)

Olmo Hybrid: From Theory to Practice and Back

Authors: William Merrill, Yanhong Li, Tyler Romero, Anej Svete, Caia Costello, Pradeep Dasigi, Dirk Groeneveld, David Heineman, Bailey Kuehl, Nathan Lambert, Chuan Li, Kyle Lo, Saumya Malik, DJ Matusz, Benjamin Minixhofer, Jacob Morrison, Luca Soldaini, Finbarr Timbers, Pete Walsh, Noah A. Smith, Hannaneh Hajishirzi, Ashish Sabharwal

Abstract: Recent work has demonstrated the potential of non-transformer language models, especially linear recurrent neural networks (RNNs) and hybrid models that mix recurrence and attention. Yet there is no consensus on whether the potential benefits of these new architectures justify the risk and effort of scaling them up. To address this, we provide evidence for the advantages of hybrid models over pure… ▽ More Recent work has demonstrated the potential of non-transformer language models, especially linear recurrent neural networks (RNNs) and hybrid models that mix recurrence and attention. Yet there is no consensus on whether the potential benefits of these new architectures justify the risk and effort of scaling them up. To address this, we provide evidence for the advantages of hybrid models over pure transformers on several fronts. First, theoretically, we show that hybrid models do not merely inherit the expressivity of transformers and linear RNNs, but can express tasks beyond both, such as code execution. Putting this theory to practice, we train Olmo Hybrid, a 7B-parameter model largely comparable to Olmo 3 7B but with the sliding window layers replaced by Gated DeltaNet layers. We show that Olmo Hybrid outperforms Olmo 3 across standard pretraining and mid-training evaluations, demonstrating the benefit of hybrid models in a controlled, large-scale setting. We find that the hybrid model scales significantly more efficiently than the transformer, explaining its higher performance. However, its unclear why greater expressivity on specific formal problems should result in better scaling or superior performance on downstream tasks unrelated to those problems. To explain this apparent gap, we return to theory and argue why increased expressivity should translate to better scaling efficiency, completing the loop. Overall, our results suggest that hybrid models mixing attention and recurrent layers are a powerful extension to the language modeling paradigm: not merely to reduce memory during inference, but as a fundamental way to obtain more expressive models that scale better during pretraining. △ Less

Submitted 15 June, 2026; v1 submitted 3 April, 2026; originally announced April 2026.

Comments: Corrected author list and typos in appendix

Ctrl-A: Control-Driven Online Data Augmentation

Authors: Jesper B. Christensen, Ciaran Bench, Spencer A. Thomas, Hüsnü Aslan, David Balslev-Harder, Nadia A. S. Smith, Alessandra Manzin

Abstract: We introduce ControlAugment (Ctrl-A), an automated data augmentation algorithm for image-vision tasks, which incorporates principles from control theory for online adjustment of augmentation strength distributions during model training. Ctrl-A eliminates the need for initialization of individual augmentation strengths. Instead, augmentation strength distributions are dynamically, and individually,… ▽ More We introduce ControlAugment (Ctrl-A), an automated data augmentation algorithm for image-vision tasks, which incorporates principles from control theory for online adjustment of augmentation strength distributions during model training. Ctrl-A eliminates the need for initialization of individual augmentation strengths. Instead, augmentation strength distributions are dynamically, and individually, adapted during training based on a control-loop architecture and what we define as relative operation response curves. Using an operation-dependent update procedure provides Ctrl-A with the potential to suppress augmentation styles that negatively impact model performance, alleviating the need for manually engineering augmentation policies for new image-vision tasks. Experiments on the CIFAR-10, CIFAR-100, and SVHN-core benchmark datasets using the common WideResNet-28-10 architecture demonstrate that Ctrl-A is highly competitive with existing state-of-the-art data augmentation strategies. △ Less

Submitted 23 March, 2026; originally announced March 2026.

Comments: 17 pages (11 pages main manuscript), 8 figures (5 in main manuscript)

Ensemble of Small Classifiers For Imbalanced White Blood Cell Classification

Authors: Siddharth Srivastava, Adam Smith, Scott Brooks, Jack Bacon, Till Bretschneider

Abstract: Automating white blood cell classification for diagnosis of leukaemia is a promising alternative to time-consuming and resource-intensive examination of cells by expert pathologists. However, designing robust algorithms for classification of rare cell types remains challenging due to variations in staining, scanning and inter-patient heterogeneity. We propose a lightweight ensemble approach for cl… ▽ More Automating white blood cell classification for diagnosis of leukaemia is a promising alternative to time-consuming and resource-intensive examination of cells by expert pathologists. However, designing robust algorithms for classification of rare cell types remains challenging due to variations in staining, scanning and inter-patient heterogeneity. We propose a lightweight ensemble approach for classification of cells during Haematopoiesis, with a focus on the biology of Granulopoiesis, Monocytopoiesis and Lymphopoiesis. Through dataset expansion to alleviate some class imbalance, we demonstrate that a simple ensemble of lightweight pretrained SwinV2-Tiny, DinoBloom-Small and ConvNeXT-V2-Tiny models achieves excellent performance on this challenging dataset. We train 3 instantiations of each architecture in a stratified 3-fold cross-validation framework; for an input image, we forward-pass through all 9 models and aggregate through logit averaging. We further reason on the weaknesses of our model in confusing similar-looking myelocytes in granulopoiesis and lymphocytes in lymphopoiesis. Code: https://gitlab.com/siddharthsrivastava/wbc-bench-2026. △ Less

Submitted 21 March, 2026; originally announced March 2026.

Comments: Accepted at ISBI 2026 WBCBench Challenge

Meta-Reinforcement Learning with Self-Reflection for Agentic Search

Authors: Teng Xiao, Yige Yuan, Hamish Ivison, Huaisheng Zhu, Faeze Brahman, Nathan Lambert, Pradeep Dasigi, Noah A. Smith, Hannaneh Hajishirzi

Abstract: This paper introduces MR-Search, an in-context meta reinforcement learning (RL) formulation for agentic search with self-reflection. Instead of optimizing a policy within a single independent episode with sparse rewards, MR-Search trains a policy that conditions on past episodes and adapts its search strategy across episodes. MR-Search learns to learn a search strategy with self-reflection, allowi… ▽ More This paper introduces MR-Search, an in-context meta reinforcement learning (RL) formulation for agentic search with self-reflection. Instead of optimizing a policy within a single independent episode with sparse rewards, MR-Search trains a policy that conditions on past episodes and adapts its search strategy across episodes. MR-Search learns to learn a search strategy with self-reflection, allowing search agents to improve in-context exploration at test-time. Specifically, MR-Search performs cross-episode exploration by generating explicit self-reflections after each episode and leveraging them as additional context to guide subsequent attempts, thereby promoting more effective exploration during test-time. We further introduce a multi-turn RL algorithm that estimates a dense relative advantage at the turn level, enabling fine-grained credit assignment on each episode. Empirical results across various benchmarks demonstrate the advantages of MR-Search over baselines based RL, showing strong generalization and relative improvements of 9.2% to 19.3% across eight benchmarks. Our code and data are available at https://github.com/tengxiao1/MR-Search. △ Less

Submitted 18 March, 2026; v1 submitted 11 March, 2026; originally announced March 2026.

Comments: 23 pages, Preprint

Challenges in Synchronous & Remote Collaboration Around Visualization

Authors: Matthew Brehmer, Maxime Cordeil, Christophe Hurter, Takayuki Itoh, Wolfgang Büschel, Mahmood Jasim, Arnaud Prouzeau, David Saffo, Lyn Bartram, Sheelagh Carpendale, Chen Zhu-Tian, Andrew Cunningham, Tim Dwyer, Samuel Huron, Masahiko Itoh, Alark Joshi, Kiyoshi Kiyokawa, Hideaki Kuzuoka, Bongshin Lee, Gabriela Molina León, Harald Reiterer, Bektur Ryskeldiev, Jonathan Schwabish, Brian A. Smith, Yasuyuki Sumi , et al. (4 additional authors not shown)

Abstract: We characterize 16 challenges faced by those investigating and developing remote and synchronous collaborative experiences around visualization. Our work reflects the perspectives and prior research efforts of an international group of 29 experts from across human-computer interaction and visualization sub-communities. The challenges are anchored around five collaborative activities that exhibit a… ▽ More We characterize 16 challenges faced by those investigating and developing remote and synchronous collaborative experiences around visualization. Our work reflects the perspectives and prior research efforts of an international group of 29 experts from across human-computer interaction and visualization sub-communities. The challenges are anchored around five collaborative activities that exhibit a centrality of visualization and multimodal communication. These activities include exploratory data analysis, creative ideation, visualization-rich presentations, joint decision making grounded in data, and real-time data monitoring. The challenges also reflect the changing dynamics of these activities in the face of recent advances in extended reality (XR) and artificial intelligence (AI). As an organizing scheme for future research at the intersection of visualization and computer-supported cooperative work, we align the challenges with a sequence of four sets of research and development activities: technological choices, social factors, AI assistance, and evaluation. △ Less

Submitted 5 March, 2026; originally announced March 2026.

Comments: Proceedings of the 2026 ACM Conference on Human Factors in Computing Systems (CHI)

Machine Learning on Heterogeneous, Edge, and Quantum Hardware for Particle Physics (ML-HEQUPP)

Authors: Julia Gonski, Jenni Ott, Shiva Abbaszadeh, Sagar Addepalli, Matteo Cremonesi, Jennet Dickinson, Giuseppe Di Guglielmo, Erdem Yigit Ertorer, Lindsey Gray, Ryan Herbst, Christian Herwig, Tae Min Hong, Benedikt Maier, Maryam Bayat Makou, David Miller, Mark S. Neubauer, Cristián Peña, Dylan Rankin, Seon-Hee, Seo, Giordon Stark, Alexander Tapper, Audrey Corbeil Therrien, Ioannis Xiotidis, Keisuke Yoshihara , et al. (99 additional authors not shown)

Abstract: The next generation of particle physics experiments will face a new era of challenges in data acquisition, due to unprecedented data rates and volumes along with extreme environments and operational constraints. Harnessing this data for scientific discovery demands real-time inference and decision-making, intelligent data reduction, and efficient processing architectures beyond current capabilitie… ▽ More The next generation of particle physics experiments will face a new era of challenges in data acquisition, due to unprecedented data rates and volumes along with extreme environments and operational constraints. Harnessing this data for scientific discovery demands real-time inference and decision-making, intelligent data reduction, and efficient processing architectures beyond current capabilities. Crucial to the success of this experimental paradigm are several emerging technologies, such as artificial intelligence and machine learning (AI/ML), silicon microelectronics, and the advent of quantum algorithms and processing. Their intersection includes areas of research such as low-power and low-latency devices for edge computing, heterogeneous accelerator systems, reconfigurable hardware, novel codesign and synthesis strategies, readout for cryogenic or high-radiation environments, and analog computing. This white paper presents a community-driven vision to identify and prioritize research and development opportunities in hardware-based ML systems and corresponding physics applications, contributing towards a successful transition to the new data frontier of fundamental science. △ Less

Submitted 24 July, 2026; v1 submitted 24 February, 2026; originally announced February 2026.

Comments: 123 pages, 53 figures

Local Node Differential Privacy

Authors: Sofya Raskhodnikova, Adam Smith, Connor Wagaman, Anatoly Zavyalov

Abstract: We initiate an investigation of node differential privacy for graphs in the local model of private data analysis. In our model, dubbed LNDP*, each node sees its own edge list and releases the output of a local randomizer on this input. These outputs are aggregated by an untrusted server to obtain a final output. We develop a novel algorithmic framework for this setting that allows us to accurate… ▽ More We initiate an investigation of node differential privacy for graphs in the local model of private data analysis. In our model, dubbed LNDP*, each node sees its own edge list and releases the output of a local randomizer on this input. These outputs are aggregated by an untrusted server to obtain a final output. We develop a novel algorithmic framework for this setting that allows us to accurately answer arbitrary linear queries about the input graph's degree distribution. Our framework is based on a new object, called the blurry degree distribution, which closely approximates the degree distribution and has lower sensitivity. Instead of answering queries about the degree distribution directly, our algorithms answer queries about the blurry degree distribution. This framework yields accurate LNDP* algorithms for the edge count, PMF and CDF of the degree distribution, and other graph statistics. For some natural problems, our algorithms match the accuracy achievable with node privacy in the central model, where data are held and processed by a trusted server. We also prove lower bounds on the error required by LNDP* algorithms that imply the optimality of our framework for edge counting in sparse graphs and Erdos-Renyi parameter estimation. Our lower bounds apply even to interactive protocols with a constant number of rounds of interaction between the nodes and the server. Existing lower-bound techniques for related models either yield loose bounds or do not apply in our setting, as graph data results in inherently overlapping inputs to local randomizers. To prove our bounds, we develop a splicing argument that stitches together views from locally similar but globally different distributions on graphs to obtain hard instances. Finally, we prove structural results that reveal qualitative differences between local node privacy and the standard local model for tabular data. △ Less

Submitted 1 April, 2026; v1 submitted 17 February, 2026; originally announced February 2026.

Enabling Low-Latency Machine learning on Radiation-Hard FPGAs with hls4ml

Authors: Katya Govorkova, Julian Garcia Pardinas, Vladimir Loncar, Victoria Nguyen, Sebastian Schmitt, Marco Pizzichemi, Loris Martinazzoli, Eluned Anne Smith

Abstract: This paper presents an end-to-end demonstration of a viable, ultra-fast, radiation-hard machine learning (ML) application on FPGAs, which could be used in future high-energy physics experiments. We present a three-fold contribution, with the PicoCal calorimeter, planned for the LHCb Upgrade II experiment, used as a test case. First, we develop a lightweight autoencoder to compress a 32-sample timi… ▽ More This paper presents an end-to-end demonstration of a viable, ultra-fast, radiation-hard machine learning (ML) application on FPGAs, which could be used in future high-energy physics experiments. We present a three-fold contribution, with the PicoCal calorimeter, planned for the LHCb Upgrade II experiment, used as a test case. First, we develop a lightweight autoencoder to compress a 32-sample timing readout, representative of that of the PicoCal, into a two-dimensional latent space. Second, we introduce a systematic, hardware-aware quantization strategy and show that the model can be reduced to 10-bit weights with minimal performance loss. Third, as a barrier to the adoption of on-detector ML is the lack of support for radiation-hard FPGAs in the High-Energy Physics community's standard ML synthesis tool, hls4ml, we develop a new backend for this library. This new back-end enables the automatic translation of ML models into High-Level Synthesis (HLS) projects for the Microchip PolarFire family of FPGAs, one of the few commercially available and radiation hard FPGAs. We present the synthesis of the autoencoder on a target PolarFire FPGA, which indicates that a latency of 25 ns can be achieved. We show that the resources utilized are low enough that the model can be placed within the inherently protected logic of the FPGA. Our extension to hls4ml is a significant contribution, paving the way for broader adoption of ML on FPGAs in high-radiation environments. △ Less

Submitted 31 July, 2026; v1 submitted 17 February, 2026; originally announced February 2026.

Journal ref: Machine Learning: Science and Technology 7 (2026) 045024

Interpretive Cultures: Resonance, randomness, and negotiated meaning for AI-assisted tarot divination

Authors: Matthew Prock, Ziv Epstein, Hope Schroeder, Amy Smith, Cassandra Lee, Vana Goblot, Farnaz Jahanbakhsh

Abstract: While generative AI tools are increasingly adopted for creative and analytical tasks, their role in interpretive practices, where meaning is subjective, plural, and non-causal, remains poorly understood. This paper examines AI-assisted tarot reading, a divinatory practice in which users pose a query, draw cards through a randomized process, and ask AI systems to interpret the resulting symbols. Dr… ▽ More While generative AI tools are increasingly adopted for creative and analytical tasks, their role in interpretive practices, where meaning is subjective, plural, and non-causal, remains poorly understood. This paper examines AI-assisted tarot reading, a divinatory practice in which users pose a query, draw cards through a randomized process, and ask AI systems to interpret the resulting symbols. Drawing on interviews with tarot practitioners and Hartmut Rosa's Theory of Resonance, we investigate how users seek, negotiate, and evaluate resonant interpretations in a context where no causal relationship exists between the query and the data being interpreted. We identify distinct ways practitioners incorporate AI into their interpretive workflows, including using AI to navigate uncertainty and self-doubt, explore alternative perspectives, and streamline or extend existing divinatory practices. Based on these findings, we offer design recommendations for AI systems that support interpretive meaning-making without collapsing ambiguity or foreclosing user agency. △ Less

Submitted 11 February, 2026; originally announced February 2026.

ACM Class: H.5.2

Encode Once, Decode Never: Reusing Audio LM Internals for Efficient Temporal Localization

Authors: Joseph An, Phillip Keung, Jiaqi Wang, Orevaoghene Ahia, Noah A. Smith

Abstract: Audio language models process input audio into rich frame-level representations, but the standard approach to temporal localization generates timestamps as sequences of text tokens, which discards the frame-level representations in favor of autoregressive decoding. However, generating timestamps as tokens is slow and not parallelizable, and tends to hallucinate when producing timestamps outside th… ▽ More Audio language models process input audio into rich frame-level representations, but the standard approach to temporal localization generates timestamps as sequences of text tokens, which discards the frame-level representations in favor of autoregressive decoding. However, generating timestamps as tokens is slow and not parallelizable, and tends to hallucinate when producing timestamps outside the training distribution. We propose internal frame-level reuse, a method that trains audio LMs to reuse their own internal audio representations for temporal localization directly, bypassing token generation altogether. We introduce a lightweight prediction head trained via different frame-level objectives: a binary frame classifier and a novel inhomogeneous Poisson process (IHP) loss that models temporal event intensity. Across word localization, speaker diarization, and event localization tasks, our approach can achieve a >50x inference speedup over token-based generation and demonstrates robust length generalization, maintaining high accuracy on out-of-distribution audio durations where token-based models collapse completely. We find that reusing audio frame-level representations yields localization accuracies comparable to (and often better than) finetuned token-based baselines. △ Less

Submitted 22 July, 2026; v1 submitted 10 February, 2026; originally announced February 2026.

Comments: To appear in COLM 2026. Refer to https://github.com/inkitori/taudio/ for the codebase

The Needle is a Thread: Finding Planted Paths in Noisy Process Trees

Authors: Maya Le, Paweł Prałat, Aaron Smith, François Théberge

Abstract: Motivated by applications in cybersecurity such as finding meaningful sequences of malware-related events buried inside large amounts of computer log data, we introduce the "planted path" problem and propose an algorithm to find fuzzy matchings between two trees. This algorithm can be used as a "building block" for more complicated workflows. We demonstrate usefulness of a few of such workflows in… ▽ More Motivated by applications in cybersecurity such as finding meaningful sequences of malware-related events buried inside large amounts of computer log data, we introduce the "planted path" problem and propose an algorithm to find fuzzy matchings between two trees. This algorithm can be used as a "building block" for more complicated workflows. We demonstrate usefulness of a few of such workflows in mining synthetically generated data as well as real-world ACME cybersecurity datasets. △ Less

Submitted 4 February, 2026; originally announced February 2026.

Comments: 15 pages, 9 figures

BASS: Benchmarking Audio LMs for Musical Structure and Semantic Reasoning

Authors: Min Jang, Orevaoghene Ahia, Nazif Tamer, Sachin Kumar, Yulia Tsvetkov, Noah A. Smith

Abstract: Music understanding is a complex task that often requires reasoning over both structural and semantic elements of audio. We introduce BASS, designed to evaluate music understanding and reasoning in audio language models across four broad categories: structural segmentation, lyric transcription, musicological analysis, and artist collaboration. BASS comprises 2658 questions spanning 12 tasks, 1993… ▽ More Music understanding is a complex task that often requires reasoning over both structural and semantic elements of audio. We introduce BASS, designed to evaluate music understanding and reasoning in audio language models across four broad categories: structural segmentation, lyric transcription, musicological analysis, and artist collaboration. BASS comprises 2658 questions spanning 12 tasks, 1993 unique songs and covering over 138 hours of music from a wide range of genres and tracks, crafted to assess musicological knowledge and reasoning in real-world scenarios. We evaluate 14 open-source and frontier multimodal LMs, finding that even state-of-the-art models struggle on higher-level reasoning tasks such as structural segmentation and artist collaboration, while performing best on lyric transcription. Our analysis reveals that current models leverage linguistic priors effectively but remain limited in reasoning over musical structure, vocal, and musicological attributes. BASS provides an evaluation framework with widespread applications in music recommendation and search and has the potential to guide the development of audio LMs. △ Less

Submitted 3 February, 2026; originally announced February 2026.

Are you going to finish that? A Practical Study of the Partial Token Problem

Authors: Hao Xu, Alisa Liu, Jonathan Hayase, Yejin Choi, Noah A. Smith

Abstract: Language models (LMs) are trained over sequences of tokens, whereas users interact with LMs via text. This mismatch gives rise to the partial token problem, which occurs when a user ends their prompt in the middle of the expected next-token, leading to distorted next-token predictions. Although this issue has been studied using arbitrary character prefixes, its prevalence and severity in realistic… ▽ More Language models (LMs) are trained over sequences of tokens, whereas users interact with LMs via text. This mismatch gives rise to the partial token problem, which occurs when a user ends their prompt in the middle of the expected next-token, leading to distorted next-token predictions. Although this issue has been studied using arbitrary character prefixes, its prevalence and severity in realistic prompts respecting word boundaries remains underexplored. In this work, we identify three domains where token and "word" boundaries often do not line up: languages that do not use whitespace, highly compounding languages, and code. In Chinese, for example, up to 25% of word boundaries do not line up with token boundaries, making even natural, word-complete prompts susceptible to this problem. We systematically construct semantically natural prompts ending with a partial tokens; in experiments, we find that they comprise a serious failure mode: frontier LMs consistently place three orders of magnitude less probability on the correct continuation compared to when the prompt is "backed-off" to be token-aligned. This degradation does not diminish with scale and often worsens for larger models. Finally, we evaluate inference-time mitigations to the partial token problem and validate the effectiveness of recent exact solutions. Overall, we demonstrate the scale and severity of probability distortion caused by tokenization in realistic use cases, and provide practical recommentions for model inference providers. △ Less

Submitted 2 February, 2026; v1 submitted 30 January, 2026; originally announced January 2026.

Memorization Dynamics in Knowledge Distillation for Language Models

Authors: Jaydeep Borkar, Karan Chadha, Niloofar Mireshghallah, Yuchen Zhang, Irina-Elena Veliche, Archi Mitra, David A. Smith, Zheng Xu, Diego Garcia-Olano

Abstract: Knowledge Distillation (KD) is increasingly adopted to transfer capabilities from large language models to smaller ones, offering significant improvements in efficiency and utility while often surpassing standard fine-tuning. Beyond performance, KD is also explored as a privacy-preserving mechanism to mitigate the risk of training data leakage. While training data memorization has been extensively… ▽ More Knowledge Distillation (KD) is increasingly adopted to transfer capabilities from large language models to smaller ones, offering significant improvements in efficiency and utility while often surpassing standard fine-tuning. Beyond performance, KD is also explored as a privacy-preserving mechanism to mitigate the risk of training data leakage. While training data memorization has been extensively studied in standard pre-training and fine-tuning settings, its dynamics in a knowledge distillation setup remain poorly understood. In this work, we study memorization across the KD pipeline using three large language model (LLM) families (Pythia, OLMo-2, Qwen-3) and three datasets (FineWeb, Wikitext, Nemotron-CC-v2). We find: (1) distilled models memorize significantly less training data than standard fine-tuning (reducing memorization by more than 50%); (2) some examples are inherently easier to memorize and account for a large fraction of memorization during distillation (over ~95%); (3) student memorization is predictable prior to distillation using features based on zlib entropy, KL divergence, and perplexity; and (4) while soft and hard distillation have similar overall memorization rates, hard distillation poses a greater risk: it inherits $2.7\times$ more teacher-specific examples than soft distillation. Overall, we demonstrate that distillation can provide both improved generalization and reduced memorization risks compared to standard fine-tuning. △ Less

Submitted 7 August, 2026; v1 submitted 21 January, 2026; originally announced January 2026.

VENI: Variational Encoder for Natural Illumination

Authors: Paul Walker, James A. D. Gardner, Andreea Ardelean, William A. P. Smith, Bernhard Egger

Abstract: Inverse rendering is an ill-posed problem, but priors such as illumination priors can help simplify it. Existing work either disregards the spherical and rotation-equivariant nature of illumination environments or does not provide a well-behaved latent space. We propose a rotation-equivariant variational autoencoder that models natural illumination on the sphere without relying on 2D projections.… ▽ More Inverse rendering is an ill-posed problem, but priors such as illumination priors can help simplify it. Existing work either disregards the spherical and rotation-equivariant nature of illumination environments or does not provide a well-behaved latent space. We propose a rotation-equivariant variational autoencoder that models natural illumination on the sphere without relying on 2D projections. To preserve the SO(2)-equivariance of environment maps, we use a novel Vector Neuron Vision Transformer (VN-ViT) as encoder and a rotation-equivariant conditional neural field as decoder. In the encoder, we reduce the equivariance from SO(3) to SO(2) using a novel SO(2)-equivariant fully connected layer, an extension of Vector Neurons. We show that our SO(2)-equivariant fully connected layer outperforms standard Vector Neurons when used in our SO(2)-equivariant model. Compared to previous methods, our variational autoencoder enables smoother interpolation in latent space and offers a more well-behaved latent space. △ Less

Submitted 24 June, 2026; v1 submitted 20 January, 2026; originally announced January 2026.

Comments: Project Repo - https://github.com/paul-pw/veni Project page - https://paul-pw.github.io/veni

Journal ref: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2026) 16248-16257

Bolmo: Byteifying the Next Generation of Language Models

Authors: Benjamin Minixhofer, Tyler Murray, Tomasz Limisiewicz, Anna Korhonen, Luke Zettlemoyer, Noah A. Smith, Edoardo M. Ponti, Luca Soldaini, Valentin Hofmann

Abstract: Recent advances in generative AI have been largely driven by large language models (LLMs), deep neural networks that operate over discrete units called tokens. To represent text, the vast majority of LLMs use words or word fragments as the tokens, known as subword tokenization. Subword tokenization obscures fine-grained information, which is problematic, especially for scientific data - such as co… ▽ More Recent advances in generative AI have been largely driven by large language models (LLMs), deep neural networks that operate over discrete units called tokens. To represent text, the vast majority of LLMs use words or word fragments as the tokens, known as subword tokenization. Subword tokenization obscures fine-grained information, which is problematic, especially for scientific data - such as computer code or biological sequences - where meaning depends on the individual characters. Models that instead operate directly on the byte encoding of text avoid these limitations, but until now they have lagged behind subword-based models in performance. Here we introduce Bolmo, a family of fully open byte-level LLMs that approach the capabilities of subword-based systems. Using a two-stage conversion procedure, we transform existing subword-based models into byte-level models with minimal additional training. The resulting models outperform prior byte-level approaches and excel on character-level reasoning tasks, while remaining competitive across standard benchmarks. By efficiently processing byte-level information, these models achieve practical inference speeds and can be adapted at low cost using the existing ecosystem around the source LLM. Our results remove a long-standing performance barrier to end-to-end byte-level language modeling, demonstrating that models operating on raw text encodings can scale competitively while offering advantages in domains requiring fine-grained textual understanding. △ Less

Submitted 9 February, 2026; v1 submitted 17 December, 2025; originally announced December 2025.

Olmo 3

Authors: Team Olmo, :, Allyson Ettinger, Amanda Bertsch, Bailey Kuehl, David Graham, David Heineman, Dirk Groeneveld, Faeze Brahman, Finbarr Timbers, Hamish Ivison, Jacob Morrison, Jake Poznanski, Kyle Lo, Luca Soldaini, Matt Jordan, Mayee Chen, Michael Noukhovitch, Nathan Lambert, Pete Walsh, Pradeep Dasigi, Robert Berry, Saumya Malik, Saurabh Shah, Scott Geng , et al. (44 additional authors not shown)

Abstract: We introduce Olmo 3, a family of state-of-the-art, fully-open language models at the 7B and 32B parameter scales. Olmo 3 model construction targets long-context reasoning, function calling, coding, instruction following, general chat, and knowledge recall. This release includes the entire model flow, i.e., the full lifecycle of the family of models, including every stage, checkpoint, data point, a… ▽ More We introduce Olmo 3, a family of state-of-the-art, fully-open language models at the 7B and 32B parameter scales. Olmo 3 model construction targets long-context reasoning, function calling, coding, instruction following, general chat, and knowledge recall. This release includes the entire model flow, i.e., the full lifecycle of the family of models, including every stage, checkpoint, data point, and dependency used to build it. Our flagship model, Olmo 3 Think 32B, is the strongest fully-open thinking model released to-date. △ Less

Submitted 14 April, 2026; v1 submitted 15 December, 2025; originally announced December 2025.

Comments: minor edit updates

A stylometric analysis of speaker attribution from speech transcripts

Authors: Cristina Aggazzotti, Elizabeth Allyn Smith

Abstract: Forensic scientists often need to identify an unknown speaker or writer in cases such as ransom calls, covert recordings, alleged suicide notes, or anonymous online communications, among many others. Speaker recognition in the speech domain usually examines phonetic or acoustic properties of a voice, and these methods can be accurate and robust under certain conditions. However, if a speaker disgu… ▽ More Forensic scientists often need to identify an unknown speaker or writer in cases such as ransom calls, covert recordings, alleged suicide notes, or anonymous online communications, among many others. Speaker recognition in the speech domain usually examines phonetic or acoustic properties of a voice, and these methods can be accurate and robust under certain conditions. However, if a speaker disguises their voice or employs text-to-speech software, vocal properties may no longer be reliable, leaving only their linguistic content available for analysis. Authorship attribution methods traditionally use syntactic, semantic, and related linguistic information to identify writers of written text (authorship attribution). In this paper, we apply a content-based authorship approach to speech that has been transcribed into text, using what a speaker says to attribute speech to individuals (speaker attribution). We introduce a stylometric method, StyloSpeaker, which incorporates character, word, token, sentence, and style features from the stylometric literature on authorship, to assess whether two transcripts were produced by the same speaker. We evaluate this method on two types of transcript formatting: one approximating prescriptive written text with capitalization and punctuation and another normalized style that removes these conventions. The transcripts' conversation topics are also controlled to varying degrees. We find generally higher attribution performance on normalized transcripts, except under the strongest topic control condition, in which overall performance is highest. Finally, we compare this more explainable stylometric model to black-box neural approaches on the same data and investigate which stylistic features most effectively distinguish speakers. △ Less

Submitted 18 December, 2025; v1 submitted 15 December, 2025; originally announced December 2025.

Comments: v3: added StyloSpeaker github link; v2: added acknowledgments

WaggleNet: A LoRa and MQTT-Based Monitoring System for Internal and External Beehive Conditions

Authors: Minju Jeon, Jiyun Kim, Sewon Kim, Seongmin Park, Bo Zhang, Anthony H. Smith

Abstract: Bee populations are declining globally due to habitat loss, pesticide exposure, and climate change, threatening agricultural productivity and food security. While existing smart beehive systems monitor internal conditions, they typically overlook external environmental factors that significantly influence colony health, and are constrained by high cost, limited scalability, and inadequate contextu… ▽ More Bee populations are declining globally due to habitat loss, pesticide exposure, and climate change, threatening agricultural productivity and food security. While existing smart beehive systems monitor internal conditions, they typically overlook external environmental factors that significantly influence colony health, and are constrained by high cost, limited scalability, and inadequate contextual analysis. We present WaggleNet, a novel dual-scope monitoring system that simultaneously captures both internal hive conditions and external environmental parameters using a cost-effective LoRa-MQTT architecture. Our system deploys modular worker nodes ($\sim$\$15 each) equipped with temperature, humidity, light, and GPS sensors both inside and around beehives. A master node functions as a LoRa-MQTT gateway, forwarding data to a cloud server with a mobile application interface. Field experiments confirmed reliable operation with 100\% packet delivery over 110 meters in line-of-sight conditions and 95 meters in obstructed environments, including successful deployment inside wooden hive structures. Our system demonstrated stable end-to-end latency under 5 seconds and continuous operation over a two-month period across diverse environmental conditions. By bridging the gap between internal and external monitoring, WaggleNet enables contextual anomaly detection and supports data-driven precision beekeeping in resource-constrained settings. △ Less

Submitted 8 December, 2025; originally announced December 2025.

Comments: 8 pages, 7 figures, 3 tables

ACM Class: C.2.1; C.2.3; C.3; I.2.10

Towards A Cultural Intelligence and Values Inferences Quality Benchmark for Community Values and Common Knowledge

Authors: Brittany Johnson, Erin Reddick, Angela D. R. Smith

Abstract: Large language models (LLMs) have emerged as a powerful technology, and thus, we have seen widespread adoption and use on software engineering teams. Most often, LLMs are designed as "general purpose" technologies meant to represent the general population. Unfortunately, this often means alignment with predominantly Western Caucasian narratives and misalignment with other cultures and populations… ▽ More Large language models (LLMs) have emerged as a powerful technology, and thus, we have seen widespread adoption and use on software engineering teams. Most often, LLMs are designed as "general purpose" technologies meant to represent the general population. Unfortunately, this often means alignment with predominantly Western Caucasian narratives and misalignment with other cultures and populations that engage in collaborative innovation. In response to this misalignment, there have been recent efforts centered on the development of "culturally-informed" LLMs, such as ChatBlackGPT, that are capable of better aligning with historically marginalized experiences and perspectives. Despite this progress, there has been little effort aimed at supporting our ability to develop and evaluate culturally-informed LLMs. A recent effort proposed an approach for developing a national alignment benchmark that emphasizes alignment with national social values and common knowledge. However, given the range of cultural identities present in the United States (U.S.), a national alignment benchmark is an ineffective goal for broader representation. To help fill this gap in this US context, we propose a replication study that translates the process used to develop KorNAT, a Korean National LLM alignment benchmark, to develop CIVIQ, a Cultural Intelligence and Values Inference Quality benchmark centered on alignment with community social values and common knowledge. Our work provides a critical foundation for research and development aimed at cultural alignment of AI technologies in practice. △ Less

Submitted 4 December, 2025; originally announced December 2025.

Comments: Under review