Computer Vision
FedCoRe: Target-Adaptive Completion for Missing Modalities in Healthcare Federated Learning
Holger R. Roth, Ziyue Xu and Peter Cnudde
Federated multimodal models often assume every site has every modality, although hospitals differ in access to EHRs, chest radiographs, and ECGs. We study this setting on a MIMIC-derived respiratory deterioration task with simulated FL clients and introduce FedCoRe (
Federated Cross-Modal Representation Completion). FedCoRe learns representation- or logit-space corrections rather than generating synthetic ECGs or CXR images. When a client observes a modality that may be missing at deployment, it evaluates the same example with and without that modality to obtain paired supervision. Only clients with such pairs update the completion module, and validation may retain the unchanged prediction. We freeze the trained
multimodal predictor during evaluation so that measured differences come only from completion. Hiding ECG reduced AUROC by about 0.085; paired-example FedAvg restored 0.0415 AUROC, or 49.0% of the lost performance. We therefore report two distinct effects: paired-example FedAvg partially recovers the missing-ECG gap, while validation-selected completion is a task-specific classifier-logit correction rather than literal ECG recovery. For CXR, effect-aware completion recovers 52.8% of the loss in a controlled test where CXR is hidden. Paired-example FedAvg transfers part of this effect, but validation keeps the no-completion baseline for deployment cases whose inputs lack CXR. Thus, FedCoRe should be read as a validation-gated completion/correction framework: it can recover missing-modality signal in supported settings, but it should be deployed only when paired examples and validation evidence support that modality.
Read the full abstract ▾
Computer Vision
XRF-to-Optical Field-of-View Localization with Vision Language Models
Xiangyu Yin, Tatjana Paunesku, Letonia Copeland-Hardin et al. (+7 more)
Registering images acquired with different microscopy modalities is essential for relating complementary measurements of the same specimen. In correlative X-ray fluorescence (XRF) and optical microscopy, the XRF map often covers only a small region of an optical image acquired from the same or an adjacent tissue section. Field-of-view (FOV) localization is necessary but can be difficult when appearance and structure differ across modalities. Here we evaluate training-free
vision language model (VLM) localization on two
datasets representing same-section high-correspondence and adjacent-section low-correspondence imaging. We test unconstrained and metadata-constrained search and compare VLMs with
geometric controls, classical template matching, and two alternative training-free approaches (DINOv2 and multiGradICON). Direct VLM prompting produced content-dependent spatial signals but was not reliable alone. Classical matching was most accurate when cross-modal structure was preserved but failed in the low-correspondence collection. A proposal-and-verify workflow used repeated VLM predictions as candidates and image-based similarity to select the final location. This workflow recovered useful localization in the low-correspondence regime.
Read the full abstract ▾
All authors Xiangyu Yin, Tatjana Paunesku, Letonia Copeland-Hardin, Martina Ralle, Zichao Wendy Di, Si Chen, Gayle E. Woloschak, Barry Lai, Mathew J. Cherukara, Stefan Vogt
Artificial Intelligence
ComponentBench: Diagnosing Component-Level Failures in Computer-Use Agents
Tianchen Guan, Xinlei Lin, Royce Cheng-Yue et al. (+2 more)
Current evaluation of computer-use
agents is split between long-horizon workflow
benchmarks and atomic GUI-grounding tests. This leaves an under-instrumented middle layer: realistic component-centered interactions (e.g., toggle a button set) that are short enough to diagnose and rich enough to capture the burdens of modern interfaces. We present ComponentBench, a
benchmark and diagnostic pipeline for component-level evaluation of computer-use
agents on modern web UIs. ComponentBench is organized around a library-agnostic ontology of 97 canonical UI components instantiated as 2,910 programmatically verified tasks across widely used component libraries, paired with cleaned human reference trajectories that enable evaluation of both task success and interaction efficiency. Beyond task collection, we introduce a scalable pipeline for
auditing realized structural difficulty after implementation and synthesizing structured failure analyses across tasks and component families. Evaluating seven models – GPT-5.4, Gemini 3 Flash, GPT-5.4 mini, GPT-5 mini, Gemini 3.1 Flash-Lite, Qwen3-VL-235B, and UI-TARS-1.5-7B – across four observation and action spaces, we show that these design choices critically impact performance. Within a single shared harness, changing only the observation and action space shifts task success by more than 30% for the same model: GPT-5 mini falls from 83.1% with accessibility-tree observations to 48.9% with coordinate-only Pixel control. Moreover, even the fastest configuration takes 3.7x as long as the matched human reference, and spatial manipulations that are trivial for humans continue to challenge current
agents.
Read the full abstract ▾
All authors Tianchen Guan, Xinlei Lin, Royce Cheng-Yue, Xiangjun Wang, Shuyan Zhou
Computer Vision
High-Flux Count-Free Single-Photon 3D Cameras
Kaustubh Sadekar, Vivek K Goyal, David Maier et al. (+1 more)
Single-
photon cameras based on single-
photon avalanche diode (SPAD) technology are gaining popularity for 3D sensing, thanks to their extreme sensitivity and time resolution. There are two key challenges with single-
photon cameras that limit their widespread use: (i) they suffer from non-linear distortions called ”pile-up” when operated in high-
photon-flux conditions, and (ii) they generate a large volume of raw
photon data, creating a severe data bottleneck at each sensor pixel. In this work, we show that while compressive capture techniques successfully mitigate data transfer challenges, they exacerbate the effects of dead-time distortion because they fail to retain sufficient information about the
photon detection history to allow post-processing pile-up correction via existing methods. We propose a new computational-imaging method that combines free-running capture with an analysis-by-synthesis software pipeline to mitigate pile-up distortions. Our results with hardware emulations and full-scene and single-pixel simulations show that our method can reliably capture scene distance and reflectance over a wide range of illumination conditions. Our work will enable high-resolution SPAD cameras that are severely bandwidth-constrained to operate in real-world high-flux scenarios.
Read the full abstract ▾
All authors Kaustubh Sadekar, Vivek K Goyal, David Maier, Atul Ingle
Computer Vision
Acquisition Geometry-Assisted Whole-Group Localization of X-ray Fluorescence Maps in Optical Microscopy Images
Xiangyu Yin, Tatjana Paunesku, Letonia Copeland-Hardin et al. (+7 more)
X-ray fluorescence (XRF) microscopy maps elemental distributions, while optical microscopy can provide complementary morphological context. Localizing XRF fields of view (FOVs) in optical images is difficult because the two modalities differ in contrast mechanism and resolution. Most current workflows place each XRF tile independently, even when acquisition metadata already record the tiles' relative scan positions. This study formalizes XRF tile-group localization, in which one optical-frame placement is estimated for the whole group, constrained by acquisition geometry and quantified using group intersection-over-union (GroupIoU). In a controlled case study, independent localization failed with GroupIoU 0.000, whereas group localization achieved 0.931. Replacing the normalized cross-correlation (NCC) metric with mutual information (MI) gave nearly identical results, showing that the outcome is not specific to one local similarity metric. In another multiscale case study, using a coarse XRF survey scan to connect the fine-scale tile group to the optical image increased mean GroupIoU from 0.694 to 0.856. These case studies support using acquisition geometry as an explicit constraint when localizing related XRF tiles.
Read the full abstract ▾
All authors Xiangyu Yin, Tatjana Paunesku, Letonia Copeland-Hardin, Martina Ralle, Zichao Wendy Di, Si Chen, Gayle E. Woloschak, Barry Lai, Mathew J. Cherukara, Stefan Vogt
Artificial Intelligence
SESSE: Sketch, Expand, Sort, Summarize, Evaluate – LLM-as-Judge Evaluation via Structured Decomposition
Dae Lee, Mihai Delgeanu and Adel Youssef
LLM-as-judge evaluation reduces response quality assessment to a single holistic A/B preference choice, providing no mechanism to isolate which quality dimensions drove the preference or distinguish model errors from genuine label ambiguity. We propose SESSE (Sketch, Expand, Sort, Summarize, Evaluate), a training-free framework that decomposes holistic judgment into structured sub-questions mined directly from the judge's own error cases; requiring no oracle responses, task-specific rubrics, or fine-tuning. On RewardBench (n=1,000), SESSE achieves near-parity with the chain-of-thought baseline and is competitive with RISE-Judge-32B (92.7%), a fine-tuned specialist, while remaining fully training-free. Per-criterion vote evidence provides an interpretable audit trail for diagnosing label ambiguity and judge failure modes unavailable from a single holistic output
token.
Read the full abstract ▾
Artificial Intelligence
The Lifecycle of LLM-as-a-Judge for Large-Scale Recommendation Explanations
Emma Yanyang Kong, JJ Tan, Ishan Gupta et al. (+8 more)
LLM-as-a-Judge, which leverages a large
language model to evaluate natural
language generated by another AI application or model, has become a standard, scalable approach for accelerating and extending costly human evaluation. Yet most work treats a judge as a static artifact, evaluating it once at construction or against a fixed
benchmark. We argue instead that an LLM judge operating in a deployed system is better understood as having a lifecycle. It must be built, trained, deployed, and continuously maintained as the surrounding data evolves, and each phase poses distinct technical and operational challenges. We present such a lifecycle for the LLM judges that evaluate recommendation explanations at Netflix. Everything we report comes out of a series of controlled online member-facing experiments, in which our pipeline generated and the judges assessed hundreds of thousands of distinct show-level explanations per week across a changing catalog. Our framework has four phases. (I) Birth defines the evaluation criteria and builds curated
benchmark datasets with human labels and rationales. (II) Training refines the judges' rubrics via
Reasoning-Aligned Rubric Tuning (RART), which uses a meta-judge over
reasoning output as the learning signal. (III) Deployment puts one judge in two online roles, quality gating and reflective generation. (IV) Monitoring runs a continuous Human-in-the-Loop (HITL)
alignment process that detects drift and triggers re-tuning behind a human review gate. We report results from a five-week online A/B test over tens of millions of members on the Netflix mobile app, in which judge-aligned explanations shifted member viewing toward novel content (previously unwatched) and increased successful browse-to-play sessions relative to a no-explanation control, with no quality-related escalations.
Read the full abstract ▾
All authors Emma Yanyang Kong, JJ Tan, Ishan Gupta, Lars Olds, Claire Campbell, David Fagnan, Ratna Kavuri, Veli Balin, Rohan Gosain, Louis Garcia, Minsu Jang
Computers and Society
FairGlucose: A CGM Fairness Benchmark Reveals Subgroup Disparities Hidden in Population-Level Validation
Junjie Luo, Xuzhe Zhi, Rui Han et al. (+5 more)
As CGM-based AI tools approach clinical deployment, whether their accuracy is equitable across patient demographics remains insufficiently tested. To enable this evaluation, we constructed FairGlucose, a 300-patient CGM cohort balanced across 12 demographic strata (age x gender x type 1/type 2 diabetes), with 132,480
forecasting samples and 3,945 unique behavioral events (meals, exercise, medication) logged by 81 patients. Benchmarking 33 models across four families on 2-hour glucose
forecasting, we find that population-level external validation can conceal substantial subgroup disparities. Aggregate out-of-distribution metrics appear stable (approximately 1.0), yet subgroup-level ratios range from 0.8 to 1.4, with T1D patients showing 6 mg/dL higher prediction error than T2D (p < 0.001). This disparity persists across all 33 models, suggesting a property of the prediction task rather than any single architecture. Further analysis shows that subgroup performance gaps align with the proportion of clinically hard cases, and that input-length sensitivity varies across demographics, motivating personalized configurations. Frontier LLMs underperform specialized neural models by 1-6 mg/dL; behavioral events contribute negligibly (approximately 0.1 mg/dL) even under oracle event access. These findings establish that population-level validation alone is insufficient for equity assessment of digital health AI, motivating subgroup-disaggregated reporting as a default standard.
Read the full abstract ▾
All authors Junjie Luo, Xuzhe Zhi, Rui Han, Abhimanyu Kumbara, Anand K. Iyer, Mansur E. Shomali, Ritu Agarwal, Guodong Gordon Gao
Artificial Intelligence · Cross-listed from stat.ME
Debiased Inference for AI-Generated Data without Gold-Standard Labels: Identification via Multiple Imperfect Measurements
Naoki Egami and Sooahn Shin
An increasing number of scholars use AI to measure variables they subsequently include in downstream analyses. Although AI-measured variables are often analyzed as if observed without error, ignoring prediction errors in automated measurement leads to substantial bias and invalid confidence intervals in downstream analyses, even if AI measurement accuracy is high, e.g., above 90%. Existing solutions, such as design-based supervised learning and prediction-powered inference, combine error-prone AI-based measurements with gold-standard labels, which may be costly and difficult to obtain in some application areas. In this paper, we propose debiased inference with multiple imperfect measurements (DMM), a framework that combines multiple error-prone AI measurements to enable valid downstream inference without gold-standard labels. Building on the established results on CP decomposition, DMM assumes that these measurements are independent conditional on the latent true label and observed unit-level features, such as text features represented by
embeddings. This framework allows for unknown misclassification rates to vary across annotation methods (e.g., large
language models) and across units of annotation (e.g., texts). Under this assumption, we use semiparametric inference theory to prove that the DMM
estimator is consistent and asymptotically normal, enabling valid inference for a wide range of downstream statistical analyses common in the social sciences. Our simulation results show that DMM yields valid inference and that adding accurate, though imperfect, measurements can improve efficiency. Focusing on common applications of large
language model annotations, we also develop diagnostics to assess the conditional independence assumption.
Read the full abstract ▾
Robotics
GuideFetch: A Task Coordination Framework for Concurrent Navigation and Object Retrieval in Assistive Robot Dogs
Qian Yin, Ruiping Liu, Kunyu Peng et al. (+7 more)
Consider one
robot guide dog escorting a blind user to a seat while a second retrieves and delivers an object. We introduce GuideFetch, a framework for coordinating this concurrent guide-and-fetch mission with heterogeneous
robots. A large
language model (LLM) instantiates a schedule-conditioned four-action schema; deterministic normalization and validation enforce registered targets,
robot capabilities, and the selected schedule, while
robot and object states govern execution and completion. We record 360 simulator runs over 90 scene–seed combinations under scripted and online plan-provenance conditions. All 180 online responses validate on the first request and match their scripted references, so the plan-provenance comparison tests normalized-plan agreement rather than a distinct execution factor. A simulator-free mutation test accepts two valid controls and rejects all 32 rule-violating variants. Across 90 scene–seed cases per schedule, sequential and parallel execution achieve $72/90$ and $71/90$ operational successes. Among 56 common successes, the implemented role-reassigned parallel protocol reduces mean makespan by 41.3%. This system-level gain combines role assignment, action overlap, and scene geometry; state checks distinguish plan validity from verified mission completion.
Read the full abstract ▾
All authors Qian Yin, Ruiping Liu, Kunyu Peng, Jianxiang Man, Isik Baran Sandan, Junwei Zheng, Yufan Chen, Di Wen, Kailun Yang, Rainer Stiefelhagen
Artificial Intelligence
Evaluating Structured Information Extraction with Open Models in a High Risk Public Sector Application
Elias Schubert and Felix Bießmann
The extraction of structured information from unstructured documents represents a critical component of digital transformations in all sectors. While proprietary solutions dominate commercial applications, a rapidly growing ecosystem of open-source Optical Character Recognition (OCR) engines, Large
Language Models (LLMs), and
Vision-
Language Models (VLMs) offers accessible alternatives. However, systematic evaluations on realistic, multi-step extraction pipelines remain scarce. Responsible usage of such extraction tools require comprehensive evaluations on realistic tasks, especially as these solutions will be key components of applications in the public sector that the EU AI act categorizes as high risk. To address this gap we present a comprehensive
benchmark assessing the end-to-end performance of open-source systems on a complex real-world document processing task classified as high risk: Student applications for an international study program. We conduct a comprehensive empirical evaluation with state-of-the-art OCR engines, LLMs and VLMs. Our results reveal that while VLMs generally outperform OCR+LLM pipelines, even state-of-the-art open-source models struggle to handle such tasks reliably in zero-shot settings. Only 4 of 35 configurations achieved F1 scores above 0.5, with the best OCR+LLM pipeline matching top VLM performance, though most OCR+LLM combinations performed substantially worse. Roughly 75% of all configurations scored below 0.25. Model scale influences performance, yet the relationship is non-linear: substantially larger models do not guarantee proportionally better results. Input quality, particularly the structural preservation of OCR output, emerges as a critical factor independent of downstream model capability.
Read the full abstract ▾
Mathematical Software · Cross-listed from math.OC
Anytime Solver Evaluation with a Normalized Signed Primal Integral and Explicit Reference Policies - Extended Version
Florian Rascoussier, Romain Billot, Lina Fahed et al. (+1 more)
Anytime solvers return usable solutions before they terminate and improve them while time remains. Their progress is commonly summarized by a primal integral, a final gap, or convergence curves. Each summary leaves consequential choices open: how to score a run before its first feasible solution, whether poor incumbents are truncated, and whether the reference value is updated after the experiment or version-frozen beforehand. These choices become visible when runs produce no valid incumbent or improve a published best-known value. We study a normalized signed primal integral built from a bounded relative gap. It assigns an intrinsic worst value to an empty run, requires no acceptance threshold, and assigns negative instantaneous gaps to incumbents that beat a frozen reference. We compare the smooth difference-over-sum kernel with a signed version of Berthold's max-normalized gap and use the former as a working default. We also distinguish analysis-time from version-frozen reference policies and recommend reading the score with the raw final gap, mean convergence curve, and target-attainment curve. We evaluate these choices on a five-arm routing campaign and two model-fidelity ladders. The two signed kernels preserve every panel ordering in this study, whereas a common acceptance threshold compresses the distances between arms and reverses one panel ordering. Updating 54 of the 212 reference values changes score levels and removes all negative scores, while leaving the observed panel orderings unchanged. An exploratory screen also identifies 12 panel comparisons in which similar integral scores conceal materially different endpoints or attainment rates. The implementation, frozen inputs, and generators are openly released.
Read the full abstract ▾
All authors Florian Rascoussier, Romain Billot, Lina Fahed, Christine Solnon
Computer Vision · Cross-listed from eess.IV
QuARC-GS: Quantized Anchored Residual Coding for Compact Dynamic Scene Streaming with Gaussian Splatting
Vu Trung Nghia Nguyen, Yuchen Wang, Kyung Chul Lee et al. (+1 more)
3D scene representation techniques such as neural radiance fields (NeRFs) and Gaussian splatting have made substantial progress in novel view synthesis, achieving high-quality renderings from arbitrary view angles. More recently, such techniques have been extended to dynamic 3D scenes; however, achieving sustainable online free-viewpoint
video (FVV) streaming remains challenging, especially for longer
videos, due to significant storage demands of detailed scene representations and high reconstruction/rendering speed needs. To address these challenges, we propose Quantized Anchored Residual Coding Gaussian Streaming (QuARC-GS), a quantization-aware 4D scene optimization framework for online dynamic scene reconstruction that achieves ultra-high compression while maintaining reconstruction speed and quality. QuARC-GS represents a scene using a single canonical frame and highly compressed per-frame residuals. Specifically, we compress each residual through two complementary strategies targeting motion, appearance, and densification. We introduce quantization-aware anchor deformation, which suppresses insignificant motion updates while preserving meaningful deformations, maintaining reconstruction quality under low-storage streaming. Furthermore, we design a change-gated densification strategy that allocates new Gaussians only in regions exhibiting genuine temporal changes, effectively eliminating redundant appearance updates and reducing storage overhead. Extensive experiments on widely used
datasets demonstrate that QuARC-GS enables competitive reconstruction quality and training speed while cutting per-frame storage by up to 11$\times$ compared to the state-of-the-art.
Read the full abstract ▾
All authors Vu Trung Nghia Nguyen, Yuchen Wang, Kyung Chul Lee, Kevin C. Zhou
Machine Learning · Cross-listed from math.OC
Self-supervised In-context Operator Learning for Stochastic Mean-Field Control
Suyi Gao, Mo Zhou and Rongjie Lai
Stochastic mean-field control (MFC) provides a fundamental framework for coordinating large populations of interacting
agents under uncertainty, with a wide range of applications. Existing numerical and deep-learning methods solve one MFC problem instance at a time and must be re-optimized whenever the task changes. In this work, we formulate
stochastic MFC as an operator-learning problem and develop, to the best of our knowledge, the first mesh-free, self-supervised neural operator for
stochastic MFC. The main challenge is that the
diffusion term in the controlled Fokker–Planck equation precludes deterministic transport-map representations. We address this challenge by combining the probability-flow ODE with an invertible normalizing-flow-based
transformer, which recasts the dynamics as a deterministic continuity equation and enables closed-form score evaluation through the exact inverse and analytical log-determinant of the normalizing flow, with $\mathcal{O}(d)$ cost per particle for networks of fixed size. Through
transformer-based in-context learning, task
prompts, represented by compact distribution parameters or raw particle clouds, condition the transport map, enabling a single pretrained operator to solve unseen tasks in one forward pass. The resulting Normalizing Flow Invertible Solution
Transformer (NFIST) is trained end-to-end by minimizing the
stochastic control objective directly, requiring no precomputed numerical solutions for training. We further prove the consistency of the proposed operator-learning formulation with task-by-task optimization. Numerical experiments on
stochastic optimal control, Schrödinger bridge, systemic-risk control, and obstacle-avoiding path planning demonstrate effective zero-shot generalization while substantially reducing the computational cost of solving large families of
stochastic MFC problems.
Read the full abstract ▾
Software Engineering
What Makes Software Issue Resolution Tasks Difficult for Agents?
Ebtesam Al-Haque and Brittany Johnson
Background. Advances in agentic systems are simultaneously, and rapidly, saturating
benchmarks. Despite this often discussed phenomena,
benchmark scores remain difficult to interpret due to the lack of control and characterization of task difficulty. More specifically, we currently have little understanding of what makes one task harder than another, and to what extent task difficulty is predictable from static task properties. Aims. We propose a measurement framework to investigate and systematically quantify what structural properties of software tasks correspond to
agent success rates for issue resolution tasks. Method. We conducted a large scale empirical study on CoderForge-Preview, the largest open
dataset of coding
agent trajectories to date, by extracting features across task patch, repository and
prompt. We evaluated the predictive power of each feature against task outcomes using ensemble methods, SHAP attribution, and effect size analysis. Results We found that task difficulty is substantially predictable from static features (AU C = 0.863) and is largely driven by patch fragmentation and repository scale.
Prompt linguistic features become visible among top contributors for tasks in the mid-band, revealing a layered structure of difficulty. Conclusion. The difficulty of an issue resolution task is encoded in its structure. This enables static, pre-hoc difficulty estimation and lays the groundwork for difficulty-controlled
benchmark construction for evaluation of
agents.
Read the full abstract ▾
Machine Learning · Cross-listed from physics.optics
A Comprehensive Review of Large Language Models for Nanophotonics: From Surrogate Modeling to Autonomous Design
Huanshu Zhang, Kegeng Tang, Lei Kang et al. (+3 more)
Metasurfaces have revolutionized the development of photonic devices by enabling unprecedented precision in light manipulation. However, their design processes are often constrained by computationally expensive simulations and complex high-dimensional design spaces. Although deep learning has accelerated the design process by serving as a surrogate model, it remains constrained by task-specific architectures and lacks universal
reasoning capabilities. This review surveys how Large
Language Models (LLMs) are adding semantic interfaces, code generation, and tool orchestration to established numerical nanophotonic workflows. We first outline the development from classical neural networks to
transformer-based models and their applications in nanophotonic design. We then review the emergence of LLM-related methods in nanophotonics and organize them into two operational modes: surrogate models that treat structure-spectrum mapping as a
language task, and agentic systems that have been demonstrated to generate code, orchestrate selected simulation steps, and support closed-loop optimization. Furthermore, to identify future cross-disciplinary opportunities, we briefly explore applications of LLMs in research fields such as materials science and wireless communications. This review concludes by looking ahead to the next generation of
multimodal foundation models with physical perception capabilities. In this
vision, artificial intelligence is evolving from passive tools into active collaborators, participating in autonomous scientific discovery.
Read the full abstract ▾
All authors Huanshu Zhang, Kegeng Tang, Lei Kang, Sawyer D. Campbell, Zihao Wang, Douglas H. Werner
Cryptography and Security
Model Card for OpenAI Privacy Filter
Charles de Bourcy, Sahra Ghalebikesabi, Avi Schwarzschild et al. (+22 more)
OpenAI
Privacy Filter is a compact, bidirectional
token-classification model for detecting and redacting personally identifiable information (PII) and secrets in unstructured text. The model is derived from an autoregressively pretrained checkpoint and converted into a bidirectional, banded-
attention classifier that labels an input sequence in a single forward pass. A constrained Viterbi decoder produces coherent spans across eight
privacy categories and exposes configurable operating points for precision-recall tradeoffs.
Privacy Filter has 1.5 billion total parameters, 50 million active parameters per
token, and a 128,000-
token context window. It is designed for efficient local deployment and domain-specific fine-tuning.
Privacy Filter is intended as a configurable data-minimization component within layered
privacy workflows, not as an anonymization or compliance guarantee.
Read the full abstract ▾
All authors Charles de Bourcy, Sahra Ghalebikesabi, Avi Schwarzschild, Alex Gorbachev, Mihai Maruseac, Annie Chu, Vol Kyrylov, Tong Mu, Ally Bennett, Andy Nguyen, Casey Meehan, Jessica Gan Lee, Shane Bauer, Harold Nguyen, Rodolpho Eckhardt, Yuqi Liu, Charlie Oxborough, Marco Rougeth, Omar Chedid, Caio Costa, Yash Parikh, Yao Li, Congzheng Song, Om Thakkar, Vinnie Monaco
Artificial Intelligence · Cross-listed from physics.geo-ph
Yingjie Xu, Siwei Yu and Jianwei Ma
Classical seismic data reconstruction relies on manually designed structural priors and iterative operators, whose coupled design space is far larger than manual trial and error can explore systematically. Deep-learning methods encode the reconstruction rules in learned weights rather than in an explicit operator that can be inspected and modified. We propose SeisEvo (Seismic
Algorithm Evolution), which does not optimize a single reconstruction result but searches for the
algorithm that produces it. Starting from a classical reconstruction
algorithm, an LLM-driven multi-
agent search modifies only the components that the user has opened for editing, without prescribing the mechanism to be discovered. Candidates that violate the physical constraints of the task are rejected outright, and the remaining ones are scored by execution. The output is neither an
agent system nor a neural network, but a standalone white-box
algorithm that requires no
agent or neural network at inference time. For interpolation without added noise, the search discovered a residual-gated, phase-aligned dip-consistency projection; Evo-POCS improves the SNR over classic POCS by 3.49 dB on average across missing ratios from 30% to 70%. For simultaneous interpolation and denoising, it discovered a reliability-grouped singular-value shrinkage; Evo-MSSA improves the average reconstruction SNR by more than 7 dB over classic MSSA and by more than 3 dB over a stronger rank-reduction baseline. Both operators retain their gains on data not used during the search. To the best of our knowledge, this is the first study to formulate the design of a seismic reconstruction operator as a constrained, LLM-driven program
evolution task. Agentic
algorithm evolution can thus complement deep learning in discovering explicit, inspectable, and deployable seismic processing
algorithms.
Read the full abstract ▾
Machine Learning
Rethinking Privileged Information in On-Policy Self-Distillation
Samyak Shrestha and Alexander Tessier
On-policy self-
distillation (OPSD) trains a student on its own responses using
token-level supervision from the same model conditioned on privileged reference information. We investigate whether performance gains from OPSD show that the student learned the information in the reference or instead reflect recovery of
reasoning behavior already present in the base model. We perform OPSD experiments on science and mathematics
datasets using Qwen3 models ranging from 1.7B to 8B. Our analysis framework separates the supervision induced by the reference from the supervision provided by the teacher without the reference and measures how each aligns with changes in the student's predictions. The correct reference does not provide a consistent performance benefit across teacher generation modes, model sizes, and training
datasets. Students can improve without the correct reference, and a solution from another problem can outperform the correct solution on several mathematical
reasoning benchmarks. The student's predictions align more strongly with the base model's thinking behavior than with the supervision induced by the reference, but controls constructed from other problems reproduce much of both
alignments. Moreover, stronger
alignment attributable to the correct reference does not reliably coincide with a greater performance benefit from the reference. Performance gains and distributional
alignment alone therefore cannot determine how privileged reference information contributes to student learning in OPSD.
Read the full abstract ▾
Robotics
Transferable Tool-Tissue Contact Detection from Stereo Depth in Robot-Assisted Surgery
Mingyeung Wu, Zhonghao Zhang, Hao Yang et al. (+2 more)
Reliable tool–tissue contact detection can support interaction-aware control and downstream force estimation in
robot-assisted surgery. Most existing methods learn a contact classifier from RGB appearance, which is hard to generalize. In this work, we use the depth image generated from a stereo pair to give more information about tool–tissue contact. For each depth frame, we localize a spatially supported minimum-distance patch around the tool boundary and reduce it to a single scalar, $-\log_{10}|d|$; this signal rises and falls in step with ground-truth contact. We formalize this observation with a fully supervised two-state hidden Markov model. We fit this model as a six-fold leave-one-session-out (LOSO) ensemble on six palpation sessions against a single silicone cup-like phantom, with the decision threshold selected from the pooled out-of-fold predictions. It is evaluated on four held-out sessions of three categories: 1. same task on same phantom; 2. same task on different phantom; 3. different task on different phantom. This model reaches held-out macro F1 $0.927$ and AUPRC $0.980$. We further compare against a reproduction of an RGB-based contact classifier from prior work. This RGB-based model achieves high performance on the first category (F1 $0.965$), but substantially lower performance on the other two, resulting in macro F1 $0.320$ across all four sessions. These results indicate that the tool–tissue distance is a strong, transferable cue for contact detection in
robot-assisted surgery.
Read the full abstract ▾
All authors Mingyeung Wu, Zhonghao Zhang, Hao Yang, Alan Kuntz, Jie Ying Wu
Information Retrieval
Global Crises and National Policies: A Large Scale Analysis of Political Content in German Language Online Media
Yara Döring and Felix Bießmann
Today most media content is consumed based on algorithmic recommendations. Evidence suggests that this can lead to politically biased media consumption patterns. Automated extraction of political agendas from texts can reveal and analyze political biases in online media – and thus help fostering politically unbiased media consumption. Here we employ modern political text analysis methods demonstrating the potential of automated fine-grained political bias analysis in online media. We conduct an analysis of political content in German
language online media during the period 2019–2022, encompassing several million articles and tweets covering events with profound societal impact globally and nationally, the COVID-19 pandemic and the beginning of the war in Ukraine. Our analysis identifies thematic similarity between national (German and Swiss) reporting, particularly for categories driven by international events. We also find divergences emerging in domestically influenced categories, reflecting differences in national policies and institutional structures. A comparison of newspaper and Twitter discourse reveals that both media converge around a shared core during the pandemic, yet differ in intensity and temporal dynamics. Newspapers exhibit more stable political content, while Twitter reacts through short-lived event-driven spikes. These findings indicate that international crises act as a powerful synchronizing force on political content in classical media, temporarily overriding both national and media-form differences. Our automated political analysis empowers citizens by rendering political agendas in online media transparent. This transparency also enables media outlets to bridge the gap between
algorithm-driven echo chambers and a more informed, balanced public discourse.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from econ.TH
Modeling Human Behavior with Type Vectors Using AI
Matthew O. Jackson, Benjamin S. Manning, Yutong Xie et al. (+2 more)
We introduce a general, easy-to-implement AI-based modeling technique for analyzing human behavior. A key feature of this approach, which contrasts with existing modeling techniques, is that it combines the flexibility and interpretability of natural
language with a mathematical structure that can be fitted to data and easily analyzed. We assign a large
language model a vector of trait intensities-a type vector-and then ask it to choose actions across settings in which we observe human choices. For instance, the type vector (2,4) could correspond to "You are a player characterized by the following profile: Altruism: 2 out of 5, Risk Aversion: 4 out of 5," after which it is asked to make choices. We can then vary the traits (e.g., Altruism,
Fairness, Trust,...) and values (e.g., 1-5) to minimize distance to human choices. We illustrate the method by applying it to model 119,147 decisions made by 78,657 subjects from more than 35 countries across 10 classic economic game roles. We find that human behavior can be closely matched using three dimensions: Risk Aversion, Strategic Sophistication, and Trust. The type vectors needed to fit individuals across games cluster into fewer than a dozen groups, with substantial variation in fit across subjects. Moreover, the individual type vectors can predict behavior in held-out games with different rules and available actions. More broadly, this new modeling method is highly generalizable and interpretable: we can input any vector of traits and use them to model behavior across any setting
Read the full abstract ▾
All authors Matthew O. Jackson, Benjamin S. Manning, Yutong Xie, Walter Yuan, Qiaozhu Mei
Machine Learning
SIGMA: Symmetry-aware, Intelligent, Geometric, Multi-faced Adaptive Traffic Control for Reliable Intelligent Transportation Systems
Pratham Payra, Jagadish, Tanmay Sen et al. (+1 more)
Traffic signal control is a challenging sequential decision-making problem requiring a balance between throughput, vehicle delay
fairness, signal stability, predictable switching, and emergency vehicle prioritisation. Existing reinforcement learning (RL) approaches often rely on predefined objectives and offer limited adaptability to changing operational priorities. They may also generalise poorly across geometrically equivalent intersections. To address these limitations, SIGMA (
Symmetry-aware, Intelligent,
Geometric, Multi-faced Adaptive traffic control) is proposed as a multi-faced RL framework augmented with a large
language model (LLM) for dynamic objective adaptation and orientation-invariant policy learning. Natural
language emergency instructions are translated into priority vectors that guide a multi-faced actor-critic controller.
Symmetry-aware rotational augmentation supports transfer across homogeneous four-way intersections, while an offline-to-online learning strategy enables stable initialisation and adaptation to evolving traffic conditions. Structural properties concerning emergency service levels, graceful degradation under LLM failure, and sensitivity to traffic demand perturbations are established, alongside bootstrap-based statistical validation. Experiments in SUMO across four urban intersections modelled on Kolkata traffic scenarios compare SIGMA with fixed-time, actuated, and Deep Q-Network controllers. Reductions in average waiting times, emergency waiting times, and queue lengths are observed, alongside improved traffic throughput. Empirical reliability and ablation analyses further assess robustness to component failures and
geometric orientation. SIGMA integrates
language-guided objective adaptation, multi-faced policy learning, and statistical reliability assessment into an adaptive framework for intelligent traffic control.
Read the full abstract ▾
All authors Pratham Payra, Jagadish, Tanmay Sen, Tanujit Chakraborty
Numerical Analysis
Inverse Born series based neural operators
John C Schotland, Aseel Titi and Jenn-Nan Wang
The inverse Born series provides a general perturbative framework for representing nonlinear inverse maps between infinite-dimensional function spaces and has found numerous applications in inverse problems governed by partial differential equations and integral equations. Motivated by its operator-theoretic structure, we develop a systematic framework for constructing neural operators that approximate the operator expansions arising in the inverse Born series. Our approach combines the analytical representation of the inverse Born series with the expressive power of neural operators, yielding data-driven approximations of the nonlinear inverse map while preserving the underlying operator structure. The proposed framework is applicable to a broad class of inverse problems and is presented in a general functional-analytic setting. To demonstrate its practical performance, we consider two representative examples: inverse scattering and the Calderón (electrical impedance
tomography) problem. Numerical experiments show that the constructed neural operators accurately approximate the inverse Born expansions and produce high-quality reconstructions across a range of test cases. These results indicate that the proposed methodology provides an effective and computationally efficient approach for learning nonlinear inverse operators and suggests a promising direction for integrating classical operator expansions with modern neural operator architectures.
Read the full abstract ▾
Artificial Intelligence
Cacheable by Design? Training Mixture-of-Experts Routers for Locality Against the Edge Memory-Bandwidth Wall: A Pre-Registered Negative Result with a Systems Measurement Study
Shriniwas Ramesh Suram
Serving a 235B-parameter Mixture-of-Experts (MoE) model on a single 8 GB GPU is bottlenecked not by compute but by
memory bandwidth: decode must stream each
token's active experts from whichever tier holds them, and on consumer hardware most experts sit on an SSD far slower than RAM. We quantify this bandwidth wall on Qwen3-235B (Q4_K_M, 134 GB): measured decode is 0.44 tok/s warm, matching a bytes-per-
token / bandwidth model, while a batching scheme that should amortize one disk sweep instead collapses at batch 32 from paging thrash. We build llama-moe-trace, a zero-surgery router-telemetry tool, and measure routing on Qwen3-30B: adjacent-
token expert reuse is 2.0x chance, 95% of traffic uses 52.5% of experts, and an LRU cache of 13.4% of experts serves 66% of requests. We then ask whether cacheability is trainable: we pre-register training of 137M MoE
language models with auxiliary locality and domain router losses, under joint criteria on cache-miss reduction and perplexity. The mechanism works (misses down up to 60%; a 99% static-pin hit rate) but every configuration fails the pre-registered <=1% perplexity gate – miss reduction and quality are tightly coupled. Concurrent StickyMoE reports the same loss as near-free on single-domain sub-25M models; on multi-domain 137M we find the tax real. Our contribution is this pre-registered, stricter-criterion, multi-domain evaluation plus edge-serving measurements. A 340M rung shows the tax does not shrink with scale (it rises slightly). We further show training-free cache-aware rerouting stacks with trained locality – together ~80% miss reduction at <=3.4% perplexity at both sizes, far cheaper than either alone – while domain-primed prefetching does not help. All code, traces, and the pre-registration are released.
Read the full abstract ▾
Artificial Intelligence
Redakto - The Incognito Tab for LLMs
Saurav Kumar Saha, Tom Röhr and Felix Bießmann
Large
Language Models (LLMs) are being increasingly used in everyday applications. A major challenge in the context of LLMs or Artificial Intelligence (AI) in general is to ensure
privacy when using them, meaning that personally identifiable information (PII) is removed from any text that enters an LLM. These challenges have become more urgent with novel EU legislation. Uncertainty around LLM usage with respect to
privacy concerns in EU countries can be a major blocker for the speed of innovation and transfer from research to applications. Here we present Redakto, a tool that can be used for anonymizing text prior to feeding it to an LLM or other downstream text processing. We provide state-of-the-art functionalities for both redaction of PII but also when used for pseudonymization. These functionalities are exposed such that they can easily be used by end-users, through the Redakto web application, and by developers and researchers, via REST APIs and model context protocol (MCP) hooks. The implementation is fully open source, requires modest compute resources, and can be readily deployed on local hardware. In contrast to prior work and in order to better assess the quality of the anonymized texts, we conduct extensive empirical evaluations on textual data from legal and medical domain with respect to both
privacy and utility of the redacted texts. Our empirical results demonstrate that the texts anonymized with different redaction strategies achieve utility scores on par with the original texts, suggesting that anonymization with Redakto can be used for LLM tasks without substantial negative impact for the tasks we explored.
Read the full abstract ▾
Robotics
VERAGMIL: Virtual Environment for Scooping Granular Foods with Imitation Learning Models
Amanuel Ergogo, Diego Dall'Alba and Przemyslaw Korzeniowski
Robot-Assisted Feeding (RAF) systems are essential for assisting individuals with disabilities or motor impairments in eating tasks. Manipulating granular food items, such as rice and beans, poses significant challenges due to their dynamic physical properties. Learning from human demonstrations offers a promising solution, but acquiring high-quality demonstrations is complex. To address this, we present VERAGMIL, a framework that combines a high-fidelity simulator with an intuitive Virtual Reality (VR) interface for recording demonstrations and supporting different imitation learning methods. VERAGMIL provides a realistic environment for training RAF systems to handle granular materials, including
robots, sensors, and various food items with distinct physical characteristics. We evaluate VERAGMIL by training three imitation learning models, BC, BC-RNN, and BCQ, on granular scooping and transporting tasks using both VR interface and 3D space mouse demonstrations, comparing them with a human-expert baseline. The models are assessed on success rate, spillage, generalization to unseen food items, and task completion time. Results show that VR-based demonstrations significantly outperform 3D space mouse data, with BCQ achieving the best overall performance, particularly in reducing spillage and approaching human performance. These findings underscore the effectiveness of our framework for training RAF systems in granular material handling. The code for our framework is publicly available at: https://github.com/AmanuelErgogo/VERAGMIL.git.
Read the full abstract ▾
Robotics
GAPL: Grounded Action-effect Policy Learning for LLM-Based Trajectory Planning
Zhihong Cui, Hengyu Liu, Zhangkai Wu et al. (+5 more)
Trajectory planning for autonomous driving requires both high-level
reasoning and precise low-level control. Large
Language Models (LLMs) offer semantic-rich planning capabilities, however, their application is limited by hallucinated
reasoning, poor grounding in environment dynamics, and limited numerical precision in control. We propose GAPL (Grounded Action-effect Policy Learning), a unified framework that integrates LLM-based effect estimation, simulation-based effect grounding, and policy optimization into a closed-loop system. GAPL consists of three modules: (1) an LLM-based Effect Evaluator for structured multi-dimensional action-effect estimation; (2) a Simulation-based Effect Grounder that predicts dynamics-consistent effects from simulator rollouts; and (3) an Effect-Aware Decision Maker that grounds LLM effect estimates against simulation via a distiller to guide Proximal Policy Optimization (PPO)-based policy learning. Experiments on four Highway-env scenarios demonstrate that GAPL consistently outperforms baselines, achieving average reductions of {0.76, 0.86, 2.00} in collision rate, average displacement error (ADE), and final displacement error (FDE), and an average reward gain of 1.44.
Read the full abstract ▾
All authors Zhihong Cui, Hengyu Liu, Zhangkai Wu, Yushuai Li, Tianyi Li, Peiyuan Guan, Amir Taherkordi, Tor Skeie
Systems and Control · Cross-listed from math.OC
A Mode-wise Adaptive Observer for Autonomous Switched Nonlinear Systems
Juan Sereno and E.A. Hernandez-Vargas
In the digital twin paradigm, online parameter updating is essential. Unlike a static model, a digital twin must continuously adapt to the evolving dynamics of the system it represents. Adaptive observers, which jointly estimate states and parameters from online data, are therefore an increasingly important tool. In this work, we formulate a mode-wise adaptive observer for a class of autonomous switched nonlinear systems with switched unknown parameters. The main challenges are twofold: removing the disturbance that switching injects into the parameter-error dynamics and guaranteeing persistence of excitation over a finite-time window without relying on an input signal. To address them, we assign a dedicated adaptive observer to each mode, active only on its corresponding interval, which directly removes the zero-input disturbance caused by switching. We then introduce a finite-window persistence-of-excitation condition together with a minimum dwell-time condition, under which the parameter estimation error is contractive and the state estimation error is bounded within the active interval of each mode. The performance of the proposed approach is illustrated with an academic example and with a practical example of evolutionary therapies.
Read the full abstract ▾
Computer Vision
Visual-Prompt Guided Wildlife Instance-Level Recognition
Mufhumudzi Muthivhi, Jiahao Huo, Terence van Zyl et al. (+1 more)
Fine-grained wildlife re-identification remains a challenging area in research. Current state-of-the-art approaches apply a detection and re-identification pipeline. We propose a one-stage end-to-end detection and re-identification model that performs identity searching within the latent space. We adopt DINOv2 for robust spatial geometry and MegaDescriptor for wildlife re-identification. We enhance latent queries with
prompt re-identification features. A detection decoder queries the scene latent space to establish object boundaries around the target identity. Preliminary findings reflect a competitive mean average precision score of 30.584% compared to the state-of-the-art two stage approach of 44.89%. Qualitative results depict effective bounding and identification of animal identities.
Read the full abstract ▾
All authors Mufhumudzi Muthivhi, Jiahao Huo, Terence van Zyl, Fredrik Gustafsson