Computer Vision
Keep Your Friends Close, and the Right Neighbours Closer: Disaster-Conditioned Kernel-Regularized Graph Attention for Building Damage Classification
Fuad Hasan and Chul Min Yeum
Disaster damage is spatial: buildings rarely fail in isolation. Yet using spatial context for damage classification remains surprisingly underexplored, and many pipelines still rely primarily on per-building appearance cues even when the dominant uncertainty is spatially structured. Complicating matters, the right neighbourhood is not the same across events. Floods, hurricanes, and wildfires can exhibit very different clustering behaviour, making spatial
reasoning valuable but easy to misuse - naive context aggregation can improve visual coherence while oversmoothing boundaries or propagating structured errors. We study this tension on xBD (the
dataset used in the xView2 challenge) in a controlled post-localization, classification-only setup: each building is represented by a pre/post combined (PPC) patch cropped from the provided polygons, and spatial context is modelled with GPS-derived building graphs. Our approach keeps local evidence "close" by preserving strong spatial relationships in disaster damage patterns, while bringing only the right neighbours "closer" through a disaster-type-conditioned graph model that injects a learnable multi-scale spatial kernel prior into
attention, allowing the effective neighbourhood scale to adapt across disaster types rather than being learned as a single global smoothing rule. To discourage coherence-by-smoothing, we add a residual de-correlation loss that penalizes positive Moran's~I in prediction residuals. We evaluate the method under event and
dataset shift with a leave-one-event-out (LOEO) protocol on xBD and cross-
dataset transfer from xBD to Ida-BD. The model improves macro-F1 and substantially reduces residual spatial autocorrelation under zero-shot event shift, indicating better use of spatial context rather than naive smoothing and enabling more reliable transfer to unseen events within known disaster types.
Read the full abstract ▾
Robotics
Koala Gripper: Co-designing Robotic Grippers and Data-Capture Devices for Scaling Dexterous Manipulation Learning
Amar Hajj-Ahmad, Zubin Kremer Guha, Tim Fofonoff et al. (+8 more)
As the demand for larger manipulation
datasets grows, handheld robotic gripper data collection and the associated gripper designs become more vital. Current data collection device designs trend towards matching the morphologies of existing robotic grippers, sacrificing ergonomics and manipulation performance. In this paper, we propose a co-design framework that guides the simultaneous development of both data collection and robotic execution devices by weaving both platform constraints into the design process. Through this workflow, we present the Koala Gripper system, a data capture device and robotic gripper platform that improves dexterity and grasp capability compared to parallel jaw grippers while preserving scalability and ease-of-use. The design introduces a novel force-optimized finger/trigger linkage mechanism with directional reflected mass characteristics, a unique monolithic dual-thumb, and user-centered ergonomic design. The design's actuated robotic fingers are backdrivable, with effective mass on the order of tens of grams. We show that these grippers are capable of secure grasps over a wide range of objects, forceful tool use, and precise singulation. We further validate the platform by deploying it with an end-to-end data collection and policy execution pipeline that highlights its capabilities through learning from demonstration. More information available at http://koalagripper.rai-inst.com
Read the full abstract ▾
All authors Amar Hajj-Ahmad, Zubin Kremer Guha, Tim Fofonoff, Zhi Ern Teoh, Ciarán T. O'Neill, Ben Thacher, Igor Fala, Vidullan Surendran, Murphy Wonsick, Peter Whitney, David Watkins
Systems and Control
AoI-Oriented Globally Optimal Joint Source and Update Scheduling in Fluid Antenna Systems
Xiaopeng Yuan, Paul Zheng and Anke Schmeink
As a promising technique, fluid
antennas enable adaptive
radio environment management and interference mitigation through reconfigurable fluid port selections. In this work, to explore the benefits of fluid
antennas for data freshness enhancement, we consider a fluid-
antenna assisted status update system supported by multiple source nodes monitoring the same environmental status. We assume a subset of the source nodes are activated to report status updates with different periods. Each user is assigned to one source node and equipped with an fluid
antenna to adaptively enhance the channel gain to assigned source node while mitigating interference from other activated source nodes. With maximal signal-to-interference-noise ratio (SINR)-based fluid port selection at all users, we formulate an optimization problem to minimize the maximum average age of information (AoI), where source node activation and assignment, i.e., source scheduling, is jointly optimized with the update periods of all activated source nodes. To optimally solve the resulting mixed-integer nonlinear problem, we first consider given source scheduling decision and apply performance achievability analysis. Aided by fixpoint theory, we propose an efficient bisection
algorithm for optimal update scheduling. Based on these characterizations, we further propose a filtering
algorithm which efficiently eliminates all non-optimal source scheduling decisions. The globally optimal joint solution is then obtained by combining the resulting optimal source scheduling with its corresponding optimal update scheduling. Numerical results validate the optimality of proposed solution and demonstrate the effectiveness of fluid
antennas in enhancing data freshness.
Read the full abstract ▾
Computers and Society
ExploraTwin, a Non-Profit Research Platform for Digital Twin Simulations
Naveen Venkat, Yuchen Qiu, Tianyi Peng et al. (+2 more)
Digital twin simulations show promise, but current empirical evidence suggests that the approach should be tested before being deployed in any particular context. To lower the friction for researchers and practitioners to test and deploy digital twin simulations, this brief commentary introduces ExploraTwin (https://exploratwin.org), an open-access, non-profit research platform for digital twin survey simulations. ExploraTwin supports two modes. In survey mode, researchers can upload a Qualtrics survey file or create a survey within the platform; select an available sample of digital twins; configure and run the simulation, and export analysis-ready data. In panel mode, researchers can assemble a small group of twins for open-ended conversations, document annotation, and moderated, focus-group-style voice discussions. We also developed CroissantTwin, a standardized data format for adding samples of digital twins to the platform. We demonstrate the survey mode workflow by using the platform to replicate 19 experiments on digital twins from the Twin-2K-500
dataset. ExploraTwin's survey execution fidelity is high: 99.6% of 197,000 answer units returned a structurally valid response on the first run.
Read the full abstract ▾
All authors Naveen Venkat, Yuchen Qiu, Tianyi Peng, George Gui, Olivier Toubia
Computer Vision
Grounded-Exo2Ego: Structured Semantic Grounding for Robust Exocentric-to-Egocentric Video Generation
Shengze Wang, Michael Stengel, Tianye Li et al. (+5 more)
Generating
egocentric video from a single exocentric
video is an emerging and important topic for AR/VR and physical AI. Compared with conventional novel view synthesis, exo-to-ego generation is a significantly harder task because the standard
geometric conditioning becomes highly unreliable under extreme view changes and large unobservable regions. We present Grounded-Exo2Ego, a principled framework that addresses these challenges at both the architectural and data levels. Architecturally, Grounded-Exo2Ego is a dual-branch
video diffusion model that couples a
geometric anchoring branch, which conditions the generation on the rendering of a 3D reconstruction, with a novel semantic grounding branch, which goes beyond the prevailing geometry-based approach and improves quality by synthesizing challenging regions based on object-level context. Additionally, we found that the overlooked issue of camera-reconstruction misalignment severely undermines exo-to-ego learning. We thus introduce a camera re-localization
algorithm that resolves this issue and substantially improves quality across all metrics. We further develop a fully automated synthetic data engine that generates and renders rigged 3D characters in procedurally generated environments. Evaluation on the challenging EgoExo4D
dataset shows that our method outperforms recent state-of-the-art approaches by large margins across all metrics. Detailed ablations validate improvements from each of our contributions at both the data and architectural level.
Read the full abstract ▾
All authors Shengze Wang, Michael Stengel, Tianye Li, Seonwook Park, Amrita Mazumdar, Koki Nagano, Alex Trevithick, Shalini De Mello
Machine Learning
Learning Exact NVIDIA SASS Encoders with $\mathbb{F}_2$ Linear Algebra
Jiading Gai
NVIDIA provides a SASS disassembler but no public SASS assembler for recent data-center GPUs, limiting controlled machine-code rewriting. We present F2Asm, which learns exact 128-bit SASS encoders from paired disassembly and original CUBIN instruction words. To our knowledge, F2Asm is the first system to learn SASS instruction encoders as vector-valued affine maps over $\mathbb{F}_2$ and the first open-source NVIDIA SASS assembler to support Rubin SM107. F2Asm uses Gaussian elimination over $\mathbb{F}_2$ to incrementally build a compact basis, detect inconsistencies, and reject inputs outside the learned span. F2Asm separates target-specific control bits, relocation rules, and CUBIN metadata from its learning
algorithm. We train encoders for Hopper SM90/SM90a, Blackwell SM100, and Rubin SM107 using 3,225 CUBINs from pinned NVIDIA and third-party production libraries, CUDA 13.3 packages, and CUDA 13.4 Developer Preview archives. In round-trip tests, F2Asm reassembles each CUBIN's disassembled SASS, and all compared executable text sections match the originals exactly. Joint training with F2Asm yields one shared encoder for five Blackwell SM targets and another for three Rubin SM targets, providing strong evidence of a common SASS encoding scheme for instructions shared within each family. Continual training extends the Rubin encoder to all 17,159 previously unsupported cuTile and GROMACS queries with 1,504 additional basis rows, matching the derived lower bound.
Read the full abstract ▾
Numerical Analysis
Nyström method for symmetric indefinite matrices
Yijia Chen, Yuji Nakatsukasa, Anjali Narendran et al. (+1 more)
The Nyström method approximates $A\approx A(\,:\,,I)A(I,I)^{\dagger} A(\,:\,,I)^{\top}=CA(I,I)^{\dagger} C^{\top}$, where $C:=A(:,I)\in\mathbb{R}^{n\times r}$ is a column subset
matrix of $A$. When applied to symmetric but indefinite
matrices, the Nyström method can fail because the core
matrix $A(I,I)$ may severely underestimate the
eigenvalues of $A$ and may become (nearly) singular. We address this issue by developing and analyzing an
algorithm that carefully chooses $\widehat{M}\in\mathbb{R}^{r\times r}$ in place of $A(I,I)^\dagger$ by solving the two-sided sketched least-squares problem $\min_{M}\|X(A-CMC^{\top})X^{\top}\|_F$, where $X\in\mathbb{R}^{t\times n}$ is a random sketch
matrix. We study in detail the cases where $X$ is a Gaussian or a leverage score sampling (LSS)
matrix, and show that with oversampling $t>r$ the residual $\|A-C\widehat{M}C^{\top}\|_*$ is comparable to $\min_{M}\|A-CMC^{\top}\|_*$. For the Gaussian sketch, we require $t=\mathcal{O}(r)$ samples; for LSS, we show that $t=\mathcal{O}(r \log r)$ samples suffice for the theoretical guarantee, with the LSS approach carrying the advantage that once a set of $t$ row indices is identified, the approximation requires only $t^{2}$
matrix-entry evaluations to find $\widehat{M}$, given $C$. We illustrate our results with synthetic examples and applications to kernel methods.
Read the full abstract ▾
All authors Yijia Chen, Yuji Nakatsukasa, Anjali Narendran, Taejun Park
Computation and Language
LiLiCorr: Lightweight Likelihood Correlation of Parallel Drafts for Speculative Decoding
Matan Rusanovsky, Yoav Miron, Roy Uziel et al. (+5 more)
Speculative decoding accelerates
language-model inference by drafting future
tokens the target model verifies in parallel. A
diffusion-style drafter such as DFlash drafts an entire block in one forward pass. It is trained on the per-position marginals rather than on the joint distribution over the block, so the
tokens it emits are individually plausible yet jointly incoherent. We introduce LiLiCorr, a Lightweight Likelihood-based model that Correlates the per-position marginals such a drafter produces. It keeps the top-K
tokens at each position and processes them jointly, emitting an in and an out vector for each. Two candidates at consecutive positions match when the earlier out vector aligns, in cosine similarity, with the later in vector. Training scores the correct pairings highest and pushes competing ones down, so coherent blocks outscore incoherent ones. The joint distribution over the block, exponential in its length, is never materialized. One lightweight network pass produces all the vectors, the pairwise scores follow as batched
matrix operations, leaving only a cheap greedy walk sequential. We co-train the DFlash drafter with LiLiCorr, so it proposes candidates that correlate into longer accepted sequences. Over the vanilla DFlash drafter it builds on, LiLiCorr accepts more and serves faster at all 72 settings we test: nine
benchmarks at two target sizes under greedy and temperature-one decoding, plus a throughput sweep over six concurrencies, two input lengths and three output-
entropy tiers. It raises acceptance length by 7 to 19%, while its single-pass scoring head costs only about 3% of the per-block latency. Against three concurrently developed methods that also restore coherence at draft time, all equally optimized on a common stack, LiLiCorr holds the highest throughput in 63 of those settings, ties within a measured noise floor in 6, and trails in only 3.
Read the full abstract ▾
All authors Matan Rusanovsky, Yoav Miron, Roy Uziel, Omer Belhasin, Hao Guo, Ran Zilberstein, Maor Ashkenazi, Michael Elad
Databases
Bolo: Verified Model Hub for Next-Generation AI Databases
Yunqi Li, Ila Petrovic and Yongjoo Park
Verified, ready-to-use inference pipelines are a cornerstone of future AI databases. They allow multi-modal databases to incorporate specialized
language,
vision, and tabular models that can deliver both high accuracy and efficiency. Unfortunately, existing model platforms such as Hugging Face fall short of this goal. While they host millions of model repositories, many contain only raw weights without runnable pipelines. Even well-documented models often fail due to missing dependencies, unsupported model classes, or incorrect task assignments. Moreover, different models fail for different reasons, with no uniform solution. Constructing a large-scale, verified model hub is nearly impossible with human effort alone. We argue that AI
agents can achieve this at scale. We present \system, a model platform that hosts verified, ready-to-use inference pipelines, powered by a multi-stage agentic system for model remediation. For models that fail under standard usage, the
agent inspects errors and repairs broken pipelines (Type~I). For models outside the scope of existing interfaces, it synthesizes pipelines from scratch using model metadata and documentation (Type~II & III). To prevent incorrect pipelines from entering the database, the
agent applies multi-stage verification—checking not only program structure but also semantic model behavior, ensuring pipelines produce meaningful outputs rather than merely executing without error. In preliminary experiments, \system achieves 97.27% and 86.08% runnable coverage for Type~II and Type~III models, respectively, demonstrating that agentic synthesis with targeted verification can transform large collections of unusable model weights into a verified database of ready-to-use inference pipelines. The preliminary database is open-sourced at \textcolor{blue}{https://bolobao.ai/}.
Read the full abstract ▾
Computer Vision · Cross-listed from eess.IV
Frozen CLIP Priors for Robust Self-Supervised Poisson Inverse Problems
Laura C. Diaz-Delgado, Emmanuel Martinez and Henry Arguello
Self-supervised learning for imaging inverse problems is increasingly important in
photon-limited settings, where acquiring clean ground truth is impractical and reconstruction must remain stable under
dataset and acquisition shifts. This challenge is amplified under Poisson noise, whose signal-dependent statistics interact with sampling operators (e.g., CFA mosaicing). Meanwhile, foundation
vision encoders trained at web scale offer distortion-invariant, content-related representations that generalize well across domains, suggesting a promising route to build priors that transfer beyond the training distribution without expensive fine-tuning. This paper proposes an ADMM-inspired unrolled plug-and-play solver for Poisson inverse problems that decouples a closed-form data-consistency update from a parameter-efficient prior. The prior is implemented as a lightweight decoder operating on frozen CLIP RN50 dense multi-scale features, adapting foundation representations with less trainable parameters. For self-supervision, the method integrates GR2R measurement-domain re-corruption with an Equivariant Imaging regularizer via virtual acquisitions. Experiments on Poisson CFA demosaicing and deblurring show competitive quality, improved robustness under shifts, and self-supervised performance approaching supervised training.
Read the full abstract ▾
Human-Computer Interaction
Me Among Us: Affective Framing in Data Donation
Zeya Chen and Zach Pino
This study investigates how different framing approaches influence the affective aspects of data donation decision-making. Although framing effects are well studied in charitable giving, how affective framing shapes data donation, especially through data visualization, remains poorly understood. Using a theoretical framework based on the functions of affect in decision-making, we examine how three distinct framing approaches, an individual-donor lens (Group A), an individual-collective lens (Group B), and a collective-institutional lens (Group C), shape participants' affective experiences and subsequent donation decisions. Through a real-world data donation study (N=24), we found that framing designs substantially influenced donation outcomes, with the individual-collective lens generating the most favorable responses. Our analysis illustrates how affect can functions as information, motivation, and as a spotlight during the decision-making process, providing insights for designing more informed data donation interfaces and communications. This research contributes to understanding the complex interplay between framing designs, affective responses, and decision outcomes in data donation contexts.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from physics.ed-ph
Large Scale AI Grading of Handwritten Physics Assessments: Score Agreement and Olympiad Team Selection Outcomes
Praveen Pathak, Siddharth Tiwary, Charudatt Kadolkar et al. (+4 more)
Multimodal AI can read handwritten physics solutions, but high-stakes grading requires agreement with official scores and outcomes. This study evaluated GPT-5.5-based grading on 10364 scanned pages from 520 handwritten submissions by 416 unique candidates or students across three assessments: a national Physics Olympiad theory examination, the final Olympiad selection camp with theory and experiment components, and a university
quantum-mechanics examination. Each submission was graded twice by AI using the official rubrics. The second round used revised page-by-page and evidence-location instructions developed after first-round disagreement analysis. During grading, AI did not see official human marks or AI–human comparisons. Total-score correlations with official marks were high (0.91–0.97). For the final Olympiad selection, AI recovered the same five-student team as official grading. The second round improved aggregate question-part agreement, especially where first-round disagreements were larger. The main difficulty remained exact partial-credit grading, especially in experimental work. Reliable AI grading therefore depends on detailed rubrics and should be used as a second reader or audit tool under examiner control.
Read the full abstract ▾
All authors Praveen Pathak, Siddharth Tiwary, Charudatt Kadolkar, Vijay Singh, David Rakestraw, Shirish Pathare, Anwesh Mazumdar
Artificial Intelligence · Cross-listed from physics.med-ph
An integrated diffusion-weighted imaging processing and interpretation platform for MR-guided radiotherapy
Yunxiang Li, Yan Dai, Yen-Peng Liao et al. (+3 more)
Background:
Magnetic resonance imaging-guided linear accelerators (MR-Linacs) allow
diffusion-weighted imaging (DWI) to be acquired at every treatment fraction, but converting these low-signal-to-noise-ratio acquisitions into clinical decisions requires both reliable quantitative processing and an interpretation that reconciles a scattered and often contradictory literature. Purpose: To describe and evaluate an integrated, web-based platform that carries raw MR-Linac DWI to a structured, literature-grounded clinical interpretation, and to assess its
retrieval-augmented generation (RAG) interpretation module by independent expert rating. Methods: The platform couples a deep-learning processing pipeline, comprising distortion correction, denoising, and intravoxel incoherent motion (IVIM)/apparent
diffusion coefficient (ADC) fitting, with longitudinal region-of-interest analysis and a RAG interpretation
agent. The
agent reasons over a two-layer knowledge base of curated publications (a structured catalog index plus line-indexed full text), delegates arithmetic to deterministic tools, and is designed to trace each statement to a source document, section, and line range. One medical physicist and one physician independently rated the
agent's reports for nine longitudinal glioblastoma cases on a 1-5 scale across three metrics: clinical-
reasoning soundness, literature-citation quality, and overall clinical utility. Results: Across 54 ratings, the pooled mean was 4.65 +/- 0.80, with 93% of ratings >= 4; metric means were 4.6 (
reasoning), 4.5 (citation), and 4.8 (utility), and raters agreed within one point on 85% of paired ratings. Conclusions: A single platform can integrate MR-Linac DWI post-processing with traceable, expert-evaluated clinical interpretation, while highlighting the safeguards needed to verify LLM-generated
reasoning in radiation oncology.
Read the full abstract ▾
All authors Yunxiang Li, Yan Dai, Yen-Peng Liao, Jie Deng, Jill B De Vis, You Zhang
Artificial Intelligence
FL-MAESTRO: Multi-Agent LLM Orchestration for Resource-Constrained Federated Learning
Jiajun Wu, Zirui Wang, Jiayu Zhou et al. (+2 more)
In
Federated Learning (FL), the communication
topology is a runtime variable rather than a fixed design choice, since links and edge devices drop in and out during training. Each round, the server must commit three coupled decisions, namely the communication
topology, per-client resource allocation, and the aggregation rule for combining local updates. Recent agentic systems have begun bringing large
language models (LLM) into FL, but the existing line of work either operates at setup time or handles a single runtime dimension such as client selection. We propose FL-MAESTRO, a multi-
agent orchestrator that makes the joint runtime FL decision directly through three specialist LLM
agents, one per decision dimension. A coordinator combines their analyses into a single decision, and a non-LLM feasibility check confirms it before the round executes. Because the orchestrator consumes the server's predicted-failure list, it withholds clients whose updates would never be aggregated, which removes the dominant source of wasted round energy in classical FL on volatile edge networks. Because client state is read as natural-text profiles, the same orchestrator extends to heterogeneous device classes without per-class energy models. On a non-IID CIFAR-10
benchmark, FL-MAESTRO matches the accuracy of the strongest energy-aware baseline while cutting wasted round energy from over a third to near zero. Code is available at https://github.com/denoslab/FL-MAESTRO.
Read the full abstract ▾
All authors Jiajun Wu, Zirui Wang, Jiayu Zhou, Qiang Ye, Steve Drew
Machine Learning
When Graph-JEPA Learns the Wrong Thing: Diagnosing and Repairing Category-Conditional Collapse
Gollam Rabby and Sören Auer
Joint-
embedding predictive architectures are selected almost universally by linear probing and effective rank. We report a case where both read healthily while the representation carries zero usable instance information. We repair it, and a second failure appears: the repaired metric saturates on a target carrying no structural information. Our corpus is a scientific-
reasoning graph over 57,903 articles, each a subgraph. A Graph-JEPA predicts one masked aspect from a subgraph's remaining aspects, attaining linear-probe accuracy 0.871 and effective rank 18-47, yet
retrieval recovers 0.00 of 14.4 bits (MRR 1.9e-4 vs chance 1.99e-4, p=0.98). Three upper bounds on the same pool and code recover nearly everything (+14.28, +14.34, +14.22 bits), ruling out corpus, masking, pool, and metric as causes. We trace this to variance allocation - frozen inputs place 86.05% of variance on subgraph identity and 0.40% on aspect identity, while trained latents place 0.39% and 99.61%. This is a property of the objective's optimum: the degenerate solution is a global minimum of the coupled predictor/EMA-target objective, present already at init. A repaired configuration reaches 14.377 of 14.379 bits, above the 13.865-bit oracle; reverting the loss to regression drops it to 0.307 bits, confirming it. Yet the repair licenses nothing about
reasoning: the target is reducible, since intra-subgraph edges are a deterministic function of node census. The oracle reaches 96.4% of the ceiling, and our largest effect is the learning-rate schedule, not architecture. Bits and a
reasoning probe show no relation across ten
cells. A data-derived target fails a quality gate - 25.96% of nodes are duplicate placeholders, and the rest is more generic than supporting evidence. Rank, probes, and metrics can all saturate on an unsupportive evaluation. We release a harness with a reducibility audit and target gate.
Read the full abstract ▾
Computer Vision
Wenzhuo Ma and Zhenzhong Chen
Generative
video compression can recover rich visual details at low bitrates, but simultaneously achieving high temporal consistency and low inference cost remains challenging. To address this issue, we propose DiffVC-ONE, a
diffusion-based generative
video compression framework built on a one-step
Video Diffusion Transformer. First, we introduce a Unified Unidirectional Latent Compressor that uses a shared model to efficiently and uniformly compress compact latent slices. We then develop a
Video DiT-based One-Step
Diffusion Enhancer that uses the reconstructed latent slices as content anchors and performs single-step spatio-temporal perceptual enhancement over an entire group of pictures. Finally, a Hybrid Condition Generator extracts structural, strength, and semantic conditions from the reconstructed content and quantization information. These conditions preserve faithful regions, control the degree of generative enhancement, and supplement content-aware perceptual details during one-step
diffusion enhancement. Extensive experiments on multiple standard
benchmarks demonstrate that DiffVC-ONE achieves state-of-the-art perceptual quality and temporal consistency with low inference cost.
Read the full abstract ▾
Software Engineering
Making Deployments Safe at Meta: Health Checks for Continuous Change-Safety
Prakash KL, Anton Korenkov, Uttam Thakore et al. (+1 more)
Continuous deployment to large scale production systems creates a tension between release velocity and reliability. Every change is a potential reliability incident, yet every delay is a missed opportunity. This paper describes the deployment time health check infrastructure that Meta uses to mediate this tension across thousands of heterogeneous services. We summarize the architecture of this prevention based distributed system's service called Service Health Checker, explain how check authors compose templated metric queries, thresholds, and workflow predicates; and discuss how the system is integrated with tiered and phased rollouts so that regressions trigger automatic rollback. We then describe the operational problems that emerged at scale, such as noise, alert fatigue, drift, and uncovered regressions, and the program of measurement, tooling, and improved defaults we deployed to address them. We close with lessons learned from years of operating deployment health checks at Meta, and the directions we are exploring next, including AI assisted health check tuning. Index Terms: deployment safety, continuous deployment, monitoring, software reliability, release engineering, software reliability engineering, AIOps, anomaly detection
Read the full abstract ▾
All authors Prakash KL, Anton Korenkov, Uttam Thakore, Christopher Hegre
Computers and Society
From Urban Mobility to Epidemic Dynamics: A Mixture-of-Experts Framework with Preference Alignment for Policy Scenario Simulation
Yun Ye, Arsalan Dezhkam, Junyuan Liu et al. (+2 more)
Non-pharmaceutical interventions (NPIs) alter epidemic risk through behavioral reallocations, not simply aggregate mobility reductions. Scenario-based NPI analysis therefore requires a behavioral layer that translates alternative policy calendars into plausible activity and mobility trajectories before downstream outcomes are simulated. We introduce UrbanShare-MoE-PA, a data-driven
agent-level framework that maps factual and alternative NPI calendars to daily time-allocation trajectories and propagates them through a calibrated behavior-driven SEIR simulator. The behavioral engine decomposes each
agent-day into travel share, POI-category allocation conditional on staying, and travel-mode allocation conditional on traveling. It combines a structured UrbanShare baseline, mixture-of-experts heads for heterogeneous POI and mode responses, and phase-aware preference
alignment for calendar-conditioned rollouts. Using data from 911
agents in Singapore observed from March to August 2020, we evaluate factual reconstruction, four alternative lockdown calendars, and epidemic-activity trade-offs. UrbanShare-MoE improves POI reconstruction over the baseline, while UrbanShare-MoE-PA achieves the lowest travel-mode errors and the clearest alternative-calendar trajectories. In the calibrated SEIR simulation, early lockdown lowers infectious burden, late lockdown increases it, and short lockdown preserves the highest weighted activity with only a modest increase in epidemic burden relative to the original policy. These results show that epidemic-activity conclusions depend on how policy calendars are translated into behavior, and that
agent-level mobility-share modeling provides an interpretable bridge between policy timing, behavior, and downstream simulation.
Read the full abstract ▾
All authors Yun Ye, Arsalan Dezhkam, Junyuan Liu, Xinglei Wang, Tao Cheng
Artificial Intelligence
A Temporal Planning Approach for Intelligent Flood Response
Fazlul Hasan Siddiqui, Md. Monjurul Islam and Sabah Binte Noor
Effective response to multiple, simultaneously flooded areas requires coordinating appropriate actions in the correct temporal order, under severe resource constraints. Automated planning provides a foundation for addressing this challenge by generating time-aware schedules, given a formal description of available resources, constraints, and goals. This work presents an intelligent flood-response framework that exploits temporal planning and models the complete operational life cycle of flood response. The framework incorporates priority-driven triage, route accessibility and travel costs, resource allocation, and supply management, while also supporting mid-execution re-planning in response to unexpected environmental changes. The framework is formulated both in the Action Notation Modeling
Language (ANML) and the Planning Domain Definition
Language (PDDL) 2.1, facilitating compatibility with a wider range of temporal planners. Experimental results establish the feasibility and scalability of the proposed framework, showing that flood response scenarios can be effectively modeled and solved using temporal planning, while providing guidance on planner selection.
Read the full abstract ▾
Networking
Making Time-Sensitive Networking Deployable: A Comprehensive Lifecycle Architecture
Rubi Debnath, Paul Pop, Silviu S. Craciunas et al. (+2 more)
Time-Sensitive Networking (TSN) provides deterministic guarantees and bounded latency for safety-critical applications across different domains. While the IEEE 802.1 TSN standards provide a comprehensive set of mechanisms for time synchronization, shaping, scheduling, resource reservation, and reliability, deploying TSN in real-world applications remains a complex, multi-step engineering task. Existing research primarily focuses on optimizing individual objectives, such as increasing schedulability, reducing latency, accelerating solution generation, or improving performance analysis. However, whether these extensively researched solutions can be deployed in real-world systems remains unanswered, as the assumptions made in these methodologies often differ from practical hardware constraints. Therefore, a broader, holistic view of end-to-end TSN deployment and management remains an open research question. Currently, there is a lack of a unified perspective, consensus, and coordinated research efforts focusing on a comprehensive end-to-end TSN deployment workflow. We present a comprehensive overview of the TSN deployment lifecycle, current challenges, limitations of existing tools, and future research directions for TSN deployment and management. Lastly, we identify key research gaps from a deployment perspective and provide guidance for the development of next-generation deployable TSN networks.
Read the full abstract ▾
All authors Rubi Debnath, Paul Pop, Silviu S. Craciunas, Marc Boyer, Sebastian Steinhorst
Machine Learning
Bern2Edge: A Neurosymbolic Compiler for Edge Deployment via Bernstein Polynomial Networks
Malak Gamal El-Din, Yifan Zhang, Yasser Shoukry et al. (+2 more)
Deploying high-accuracy neural networks on resource-constrained edge devices remains challenging, as existing approaches treat training, compression, and hardware synthesis as separate stages, leaving a gap between software-trained models and efficient end-to-end deployment with limited support for interpretability. We propose Bern2Edge, an end-to-end framework that uses knowledge
distillation to convert a pretrained teacher feed-forward network into hardware-efficient representations via Bernstein
polynomial activations. This representation enables two deployment paths: (i) a high-fidelity LUT-based realization that preserves model fidelity under compression, and (ii) a symbolic rule-based representation derived from Bernstein activation geometry, enabling interpretable inference with explicit input-space constraints. The resulting BNNs achieve up to 2.12 percentage-point (pp) accuracy improvement over ReLU under identical compression constraints. At the system level, Bern2Edge achieves up to 99.8% latency reduction and 95.2% BRAM reduction relative to a W8A8 quantized teacher on an AMD Xilinx KV260 FPGA, while maintaining accuracy within 0.5 pp, and further deploys on a low-power Spartan-7 XC7S15 FPGA. The rule-based path reduces DSP usage by up to 89.0% at a cost of 1.5 pp in total accuracy.
Read the full abstract ▾
All authors Malak Gamal El-Din, Yifan Zhang, Yasser Shoukry, Sitao Huang, Salma Elmalaki
Networking
Towards Traffic Modelling of Multi-Agent Systems: The Role of Coordination Topology
Davide Lamagna, Albert Cabellos, Alberto Rodriguez-Natal et al. (+2 more)
Multi-
agent LLM systems are an emerging networked workload whose rapid deployment raises questions about the traffic patterns they generate. Compared to conventional applications, these systems generate requests internally: a single user task can induce a structured sequence of model calls whose timing is governed by coordination logic rather than by user arrival rate. It is not clear whether classical traffic models, designed for human-driven workloads, apply to this setting. We present an empirical characterisation of LLM-call interarrival time distributions across sequential,
star, and full-mesh agentic coordination
topologies, using a multi-layer measurement framework over 500 repeated runs per
topology. We find that
topology fundamentally shapes the arrival process of requests to the LLM backend: fan-out coordination introduces a structural bimodality absent in sequential execution, and the reasoningphase component is best described by a log-normal distribution, with the Poisson exponential null model decisively rejected across all
topologies. These differences propagate to inference and network level metrics. The framework and analysis pipeline are released openly at https://github.com/dlamagna/agentraffic.
Read the full abstract ▾
All authors Davide Lamagna, Albert Cabellos, Alberto Rodriguez-Natal, Gábor Rétvári, Berta Serracanta
Numerical Analysis
Regularized summation of Fourier-Laguerre series in the weighted sup-norm
S. G. Solodky and Y. A. Volynets
We consider the problem of recovering functions defined on the half-line from inexact input information. For the proposed regularizing summation methods based on Laguerre
polynomials, we analyze their approximation properties on functions from Wiener classes. We establish conditions under which these methods are stable with respect to small perturbations of the input data and order-optimal not only in accuracy in the weighted $\sup$-norm, but also in the number of
Fourier-Laguerre coefficients used.
Read the full abstract ▾
Computer Vision
Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs
Yunheng Li, Guohong Mu, Hao Li et al. (+4 more)
Multimodal large
language models (MLLMs) have become a prevailing paradigm for unified
video perception. However, post-training on large multi-task
datasets remains challenging, as existing reinforcement learning methods sample on-policy groups with few high-quality rollouts even with costly chain-of-thought (CoT) generation. In this paper, we study the sample efficiency and scalability of RL post-training for
video MLLMs and introduce OraRL. We identify an overlooked role for annotations: Beyond scoring rollouts, each can enter its on-policy group as an oracle rollout, a direct positive optimization target. Direct oracle integration, however, is nontrivial: a high-reward oracle raises the group baseline and inverts otherwise positive policy advantages, a failure we term advantage inversion. At the core of OraRL is a decoupled advantage
estimator: policy rollouts determine an oracle-free baseline, while the oracle-policy gap modulates both a directional gain and a separate detached oracle advantage. Sign-balanced
pruning improves efficiency: by retaining only the oracle and the strongest rollouts of each sign, OraRL requires just 2.2x the step time of SFT, less than half the 4.9x required by GRPO with CoT. OraRL scales with model size and data, surpassing its backbone from 0.8B to 9B and GRPO up to 100k
prompts. Without chain-of-thought,
Video-ORA-9B decodes in 130 ms instead of 4,780 ms. Compared with the respective prior best models, it raises temporal mIoU from 62.5 to 66.0, tracking AO from 73.0 to 78.2,
segmentation from 64.3 to 70.4, and the three-
benchmark spatial-intelligence macro average from 51.0 to 56.1; on VSI-Bench, it scores 73.1 against 55.0 for GPT-5 and 55.1 for Gemini-3-Pro.
Read the full abstract ▾
All authors Yunheng Li, Guohong Mu, Hao Li, Shengsheng Qian, Dingwen Zhang, Qibin Hou, Ming-Ming Cheng
Artificial Intelligence
Lost in Translation: How Universal Ethical Values Fail to Translate Across Global Contexts
Ozioma C. Oguine, Munachimso B. Oguine, Cesar Cervera et al. (+6 more)
AI ethics frameworks treat values such as
fairness, transparency, and accountability as universal and uniformly operationalizable across contexts. We examined how 14 experts across 10 countries made sense of AI in practice, reinterpreted core values, and envisioned governance alternatives. We found that AI deployment is characterized by structurally unequal conditions, marked by infrastructural constraints, extractive practices, and a "mystification" of technology, which fundamentally shape perceptions of risks and opportunities. Our findings reveal that experts reinterpret values to fit local moral logics:
privacy as collective and relational rather than individual; transparency as trust-building accountability rather than technical disclosure; and
fairness as equity in access and representation rather than parity in outcomes. We identify these as translation gaps between encoded global frameworks and situated local practices. Finally, we propose pathways toward plural governance that redistributes epistemic authority and treats ethical negotiation as an ongoing, context-sensitive process rather than a settled technical standard.
Read the full abstract ▾
All authors Ozioma C. Oguine, Munachimso B. Oguine, Cesar Cervera, Jenny Yang, Pooja Voladoddi, Mario Rodriguez, Saif Eddin Bani Malhem, Karla Badillo-Urquiola, Daricia Wilkinson
Machine Learning
Metag: A dataset to build agentic meta-reviewing capabilities
Anirudh Sundar, Min Chen, Divya Tadimeti et al. (+11 more)
AI tools increasingly support tasks across the scientific research cycle, from experiment design and manuscript preparation to peer review. At the same time, the continuing growth in conference submissions has increased the burden on meta-reviewers, who must synthesize reviewer feedback, author rebuttals, and manuscript revisions. To address this concern, this paper introduces Metag, a
dataset to accelerate the development of meta-reviewing
agents, specifically to identify changes made to scientific articles during the review-rebuttal process. Each instance contains a reviewer concern, the author's proposed resolution, and the manuscript diffs implementing the stated change. Metag is collected by obtaining manuscript versions from before the review deadline and after acceptance, computing differences between the two documents, and asking human annotators to align these differences with action items from OpenReview discussions. The resulting
dataset consists of 349 high-quality action items tied to paper differences and will enable building methods to empower meta reviewers to quickly identify whether authors have addressed reviewer statements and where in the paper those changes have been made, resulting in additional transparency and traceability throughout peer review. The
dataset is publicly available at https://github.com/microsoft/Metag-
dataset.
Read the full abstract ▾
All authors Anirudh Sundar, Min Chen, Divya Tadimeti, Gemma Zhang, Xinyi Alice Li, Nigel Boachie Kumankumah, Pavan Uttej Ravva, Sadid Hasan, Somya Chatterjee, Pruthvi Prakash Navada, Xiao Wang, Yue Kang, Sulaiman Vesal, Larry Heck
Artificial Intelligence
Terminal Agents: A Survey of AI Agents in Command-Line Environments
Yi Bin, Xiaoyang Yuan, Haoxi Zeng et al. (+9 more)
Large
language model
agents increasingly act through terminals, yet existing surveys disperse terminal-mediated behavior across software engineering, tool use, and computer-use research. We regard terminal
agents as systems whose dominant progress-bearing action–observation loop is mediated by terminal command execution, textual feedback, and stateful environment interaction. Using terminal-mediated execution as an organizing lens, this survey establishes workload-level boundaries and connects system architecture, competence acquisition, and evaluation through a seven-dimensional terminal competence profile. Our synthesis shows that realized behavior is jointly shaped by the model, interface, harness, runtime, and environment. Executable trajectories ground learning in action consequences, verification, and recovery, whereas prevailing evaluations emphasize final outcomes and expose process quality, recovery, and governance unevenly. Bounded fixed-condition diagnostics illustrate two implications:
benchmark families expose different process signals, and matched system comparisons reveal
benchmark-dependent performance and limits of component attribution. These findings motivate explicit reporting of system and runtime conditions, supported by replayable traces and process-level evidence. The framework provides a unified basis for studying terminal-mediated agency across software engineering and emerging application domains.
Read the full abstract ▾
All authors Yi Bin, Xiaoyang Yuan, Haoxi Zeng, Wencheng Ye, Wenqi Shao, Chen Qian, Wei Ye, Yujuan Ding, Zheng Wang, Pengpeng Zeng, Jingkuan Song, Heng Tao Shen
Machine Learning · Cross-listed from stat.ML
Uncertainty propagation in auto-regressive random neural network models
Janice Adams and Daniele Venturi
We develop analytical and particle-based methods for uncertainty propagation in random neural network models, where both the inputs and network parameters are allowed to be random. Building on the piecewise-linear structure of the Leaky ReLU activation function, we derive a local approximation of the neural network output with respect to perturbations in both its inputs and parameters. This approximation is exact for perturbations that preserve the network activation pattern, and it allows us to compute analytical expressions for the probability density function and characteristic function of the network output, together with closed-form approximations for its mean and covariance. We extend this uncertainty propagation framework to autonomous dynamical systems whose one-step
evolution map is represented by a random neural network. Repeated application of this map defines an autoregressive model, for which we derive recursive equations to propagate uncertainty in both the state and network parameters over time. These equations explicitly account for the state-parameter cross-covariance that develops under successive iterations of the network. Numerical experiments on the Lorenz-63 system and the Kuramoto-Sivashinsky equation demonstrate accurate uncertainty propagation through the predictability horizon and the applicability of the proposed framework to high-dimensional dynamical systems.
Read the full abstract ▾
Cryptography and Security
AEGIS: Preventing Cross-Domain Resource Abuse in MCP
Shriti Priya, Teryl Taylor and Frederico Araujo
The Model Context Protocol (MCP) is an open source JSON-RPC protocol that standardizes how large
language models (LLMs) interact with external systems through programmatic functions known as tools. Attackers or malicious
agents can exploit certain modalities of these MCP tools to degrade the overall quality of service of
agent-based applications. For example, an
agent may request an excessively large search radius or very long
videos, overloading backend systems and potentially causing slowdowns or denial-of-service. Each modality including text, images,
video, and location introduces distinct vectors for resource abuse, complicating the development of consistent mitigation strategies. Moreover,
multimodal and crossdomain tools expose diverse request schemas and parameters, making it difficult to define policies that are both generalizable and precise enough to enforce meaningful resource constraints. In this paper, we present AEGIS, a policy enforcement component that enables administrators to define fine-grained safeguards against resource abuse across heterogeneous MCP tools and modalities. AEGIS leverages the
reasoning capabilities of large
language models to analyze, categorize, and normalize diverse tool invocations into a unified, policy-friendly representation accessible to security practitioners. Integrated with the Open Policy
Agent and the ContextForge AI Gateway, AEGIS detects and mitigates abusive behaviors while preserving the flexibility of MCP-based
agent ecosystems.
Read the full abstract ▾
Machine Learning
When Clean Data Hurts: Learning with Monotone Corruptions Beyond Binary Classification
Julian Asilis, Shaddin Dughmi and Chirag Pabbaraju
Optimal learners are tailored to exploit the i.i.d.\ data assumption underlying the classic PAC model. What if an i.i.d.\ training sample were corrupted with correctly labeled examples drawn from an otherwise unrelated, even
adversarial source? This model of learning with monotone
adversarial corruptions was recently introduced by Larsen et al. (2026), who demonstrated that all known optimal binary learners suffer increased error rates in this setting, from $O(d / n)$ in the PAC model to $\Omega (d \log(n / d) / n)$ under monotone corruption. Mehrotra (2026) proved this logarithmic factor to be necessary for binary classification, but left open the consequences of corruption for more general learning settings, such as multiclass classification and partial binary concept classes. As our primary result, we demonstrate that monotone adversaries are frighteningly more powerful in each of these settings. We exhibit a learnable multiclass problem, of DS dimension only 2, that becomes altogether unlearnable under a monotone adversary, and show an analogous result for partial binary concept classes. These results are achieved by an adaptive adversary permitted to view the original i.i.d.\ training set $S$ and to insert $b < \infty$ corrupted datapoints into $S$. In the multiclass example, the adversary need only insert a linear number $b = |S| = n$ of datapoints. We complement these impossibility results by proving that every class remains learnable when the number of adaptive additions is $o(n)$, which our previous multiclass lower bound proves to be tight. We further observe that the classic multiclass error rate of $O(d_{\mathrm{DS}} / n)$ remains achievable against adaptive adversaries restricted to a known constant budget $b = O(1)$, against semi-adaptive adversaries viewing only a $p$-fraction of $S$ for $p \in (0, 1)$, and against oblivious adversaries that cannot view $S$.
Read the full abstract ▾