Logic in Computer Science
Extending concurrent separation logic to the hardware level to verify the xv6 OS kernel on RISC-V with AI agents
M. Frans Kaashoek and Nickolai Zeldovich
MachCSL is a framework for verifying system software, such as an OS kernel, on top of low-level semantics of a RISC-V computer, based on the Sail RISC-V semantics. The key idea behind MachCSL is to adapt concurrent separation logic, based on Iris, to
reasoning about low-level hardware execution at the sub-instruction level: page-table translation, TLB, privilege levels, configuration registers, instruction fetch/decode/execute, traps and interrupts, DMA, shared
memory, power failures, etc.
Reasoning at this level of detail ensures that the system software correctly manages all of the hardware details. Verifying software at this low level of abstraction is tedious, but LLM-based
agents are capable of
reasoning about such low-level details. As a case study, we verify the xv6 OS kernel (6,657 lines of C and assembly code), which provides a traditional Unix system call interface (processes, file system, file descriptors, and preemptive scheduling) and has substantial internal concurrency (multi-core support with fine-grained locking, shared
memory, interrupts, DMA, etc.). In the verification process, we uncovered 11 bugs in the xv6 implementation, as well as one bug in the Sail RISC-V semantics, and one bug in Sail's Lean extraction. The verification effort took us 102 days, including the time to develop the MachCSL framework. On top of the verified xv6 kernel, we prove a
theorem about console-level behavior: e.g., if the user types echo hello world as input on the UART console, the only output the system can produce is hello world (if there are no crashes or other errors). This
theorem covers both the kernel and the init, sh, echo, cat, grep, sync, and seccomp binaries in the initial file system image.
Read the full abstract ▾
Hardware Architecture
Confidence-Gated Admission for Hardware Prefetching: When the Gate Matters More Than the Predictor
Youssef Majdane, Simone Jarno Casartelli and Enrico Lopedoto
Learned cache prefetchers are typically evaluated against classical predictors that always issue requests, confounding the prediction model with the admission policy. We disentangle these variables with matched controls: the same admission gate is applied to both a 257-parameter online MLP and a classical stride predictor. The neural advantage vanishes; the MLP is indistinguishable from gated stride on random traffic and slower on most regular streams. The gate itself is architecturally useful independent of the predictor: on twenty SPEC CPU2017 programs in native ChampSim, it removes 35% of prefetches and improves accuracy from 11% to 15%, but DRAM reads change by only 0.07% demonstrating that proxy metrics do not predict endpoint behavior. We prove gate-closed execution reproduces the no-prefetch baseline exactly. The gate matters more than the predictor, and better proxies do not imply better endpoints.
Read the full abstract ▾
Computer Vision
Editable Visual Design
Junyan Ye, Wei Liu, Dongzhi Jiang et al. (+9 more)
While
diffusion base models such as GPT-Image-2 and Nano-Banana exhibit remarkable visual expressiveness, their end-to-end generation inherently yields flattened bitmaps with error-prone text, precluding layer-wise post-editing. Conversely, code-based visual generation via Coding
Agents provides precise layout control and decoupled layers, yet remains constrained by a lack of global aesthetic intuition and the difficulty of coding complex visual assets. To address this, we propose Editable Visual Design, a new paradigm driven by a Coding
Agent. We designate the VLM as the “creative
brain” for requirement comprehension, task planning, and aesthetic judgment, while utilizing the image generation model as an on-demand “visual world simulator” to synthesize standalone visual assets. Operating under an “imagine first, then act” closed-loop workflow, the
agent generates isolated assets, writes native HTML/CSS, and iteratively refines the design against visual rendering feedback. Furthermore,
Agent Design Replay faithfully reproduces the creative and
reasoning trajectory akin to that of professional human designers. Ultimately, the system delivers editable artifacts with decoupled layers and real text, enabling users to perform intuitive mouse dragging and layout adjustments on a graphical user interface. Validations on posters, infographics, and other scenarios show that this paradigm successfully achieves both refined aesthetics and production-grade editability.
Read the full abstract ▾
All authors Junyan Ye, Wei Liu, Dongzhi Jiang, Zichen Wen, HaoDong Li, Zhutao Lv, Jiaxin Lin, Jinhua Yu, Jun He, Zilong Huang, Rui Chen, Weijia Li
Computer Vision
DSAQuant: Denoising-Stage-Aligned Quantization-Aware Training for Video Generation
Shuaiting Li, Zelin Gao, Haibin Shen et al. (+3 more)
Video diffusion models (VDMs) have achieved impressive progress in text-to-
video generation, but their high
memory and computational costs hinder practical deployment. Quantization-aware training (QAT) is an effective solution for compressing and accelerating advanced generative models without runtime overhead at inference. However, existing QAT methods suffer from a distinctive challenge in VDMs: while they often preserve
prompt semantics, global layout, and coarse motion, the quantized model severely degrades visual details, texture fidelity, and sharpness. In this paper, we trace this degradation to the timestep-agnostic design of conventional quantization pipelines, which overlooks the stage-wise functionality of
video denoising. In VDMs, early denoising steps mainly establish global structure and motion, whereas middle and late steps refine local appearance and high-frequency details. Based on this insight, we propose DSAQuant, a Denoising-Stage-Aligned Quantization-aware training framework for VDMs. During training, Denoising-Stage Oriented Supervision preserves teacher
distillation in early steps for stable structure planning, while shifting later steps toward target-driven optimization to enhance detail reconstruction. During inference, Denoising-Stage Gated Guidance disables CFG in the final denoising steps to prevent it from amplifying quantization-induced errors into high-frequency artifacts. Extensive experiments on the Wan and CogVideoX families under W4A4 and W3A3 settings show that DSAQuant consistently outperforms the SOTA QAT baseline, improving the VBench average score by up to 6.60 under aggressive W3A3 quantization while preserving strong text-
video alignment. These results demonstrate that effective VDM quantization requires not only reducing quantization error, but also aligning quantization training and inference with the stage-wise nature of
video diffusion.
Read the full abstract ▾
All authors Shuaiting Li, Zelin Gao, Haibin Shen, Yujun Shen, Haotong Qin, Yinghao Xu
Artificial Intelligence
IRWOZ 2.0: A Large Language Model-driven Dialogue Dataset for Industrial Robot Conversations
Chen Li and Dimitrios Chrysostomou
IRWOZ has improved industrial human-
robot interaction (HRI) dialogue systems through domain-specific annotations. However, its initial version contains substantial noise in dialogue states and utterances, limiting state-tracking accuracy. We introduce IRWOZ 2.0, which addresses these limitations through large
language model (LLM) enhanced generation (Mistral/Claude-3.5) and quality refinements. Our improved
dataset expands to 390 dialogues across 4 industrial domains (Assembly, Delivery, Position, Relocation), featuring manual corrections and automated typo removal.
Benchmark experiments on dialogue state tracking demonstrate significant improvements, with GPT-2's BLEU-4 score increasing from 0.1651 to 0.5604 compared to original IRWOZ. To support industrial HRI research, we publicly released IRWOZ 2.0
dataset at https://ieee-dataport.org/documents/irwoz-20-large-
language-model-driven-dialogue-
dataset-industrial-
robot-conversations
Read the full abstract ▾
Computational Engineering
Influence of Extruded Filament Shape on Buildability in 3D Concrete Printing: A Geometry-Informed Deep Learning-FEM Approach
Giacomo Rizzieri, Saif-Ur-Rehman, Jörg F. Unger et al. (+1 more)
The
geometric morphology of deposited filaments can significantly influence the structural performance and stability of 3D concrete-printed (3DCP) structures. However, most finite element (FEM)-based approaches for buildability assessment represent printed layers as simplified rectangles, potentially limiting predictive accuracy. This study proposes a geometry-informed modelling framework that integrates the deep-learning-based filament shape prediction tool ShapeGen3DCP with a layer-activation FEM approach to investigate the effect of realistic filament geometries on buildability. The framework generates geometry-aware numerical models directly from material and process parameters, eliminating the need for experimental filament characterization or computationally intensive fluid-flow simulations. Validation against experimental data and a parametric study of rectilinear walls demonstrate that extrusion parameters and the resulting filament geometry can significantly influence buildability predictions. Realistic filament representations are particularly important for free-flow deposition, whereas layer-pressing strategies are less sensitive to
geometric simplifications. Among the investigated representations, an elliptical approximation provides an effective balance between
geometric fidelity and modelling simplicity. When rectangular representations are preferred to enable regular computational meshes for faster simulations, defining their dimensions based on volume conservation improves prediction reliability compared with calibrating them using either the maximum filament width or the interlayer contact width. Overall, the proposed methodology demonstrates the importance of incorporating filament geometry into 3DCP simulations and provides practical guidance for selecting efficient and accurate
geometric representations for buildability assessment.
Read the full abstract ▾
All authors Giacomo Rizzieri, Saif-Ur-Rehman, Jörg F. Unger, Annika Robens-Radermacher
Computer Vision
Stable and Scalable Bundle Adjustment of Holistic 3D Structures
Shaohui Liu, Rémi Pautrat, Daniel Barath et al. (+3 more)
Bundle Adjustment (BA) is a cornerstone of 3D computer
vision and has benefited from decades of advances in sparse optimization and numerical methods. It was originally developed for jointly optimizing camera intrinsics, poses and sparse 3D points. While extensions incorporate lines and other primitives, integrating richer
geometric structures such as parallelism, coplanarity, or wireframes often introduces significantly increased computational cost and reduced numerical stability. In this paper, we propose a unified framework that extends bundle adjustment to jointly optimize
geometric features and higher-order relations. We first introduce a taxonomy that distinguishes scalable
geometric features with direct 2D measurements (e.g., points and lines), from groups encoding higher-order relations (e.g., coplanarity, parallelism, etc.), where we show that groups can be modeled as camera-like entities within the bundle adjustment framework. Building on this formulation, we propose that both group constraints and cross-feature relations (i.e., point-line associations) can be expressed through 2D reprojection measurements. By formulating group-induced and cross-feature reprojection errors, we preserve the sparsity structure of classical point-based BA under Schur elimination, while avoiding direct 3D regularization that degrades the conditioning and stability. Experiments on both real-world and synthetic
datasets demonstrate runtime performance comparable to classical point-only bundle adjustment, while producing significantly richer 3D structures and improved
geometric accuracy.
Read the full abstract ▾
All authors Shaohui Liu, Rémi Pautrat, Daniel Barath, Richard Hartley, Viktor Larsson, Marc Pollefeys
Artificial Intelligence
Instruction Duplication as an Inference-Time Control Primitive
Victor Lavrenko
Procedural instruction following is a basic requirement for controllable
language-model systems, especially when generated trajectories are inspected or repaired downstream. We introduce instruction duplication, a minimal black-box inference-time control that repeats only the procedural instruction, without retraining or decoding changes. Across seven instruction-tuned models, 300 medical multiple-choice questions, eight placement conditions, and 16,800 scheduled generations, moving from one to two copies raises the deterministic All-8 diagnostic–responses passing all eight observable tests–from 90.22% to 93.17% (+2.95 percentage points), eliminating 30.2% of the failures remaining after one copy. Pre-provisional TF-IDF recall rises from 73.44% to 74.81% (+1.38 points; Holm-adjusted p < .001), while final-answer accuracy remains exactly 60.21%. Premature commitment increases from 1.52% to 2.30% (p_Holm = .00536). A blinded challenge audit yields 10/30 directional confirmations, 20/30 perceptual ties, and no reversals; its prespecified 28/30 confirmation criterion is not met. Yet this distinction can matter operationally when a downstream system acts on the generated trajectory. In Answer Engineering (AE), where explicit trajectory state determines local repair, the published reason-first no-editing SSNHL endpoint was 25.1%; system-only AE was later reproduced at 84.2%, and the same trailing duplicate raised it to 97.1%. For conductive diagnostic branch preservation, the corresponding values are 58.9% published without editing, 78.6% with reproduced AE, and 73.8% with AE plus duplication–a within-AE decrease, but still 14.9 points above the no-editing baseline. Instruction duplication is therefore a low-complexity, placement-sensitive control whose practical value can emerge through the downstream system that consumes the exposed trajectory.
Read the full abstract ▾
Computation and Language
Representational alignment yields generalizable safety in language models
Lingyu Li, Yan Teng, Yingchun Wang et al. (+1 more)
Aligning large
language models (LLMs) is essential for their safe deployment. Current
alignment methods mainly optimize observable responses, yet models remain vulnerable when the same harmful intent is recast in unfamiliar or
adversarial forms that humans can easily recognize. Prototype theory offers an account of this adaptability. Human concepts are represented around central cases, and new instances are categorized according to their graded typicality relative to these prototypes. Here we show that such categorization of moral concepts is weakly preserved in current LLMs. Across 23 LLMs, models often failed to distinguish opposed moral categories or preserve fine-grained typicality within each category. These deficits persist across parameter sizes and
alignment stages. We developed representational similarity optimization, which directly aligns the latent representations in LLMs with the categorization expressed in human moral judgements, without supervising generated responses. In matched experiments using the same 251,334 moral annotations, standard behavioral
alignment learned the intended moral judgements at the response level while leaving the categorization structure largely unchanged and increasing vulnerability across
adversarial evaluations. Reorganizing moral categorization produced more modest gains in explicit judgements but consistently improved
adversarial robustness across model scales on diverse
benchmarks and attack strategies. Our findings provide functional support for the view that prototype-based categorization contributes to behavioral adaptability. They also show that transferring this representational principle to LLMs yields generalizable safety under
adversarial conditions.
Read the full abstract ▾
All authors Lingyu Li, Yan Teng, Yingchun Wang, Xia Hu
Artificial Intelligence
FLY-EVAL++: An Evidence-Driven Evaluation Protocol for Safety-Constrained Flight Prediction with Large Language Models
Yalun Wu, Junfeng Fang, Jiawei Wang et al. (+6 more)
Evaluating large
language models (LLMs) in safety-critical, physics-governed environments requires more than accuracy-based metrics, because predictions that are numerically close to the ground truth can still violate operational constraints, combine fields in physically inconsistent ways, or fail to produce usable structured outputs. Existing evaluation protocols do not measure these failure modes reliably. We propose FLY-EVAL++, an evidence-driven evaluation protocol that combines deterministic verification of protocol compliance, physical feasibility, and safety constraints with fixed rubric-guided aggregation into interpretable multi-dimensional scores. We instantiate FLY-EVAL++ for Flight Trajectory and Attitude Prediction (FTAP) by extending the PilotBench setting with history-conditioned and multi-step prediction tasks. Across 66 LLMs, safety compliance is the most discriminative dimension of model behavior: models with comparable predictive performance differ by more than 28 points in safety score, and we observe recurrent failures including safety violations under physically plausible predictions and instability in multi-step rollouts. These results show that evaluation in safety-critical domains should measure constraint satisfaction and structured validity explicitly rather than rely on accuracy-centric reporting alone.
Read the full abstract ▾
All authors Yalun Wu, Junfeng Fang, Jiawei Wang, Haotian Liu, Qijun Yang, Minghan Yang, Hongcheng Guo, Zhoujun Li, Boyang Wang
Machine Learning
A Location-Invariant Estimator of Extremal Quantile Treatment Effects for Heavy-Tailed Distributions
Xin Yu, Shuwei Huang, Jicheng Liu et al. (+4 more)
Quantile treatment effects (QTEs) measure the effect of a treatment on the distribution of an outcome, and their estimation at extreme
quantile levels is of central interest in applications where the target
quantiles lie far beyond the range of the data. For heavy-tailed potential outcomes, existing extremal QTE
estimators rely on extrapolation combined with a causal extreme value index (EVI)
estimator, but the resulting
estimator is not invariant under a common location shift of the potential outcome distributions, even though the population QTE is. We address this issue in two steps. First, we adapt the location-invariant Fraga
estimator of the EVI to the causal setting using inverse propensity score weighting. Second, we replace the original extrapolation formula with a difference-based scheme, under which the location parameter cancels when
quantile differences are taken. The resulting QTE
estimator is therefore location invariant. We establish the consistency and asymptotic normality of the proposed extremal QTE
estimators, and provide a consistent variance
estimator, leading to asymptotically valid inference. A simulation study confirms the location invariance, the stability with respect to the threshold, and the coverage of the proposed methods.
Read the full abstract ▾
All authors Xin Yu, Shuwei Huang, Jicheng Liu, Jielin Tang, Bolin Wang, Yunxiao Zhang, Tian Zhao
Cryptography and Security
A Black Box for Agentic Processes: Blockchain-Anchored Evidence for AI Agent Communication, Human Oversight, and GRC Audits
Arslan Brömme
Autonomous AI
agents increasingly communicate with other
agents, invoke tools, exchange intermediate results, and request human approvals. These workflows create a new auditability problem: organizations must reconstruct what happened, when it happened, which
agent or human was involved, which control or policy applied, and whether records were modified afterwards. Motivated by the 2026 OpenAI/Hugging Face incident, this position and architecture paper proposes a product- and vendor-neutral black-box architecture for agentic processes. The architecture creates blockchain-anchored cryptographic commitments for selected
agent communications, human-in-the-loop approvals, tool calls, and process artifacts without placing sensitive content on-chain. We define an evidence model that distinguishes temporal anchoring and artifact integrity from event ordering, capture authenticity, authorized anchoring, and causal traceability. The latter properties require additional architectural controls. We then discuss practical use for Governance, Risk, and Compliance (GRC), including compliance testing, risk-based evidence selection, monitoring evidence streams, incident reconstruction, and regulatory reporting readiness under the EU AI Act, NIS2, and the Cyber Resilience Act (CRA). This position and architecture paper does not present an empirical performance or security evaluation. The approach does not prevent
agent misbehavior or prove semantic truth. Rather, it strengthens the evidentiary basis for later verification of critical process traces.
Read the full abstract ▾
Artificial Intelligence
InSituMeasure: Probing Situated Measurement Grounding in Industrial Scenes with Multimodal Large Language Models
Chao Shen, Xinyuan Li, Yunfan Zhou et al. (+4 more)
For trained operators, gauge reading requires little specialized knowledge, low cognitive effort, and high repeatability. Yet
Multimodal Large
Language Models (MLLMs) remain unreliable in continuous-valued measurement despite strong results on general
multimodal benchmarks. Existing
benchmarks expose this weakness but isolate measurement from realistic, knowledge-grounded settings, with limited situated context, specialized instruments, real-world noise, and matched diagnostic annotations, reducing realism and constraining root-cause analysis. We introduce InSituMeasure to evaluate situated measurement grounding. It contains 2,922 real industrial monitoring scenes across eight functional categories of professional engineering instruments, with dense gauge-attribute annotations and noise tags for failure diagnosis. We define metrics for numerical accuracy under predefined tolerances and unit consistency, rejection of fake or unanswerable tasks, and
alignment between model failures and annotated error factors. Across 24 state-of-the-art MLLMs, the best model reaches only 25.7% joint value-unit accuracy and 51.8% confidence-diagnosis F1, revealing a substantial gap between general
multimodal competence and reliable situated measurement. Further analysis identifies failures from text-induced shortcuts, overconfident responses, and authentic industrial noise, including mixed disturbances, viewpoint deviation, occlusion, and environmental interference.
Read the full abstract ▾
All authors Chao Shen, Xinyuan Li, Yunfan Zhou, Jianguo Yao, Haibing Guan, Zhihai Wang, Xijun Li
Artificial Intelligence
LLM4CKD: Large Language Models for Early Stage Chronic Kidney Disease Screening
Muhammad Ashad Kabir and Sirajam Munira
Early screening of chronic kidney disease (CKD) is critical for timely intervention, yet most machine learning (ML) and deep learning (DL) approaches require labeled data and model training, limiting their use in real-world screening settings. This study evaluates the effectiveness of large
language models (LLMs) for CKD screening under zero-shot and few-shot in-context learning settings and compares them with traditional ML and DL methods. We propose a framework that uses clinically selected tabular features and structured
prompt templates to enable LLM-based inference without task-specific training. LLM performance is evaluated across multiple
prompt styles, feature configurations, and data settings, and compared with standard ML, DL, and tabular foundation model (TFM) baselines, and existing CKD screening tools. The results show that LLMs can achieve competitive performance using only a small number of examples, often matching or outperforming traditional approaches in low-data settings. However, their performance remains model-dependent and less stable as input complexity increases. In contrast, ML, DL, and TFM models show more consistent improvement with larger training data. Overall, the findings highlight a trade-off between data efficiency and stability, suggesting that LLMs may serve as a flexible complementary approach for CKD screening when labeled data are limited. To facilitate further research and reproducibility, the code has been made publicly available at https://github.com/akabircs/LLM4CKD
Read the full abstract ▾
Computational Engineering
Differentiable Hybrid Modelling for Learning and Optimising Chemical Transport Processes from Experimental Data
Arthur Jessop, Mohammed Alsubeihi, Ben Moseley et al. (+1 more)
Transport models underpin the design and optimisation of chemical processes, yet their constitutive laws are typically hand-picked, their experimental initial conditions are assumed exact, and their computational cost restricts optimisation to a handful of process variables. Here we introduce a differentiable hybrid modelling framework that embeds neural networks within a GPU-accelerated population balance equation solver to discover constitutive laws and assimilate initial conditions directly from experimental crystallisation data. Using thirteen real experiments with multi-dimensional size and shape measurements, we show that treating measured initial conditions as exact yields a physically inconsistent rate law despite improved predictive accuracy, whereas assimilating them recovers a physically consistent, non-linear law and reduces trajectory error sevenfold relative to conventional modelling. End-to-end differentiability further enables gradient-based optimisation of high-dimensional operating profiles, identifying a 300-variable temperature profile that reduces
crystal aspect ratio by 25% at constant mass, facilitating superior product attributes. Our framework augments, rather than replaces, mechanistic modelling, offering a general route to learning transport models from data and optimising processes with them.
Read the full abstract ▾
All authors Arthur Jessop, Mohammed Alsubeihi, Ben Moseley, Ashwin Kumar Rajagopalan
Machine Learning
Unlocking Lossless Speedups in LLMs via Discrete Diffusion
Subham Sekhar Sahoo, Lingjie Chen, Khiem Pham et al. (+14 more)
Large
Language Models (LLMs) owe much of their success to next-
token prediction (NTP), but their autoregressive (AR) structure requires slow, sequential
token generation. To overcome this bottleneck, we introduce
diffusion-augmented LLMs, a new class of models that defines an AR model distribution while using
diffusion to draw multiple
tokens in parallel from that distribution. We decouple the parameters of these models into two sets: AR weights, trained using the standard NTP objective, and lightweight
diffusion weights, trained to generate multiple
tokens simultaneously. The
diffusion weights are learned through a simple
Diffusion Distillation phase that adds negligible overhead to existing LLM training pipelines. We also introduce $\Psi$-Spec, a family of samplers that enables lossless acceleration and inference-time scaling at a fixed context length. Unlike speculative decoding, our method requires no separate draft model. Unlike
diffusion LLMs (d-LLMs), it accelerates generation without sacrificing the quality of the underlying AR model. The resulting models, called Uno, can be trained from scratch or built by augmenting existing open-weight AR LLMs. Uno achieves higher throughput than leading speculative-decoding methods at every evaluated batch size and delivers up to $3\times$ speedups over the base AR model, including at the largest batch size supported by the device. Notably, our 8B Uno model outperforms the leading open d-LLM, the 26B DiffusionGemma, and the proprietary Mercury 2 across all evaluated
benchmarks in agentic tool use, coding, and long-context
reasoning. We release code and checkpoints at: https://s-sahoo.github.io/uno/
Read the full abstract ▾
All authors Subham Sekhar Sahoo, Lingjie Chen, Khiem Pham, Jonathan Geuter, Chaitanya Dwivedi, Varad Pimpalkhute, Yash Akhauri, Alexander Moreno, Mikhail Yurochkin, Zhenting Wang, Mostafa Elhoushi, Nolan Dey, Shane Bergsma, Joel Hestness, John Thickstun, Eric Xing, Zhengzhong Liu
Computer Vision
The Blind Spot in 2D Infants' Pose Estimation:Robust Learning from Noisy Annotations
Emanuele Cardinale, Marco Proietti, Alessandro Cacciatore et al. (+3 more)
Noisy annotations pose a significant challenge for supervised deep learning, as neural networks rely on large-scale, high-quality labeled data whose corruption can severely impair model performance. Although robustness to label noise has been extensively studied for classification tasks, it remains relatively underexplored in Pose Estimation (PE). This limitation becomes critical in clinical contexts, including neonatology, where PE of preterm infants is used to support the assessment of spontaneous motility, a key indicator of neurodevelopmental trajectories. In such settings, infants' images labeling is further hindered by visual challenges (e.g., keypoint self-occlusions, caregiver interference), making the annotation process inherently susceptible to errors. To tackle noisy annotations in PE, we introduce REliable keypoint selection via
Memory of traINing Dynamics (REMIND), a clustering-based keypoint-selection strategy that exploits keypoint-wise training dynamics to identify noisy labels without assuming any prior knowledge of the noise distribution, thus enabling noise-free model training. When evaluated on the proprietary NeoPose
dataset, comprising 46
videos of 46 preterm infants recorded in real clinical settings, REMIND correctly identifies noisy annotations across multiple corruption scenarios, achieving up to 93% Area Under the Curve (AUC) with three different PE architectures used in the relevant literature. To our knowledge, this is the first study to explicitly address label noise in preterm infants' PE, paving the way for the design of trustworthy learning-based
algorithms for infants'monitoring support when data quality cannot be guaranteed.
Read the full abstract ▾
All authors Emanuele Cardinale, Marco Proietti, Alessandro Cacciatore, Maria Francesca Spadea, Lucia Migliorelli, Sara Moccia
Machine Learning
RobustSeiz: An Open-Source Framework for Benchmarking the Robustness of EEG Seizure Detection Models
Mohammad Mohammadi and Alireza Zarei
Despite strong performance on held-out electroencephalography (
EEG) data, seizure detectors may fail under real-world acquisition variability, artifacts, and
adversarial inputs. We introduce RobustSeiz, an open-source, model-agnostic framework that provides a standardized, reproducible protocol for stress-testing and comparing seizure detectors under controlled, clinically motivated distribution shifts before deployment. We standardize four public scalp-
EEG corpora (CHB-MIT, TUSZ, Siena, and SeizeIT1) into BIDS-
EEG trees and evaluate subject-independent detectors on held-out splits. Environment, noise, and
adversarial transforms are swept over predefined hyperparameter grids. Each run reports sample- and event-level sensitivity, precision, F1, false positives per 24 h, Lead and Lag onset timing, and Monte Carlo dropout predictive agreement. RobustSeiz includes a Dockerized GPU pipeline, experiment registry, and full-evaluation and research-subset modes. We demonstrate the framework with a contemporary seizure detector on TUSZ across the complete implemented shift grid; an AWGN analysis illustrates how perturbation severity changes detection quality, onset timing, and predictive agreement. RobustSeiz provides a shared benchmarking standard for evaluating seizure-detector robustness under realistic clinical stressors, extending pre-deployment assessment beyond clean-data accuracy.
Read the full abstract ▾
Artificial Intelligence
The Dually Flat Geometry of Planning as Inference
Nikola Milosevic, Asaki Kataoka, Nicolas Hinrichs et al. (+2 more)
We present an alternative characterization of the occupancy measure of reinforcement learning, obtained by
embedding the planning criterion into the dynamics through a resetting planning process. Its stationary measure, which we term visitation measure, is the object on which the information geometry of decision making is most naturally expressed. The achievable visitation measures form a dually flat statistical
manifold whose two affine charts are the visitation probabilities and the log-policies, dual under the conditional
entropy. This structure makes planning-as-inference generalize from linear rewards to nonlinear functionals of the visitation, each iterate solved by one natural-gradient step, and gives the temporal-difference error the interpretation of a marginal-utility estimate. We develop the geometry and its consequences for reinforcement learning and theoretical neuroscience.
Read the full abstract ▾
All authors Nikola Milosevic, Asaki Kataoka, Nicolas Hinrichs, Kenji Doya, Nico Scherf
Information Theory
On the Impact of Site-Specific Training for a Real-World 5G NR System
Reinhard Wiesmayr, Nuri Berke Baytekin, Chris Dick et al. (+1 more)
Site-specific training can improve wireless receiver performance without increasing computational complexity. However, real-world results have so far focused on fully trainable neural receivers and single-layer transmissions. We study site-specific finetuning of three receiver architectures: fully trainable neural, model-driven neural, and model-based. We train and evaluate these receivers using new measurements from a standard-compliant 5G NR testbed at ETH Zurich with dual-layer uplink transmission, including measurement campaigns conducted more than six months apart. Our results show that site-specific finetuning (i) substantially improves fully trainable and model-driven neural receivers, while resulting in only marginal gains for the less tunable model-based receiver; (ii) enables a single neural receiver jointly finetuned for single- and dual-layer transmission to closely match receivers finetuned separately for each configuration; and (iii) remains effective across measurement campaigns separated by more than six months. We also investigate site-specific linear minimum mean-square error channel estimation using covariance
matrices estimated from either synthetic channels or site-specific measurements. When combined with iterative detection and decoding, site-specific channel estimation achieves the lowest error rate observed in our
datasets. Our finetuning code and measurement
datasets are publicly available at https://github.com/IIP-Group/site_specific_training
Read the full abstract ▾
All authors Reinhard Wiesmayr, Nuri Berke Baytekin, Chris Dick, Christoph Studer
Numerical Analysis
Closure complexity of longest-edge bisection for triangular meshes
Yuwen Li and Zhiyuan Yang
On triangular meshes, we analyze local mesh refinement based on longest-edge bisection equipped with the serial longest-edge propagation-path closure. Ties are resolved by terminal priority: if the incoming shared edge is a longest edge of the neighboring triangle, the pair is declared terminal and that edge is bisected. For every adaptive mesh sequence $\mathcal{T}_0, \mathcal{T}_1, \ldots, \mathcal{T}_L$ with a sequence of marked sets $\mathcal{M}_0, \mathcal{M}_1, \ldots, \mathcal{M}_{L-1}$, we prove the cumulative closure estimate $$\#\mathcal{T}_L-\#\mathcal{T}_0 \lesssim\sum_{\ell=0}^{L-1}\#\mathcal{M}_\ell.$$ The proof derives single-mark locality from the uniform multiplicative gap between possible descendant diameters implied by finite similarity classes, and converts this locality into the cumulative estimate through a Binev–Dahmen–DeVore-type charging argument.
Read the full abstract ▾
Computers and Society
Shifting from Injection to Interaction: Rethinking Web Security in the Age of LLMs and Beyond
Nivedita Singh, Alsharif Abuadbba, Yansong Gao et al. (+2 more)
Large
language models (LLMs) are becoming integral to web applications and browser
agents, transforming online interactions while introducing new attack vectors and reshaping longstanding web vulnerabilities. Classical threats such as cross-site scripting (XSS) can be amplified through LLM-mediated interactions, while LLM-specific vulnerabilities can propagate across web applications, introducing attacks such as
prompt injection. Securing modern web systems therefore requires understanding interactions between traditional and LLM-specific threats across the system lifecycle. Unlike prior surveys treating web and LLM security separately, this survey provides a unified analysis of how LLMs amplify web vulnerabilities across client-side, server-side, and pipeline layers while evaluating defenses and their limitations. The analysis examines extending NIST and ISO/IEC AI security frameworks to the security needs of LLM-enabled web environments. Three unresolved challenges are identified:
adversarial natural-
language instructions, autonomous
agent security, and post-deployment security through continuous monitoring and adaptation. An LLM-aware monitoring and control framework is proposed, integrating semantic input validation,
prompt integrity protection, output isolation,
agent governance, and runtime monitoring. This unified perspective characterizes the evolving threat landscape and outlines future directions for secure AI-enabled web systems.
Read the full abstract ▾
All authors Nivedita Singh, Alsharif Abuadbba, Yansong Gao, Surya Nepal, Hyoungshick Kim
Programming Languages
Typed Flexible-Arity Slotted E-Graphs: A Soundness Construction and an Alloy Case Study
Guanxuan Wu and Allison Sullivan
Slotted e-graphs represent open terms modulo consistent renaming, while algebraic operators benefit from canonical sequence, bag, or set children. We compose the two at a specification level: typed slot-mapped invocations inhabit operator-declared ports whose sibling quotient and recursive flattening licenses are certified separately. A generic finite quotient presentation proves exactness of its least-orbit normal form, while certified records specify effective-support kernel extraction and collision. For abstract obligation traces carrying local endpoint certificates, we prove finite-unfolding equational soundness. An
Alloy case study compares seven related pipeline arms on a frozen corpus and a controlled transformation suite.
Read the full abstract ▾
Computer Vision
Catalogue Photography as a Cold Start: Toward Deployable Rotary Milling Tool Recognition
Abilash Philip Madavath, Chandra Yuvesh Aubeeluck, Augustin Raju et al. (+3 more)
Verifying that manufactured batches of rotary milling tools, also known as carbide burrs, conform to production order sheets remains a largely manual and error-prone quality assurance task. Automating this process with computer
vision faces a critical cold-start constraint since no labelled imagery from the deployment environment is available, leaving manufacturer catalogue photography as the sole source of supervision. We investigate how far catalogue supervision can support an industrial recognition pipeline under domain shift, explicitly measuring the gap between catalogue separability and performance on held-out field photographs. Our findings reveal three key insights. First, off-the-shelf frozen feature extractors do not reliably separate the two task attributes, head shape and tooth profile, motivating targeted representation learning. Second, metric learning produces near-perfect unsupervised cluster discovery on catalogue images (adjusted Rand index 0.94–0.97), yet on field photographs under half of the accuracy gained from training survives. Third, the largest transfer gains do not come from model scale or representation complexity, but from simple changes that reduce domain sensitivity: converting images to grayscale (+0.22) and constraining
retrieval against the known order sheet (+0.11). We therefore treat catalogue photography as a useful cold start rather than a deployment-ready training domain, and provide empirical baselines and an evaluation protocol for catalogue-to-field transfer in precision tool manufacturing.
Read the full abstract ▾
All authors Abilash Philip Madavath, Chandra Yuvesh Aubeeluck, Augustin Raju, Nicolas Pyschny, Felix Hackelöer, Florian Zwanzig
Computation and Language
Alignment-Free Text-Audiobox for Voice Dubbing and Full-Duplex Dialogue Synthesis
Sanyuan Chen, Min-Jae Hwang, Sho Inoue et al. (+12 more)
We present
Alignment-Free Text-Audiobox (Text-AB), a unified framework for high-quality voice dubbing and full-duplex dialogue synthesis. Building on a
Diffusion Transformer trained with a flow-matching objective, Text-AB departs from the Audiobox system along three dimensions. First, it operates in a latent
diffusion framework using DAC-VAE features that encode 48 kHz waveforms into a 25 Hz latent sequence, giving over 10x higher compression than previous EnCodec representations while improving resynthesis quality. Second, Text-AB is
alignment-free: it consumes raw text via an off-the-shelf text encoder and learns text-
speech alignment through cross-
attention, removing the need for forced
alignment and explicit duration prediction. Third, we scale model and data substantially, pretraining a 3B-parameter model on 480k hours of monolingual
speech, followed by supervised fine-tuning on three downstream tasks: cross-lingual voice dubbing, full-duplex dialogue synthesis, and emotional full-duplex dialogue synthesis. At inference, Text-AB supports one-shot generation for up to ~1 min of
speech and arbitrarily long-form generation via a multi-
diffusion scheme, plus a multi-stage reranking strategy that enhances quality based on automated metrics. On a real-world dubbing
benchmark, Text-AB delivers a step-change improvement over the latest internal dubbing system, with large gains in prosody similarity, voice similarity, naturalness, and shareability. For full-duplex dialogue synthesis, it approaches human recordings on short-form conversations and substantially outperforms the latest internal model on long-form human-likeness and expressivity, while natively modeling turn-taking, back-channeling, and emotional dynamics. For emotional dialogue synthesis,
emotion conditioning significantly improves
emotion alignment and emotional interaction quality over the unconditioned baseline.
Read the full abstract ▾
All authors Sanyuan Chen, Min-Jae Hwang, Sho Inoue, Anna Sun, Bokai Yu, David Kant, Dongmin Hyun, Dorian Desblancs, Gregory Antonovsky, Oleg Repin, Peng-Jen Chen, Xutai Ma, Zehai Tu, Juan Pino, Wei-Ning Hsu
Computer Vision
IchthyoNoma: Nomenclature and Context Sensitivity of Zero-Shot Biological Vision–Language Models for Bangladeshi Freshwater Fish Recognition
Nazim-E-Alam, Tarek Rahman and Md Kishor Morol
Zero-shot
vision-
language models (VLMs) are increasingly used as training-free species recognizers, but reported accuracy can reflect more than visual species knowledge. We audit CLIP, BioCLIP, BioCLIP2, and a
multilingual Jina CLIP v2 control on seven freshwater-fish categories from two Bangladeshi sources (10,321 images). BioCLIP2 reaches 72.36% on BFF-15 with English common names and 68.91% on SylFishBD with scientific names, versus 25.15% and 14.40% for generic CLIP. BioCLIP2 Bengali
prompts are near chance in balanced accuracy (14.22-14.29%); Jina partially recovers Bengali discrimination to 21.89% and 16.36%, but bare Bengali names return to 14.29% on both sources. Paired SylFishBD interventions show no significant weak-blur effect, modest losses from stronger blur/gray masking, a larger white-mask artifact, and strong species dependence. Zero-shot biological VLM scores therefore jointly reflect biological specialization,
multilingual alignment, nomenclature,
prompt formulation, and context.
Read the full abstract ▾
Robotics
MulDP: Multimodal Diffusion Policy for Autonomous Quadruped Parkour Navigation across Complex Terrains
Kangmai Hu, Yueqi Zhang, Peng Zhai et al. (+5 more)
Quadruped
robots have demonstrated impressive agility in parkour locomotion across complex terrains. However, most systems still rely on human intervention for high-level planning, and autonomous parkour
navigation remains underexplored. The key challenges include fine-grained velocity regulation, long-horizon anticipatory behaviors, and tight coupling between perception and
embodied execution. To address these challenges, we propose a
Multimodal Diffusion Policy (MulDP) that integrates visual perception with
robot proprioception and goal information to generate temporally coherent and anticipatory
navigation velocity commands, tightly coupling perception with
embodied control to enable robust autonomous
navigation. To support the training of MulDP, we construct the first Quadruped Parkour
Navigation Dataset (QPND), a
multimodal dataset that encompasses diverse
navigation behaviors and complex terrains. Extensive simulation and real-world experiments demonstrate that MulDP enables robust long-horizon autonomous
navigation and effective traversal across complex terrains.
Read the full abstract ▾
All authors Kangmai Hu, Yueqi Zhang, Peng Zhai, Xiaoyi Wei, Jiabin Hu, Zhixiang Liu, Quancheng Qian, Lihua Zhang
Computer Vision
Sharpening the Ensemble: An SSIM-Aligned Residual Refiner for Brain-MRI Inpainting Post-Processing
Kubilay Kağan Kömürcü and İlkay Öksüz
Brain-MRI inpainting replaces a masked region of a scan with synthesized, anatomically plausible healthy tissue, so that analysis tools built for healthy
brains can be applied to images they would otherwise reject. On the BraTS local-synthesis
benchmark, which ranks submissions on the structural similarity index (SSIM), the peak signal-to-noise ratio, and the mean squared error (MSE) jointly, the strongest recent models are accurate, but several report blurry synthesized regions and attribute this to the mean-seeking behavior of the $\ell_1$ and MSE terms in their training losses. We address this in post-processing, forming a deep ensemble of the two co-first-place 2025 models and training a lightweight residual refiner on the ensemble's own outputs under an $\ell_1$ loss augmented with a structural-similarity term whose weight $\lambda$ we vary. At a moderate $\lambda$ the refiner improves SSIM over the ensemble, from $0.8767$ to $0.8780$ on a held-out reproduction of the official scorer and from $0.8555$ to $0.8572$ on the official validation leaderboard, with essentially no change in MSE. The gain is small but consistent, improving $62.6\%$ of the held-out cases with a signed-rank $p=2.2\times10^{-7}$, whereas over-weighting the structural term reverses it. Two ablations bound the effect. Adding any third model to the two-model ensemble degrades it, and classical unsharp masking fails to improve SSIM at any strength (best $0.8765$ against $0.8767$), so the gain reflects learned rather than indiscriminate sharpening. The result is a cheap, reproducible post-processing stage that improves an already strong ensemble without any large-scale retraining.
Read the full abstract ▾
Distributed Computing
Barnacle: Adaptive Multi-Leader Scheduling for DAG-Based Consensus
George Danezis, Zeno De Angeli, Alexandru Ianov Vitanov et al. (+5 more)
In DAG-based consensus, all validators propose blocks concurrently, and designated leader blocks drive transaction commit. Having multiple leader slots per round cuts queuing latency, yet production deployments run a single leader because of head-of-line blocking: a slow leader stalls the pipeline for at least one leader timeout, and for several waves when its slot must wait for the fallback indirect decision rule. This risk grows with the leader count. We introduce Barnacle, an add-on that adapts the leader count at run time. Every interval, it measures on the agreed committed DAG the fraction of slots decided as commit by the direct rule, and drives the leader count with additive increase, multiplicative decrease. The measurement requires no extra messages and no cryptography, and is deterministic. Barnacle is generic over DAG protocols; we instantiate it on four protocols spanning the Byzantine (3f + 1, 5f + 1), crash-only (2c + 1), and mixed (5f + 3c + 1) fault models, with proven safety and liveness. Results show Barnacle matches the best static leader count in every regime: in a healthy network its latency is 6-13% lower than a single leader's, and under degradation it matches a single leader while remaining 35-56% below a static high count. We are currently collaborating with the Sui team to integrate Barnacle into the Sui blockchain.
Read the full abstract ▾
All authors George Danezis, Zeno De Angeli, Alexandru Ianov Vitanov, Philipp Jovanovic, Lefteris Kokoris-Kogias, Alberto Sonnino, Pasindu Tennage, Igor Zablotchi
Machine Learning · Cross-listed from eess.SP
Cooperative Multi-Task Semantic Communication for Joint Classification and Regression Tasks
Ahmad Halimi Razlighi, Mohammad Siddiqur Rahman, Maximilian H. V. Tillmann et al. (+2 more)
Multi-Task semantic communication (SemCom) prioritizes simultaneous execution of multiple tasks over bit-accurate reconstruction in future intelligent networks. In our prior work [1], we introduced the cooperative multi-task SemCom (CMT-SemCom) framework, in which the semantic encoder is divided into a common unit (CU) and multiple specific units (SUs) to facilitate cooperative multi-task processing. However, CMT-SemCom has been evaluated on homogeneous classification tasks on simplistic
datasets, limiting its applicability to real-world perception systems. In this paper, we extend our CMT-SemCom to jointly handle heterogeneous classification and regression tasks on the complex Cityscapes
dataset. We adopt the information maximization (InfoMax) principle so that it accommodates mixed discrete and continuous semantic variables. In particular, we
benchmark the proposed framework against independent single-task training, a conventional task-agnostic digital transmission, and single-encoder multi-decoder SemCom. Additionally, we investigate the impact of CU capacity on joint task performance, providing design insights. Extensive evaluations demonstrate that CMT-SemCom significantly outperforms the
benchmarks.
Read the full abstract ▾
All authors Ahmad Halimi Razlighi, Mohammad Siddiqur Rahman, Maximilian H. V. Tillmann, Edgar Beck, Armin Dekorsy