Computational Engineering
Adapting a Large Language Model Crash-Severity Pipeline to Tennessee: Performance Across Sampling Strategies
Abhilasha Saroj, Pranav Govindu, Bharat Sharma et al. (+1 more)
State crash databases differ in structure, coding, and injury-severity distributions, limiting direct reuse of predictive workflows across jurisdictions. This study adapts the SafeTraffic Copilot large
language model (LLM) crash-severity workflow to a three-year Tennessee inventory of 624,392 crashes. Tennessee crash, roadway, vehicle, and person attributes were harmonized and converted into textual
prompts while unavailable values were preserved rather than inferred. Llama 3.1 8B was fine-tuned using low-rank adaptation to classify five injury-severity categories. Random, county-based, and severity-balanced sampling strategies were evaluated using separate in-sample and unseen-test experiments; unseen-test experiments used 70/15/15 training, validation, and test splits. On their respective unseen test sets, random and county-based models achieved weighted F1-scores near 80%, but macro F1 remained below 47% and fatal-crash F1 below 27%, showing that strong aggregate performance can mask weak recognition of rare outcomes. Within its balanced evaluation population, the severity-balanced model achieved weighted and macro F1-scores of 57.7% and a fatalcrash F1-score of 65.9%, yielding more even class-level performance. Because each sampling strategy used a different test subset, crossstrategy differences are descriptive rather than controlled rankings. The results highlight the importance of interpreting LLM crashseverity performance together with sampling design, class balance, class-level metrics, and evaluation-population composition.
Read the full abstract ▾
All authors Abhilasha Saroj, Pranav Govindu, Bharat Sharma, Usman Ahmed
Computation and Language
TimeBraid: Unifying Time Series and Language for Understanding and Forecasting
Xinyue Wang, Jiacheng Pang, Kun Zhou et al. (+7 more)
We present TimeBraid, a series of unified time-series and
language models that align pretrained
language models and pretrained time-series foundation models through interleaved global residual
attention layers. Each model inherits knowledge, instruction following, and
reasoning from one side, continuous-signal perception and zero-shot
forecasting from the other, and fuses the two in a shared representation space where both modalities are understood and generated. We study the design choices that make such unified modeling work: where to align the two representation spaces, how to ground
language in temporal structure, how to balance understanding with generation, and how to keep joint optimization stable. The resulting recipe combines a unified prompting scheme for diverse time-series and text tasks, stabilized joint training, and supervision from 2.2M curated series–text pairs and 4.9M instruction-tuning samples. Across
benchmarks spanning time-series perception, understanding,
reasoning, and both context-aided and unimodal
forecasting, TimeBraid remains competitive with far larger general-purpose models and task-specific counterparts.
Read the full abstract ▾
All authors Xinyue Wang, Jiacheng Pang, Kun Zhou, Kexin Zhang, Defu Cao, Fan Feng, Faisal, Songyao Jin, Yan Liu, Biwei Huang
Social and Information Networks · Cross-listed from math.OC
Budget-Constrained Graph Augmentation for Robust Network Design via Kirchhoff Index Minimization
Omkar Bhoite, V Sateeshkrishna Dhuli, Stefan Werner et al. (+1 more)
Enhancing the robustness of deployed networks against failures and disruptions is critical for reliable operation. This requires deciding which new links to install and how strongly to weight them under limited resources. We study this problem through the Kirchhoff index, or total effective resistance, a spectral measure of global connectivity. The resulting augmentation problem couples discrete candidate-edge selection with continuous weight allocation under heterogeneous per-unit deployment costs, a total budget, and an exact-cardinality constraint. For a fixed weighted base graph, this yields a mixed-integer formulation and a semidefinite relaxation whose optimum lower-bounds the mixed-integer optimum. We cast the relaxation as a cone program and solve it numerically using a homogeneous self-dual
embedding and first-order operator splitting. Feasible discrete designs are recovered through rounding-and-repair procedures and assessed by a posteriori gap estimates relative to the numerical semidefinite program (SDP)
benchmark. As a scalable alternative, we develop an exact-$k$, budget-feasible greedy heuristic built on rank-one
Laplacian updates and biharmonic-distance caching, and interpret its progress through a Bellman value-to-go
benchmark with a conservative spectral lower bound on the local policy ratio. Experiments on synthetic and real infrastructure networks across graph sizes, budgets, weight distributions, and cost regimes show that, under fixed budgets, distance-proportional costs limit the achievable resistance reduction and shift installed conductance toward shorter links relative to uniform per-unit costs.
Read the full abstract ▾
All authors Omkar Bhoite, V Sateeshkrishna Dhuli, Stefan Werner, Kimmo Kansanen
Computer Vision
OREO: Fidelity Alignment in 3D Generation via On-the-fly Rendering-Editing Optimization
Zhiyuan Ma, Wenbo Hu, Wang Zhao et al. (+3 more)
Despite recent advancements in 3D generation, models often struggle to produce assets with high visual fidelity. To bridge this gap, we propose OREO, an
alignment framework that enhances the realism of 3D generators by leveraging rich 2D
diffusion priors. Instead of relying on static
datasets, OREO establishes a dynamic optimization loop that produces on-the-fly edited renderings as 2D pseudo-targets. At its core, we introduce Reinforced Editing, which utilizes a 2D model to refine rendered views of the 3D output, enhancing their overall visual fidelity while preserving the underlying geometry, viewpoint, and content. These refined views serve as high-quality supervision targets, enabling the 3D generator to learn from its own generated samples and progressively improve its visual quality. Experiments demonstrate that OREO effectively improves upon pre-trained baselines, producing 3D assets with enhanced visual realism.
Read the full abstract ▾
All authors Zhiyuan Ma, Wenbo Hu, Wang Zhao, Pengfei Wang, Ying Shan, Lei Zhang
Computer Vision
Sheekar Banerjee, Md. Srabon Chowdhury, Md. Mahbub Hasan Akash et al. (+1 more)
Accurate
brain tumor
segmentation from
Magnetic Resonance Imaging is essential for diagnosis, treatment planning, and
surgical guidance. Although Convolutional Neural Networks, particularly UNet, have achieved significant success in medical image
segmentation, they often struggle to capture the long-range spatial dependencies required to model tumors with irregular shapes and complex boundaries. This paper proposes a lightweight
Vision Transformer UNet that combines the hierarchical feature extraction capability of UNet with the global context modeling of
Vision Transformers. The proposed architecture incorporates a compact ViT bottleneck within a U-Net encoder-decoder framework, enabling effective learning of both local and global features while maintaining computational efficiency with only 2.6 million trainable parameters. The model was evaluated on the TCGA LGG MRI
Segmentation dataset, achieving a mean Intersection over Union of 0.8100 and a Dice score of 0.8446, outperforming the baseline UNet by 3.75% and 3.15%, respectively. Extensive quantitative and qualitative analyses, including confusion
matrix evaluation, precision recall curves, per-image performance distribution, and tumor size dependency analysis, demonstrate the effectiveness and robustness of the proposed method for
brain tumor
segmentation.
Read the full abstract ▾
All authors Sheekar Banerjee, Md. Srabon Chowdhury, Md. Mahbub Hasan Akash, Ishtiak Al Mamoon
Artificial Intelligence
Huseyin Cavus, Sebin Sabu, Joshua Spear et al. (+2 more)
Interpretable machine learning for Large
Language Models (LLMs) increasingly relies on sparse probing methods that identify small sets of
neurons claimed to detect and causally influence behaviors such as factuality recall, safety
alignment, and
hallucination. These claims have important implications for model
auditing and behavioral steering, yet they are rarely tested against known failure modes of $L_1$-regularized probing in correlated, high-dimensional feature spaces. We propose a five-step diagnostic protocol covering feature correlation, bootstrap stability, sparse versus dense ranking disagreement, intervention baselines, and cross-
dataset evaluation as a minimum standard for sparse-
neuron localization claims. We investigate prior work using our proposed approach, specifically on H-
neurons using open-source LLMs across TriviaQA, BioASQ, and NQ-Open
datasets. Our results demonstrate detection replicates across both models and
datasets, and exceeds the original reported AUROC gaps for TriviaQA and BioASQ
datasets. Gemma 3 4B consistently outperforms MedGemma 4B on matched
datasets, with AUROC gaps of +0.311 versus +0.235 on TriviaQA, +0.474 versus +0.455 on BioASQ, and +0.128 versus +0.112 on NQ-Open respectively. Causal validation at $n = 500$ with five random seeds shows statistically significant effects beyond random same-layer baselines. At the same time, the diagnostic results indicate that the selected
neurons are not uniquely localized. Across the three Gemma 3 4B settings, 19 of 22 selected H-
Neurons have Pearson $|r| > 0.7$ with other features, bootstrap selections show only moderate stability, and sparse and dense rankings overlap only weakly. Our findings show that sparse predictive structure can coexist with non-unique
neuron selection. Routine diagnostic validation is necessary to distinguish detection claims from localization claims in mechanistic interpretability.
Read the full abstract ▾
All authors Huseyin Cavus, Sebin Sabu, Joshua Spear, Jaskaran Singh Kawatra, Pavithra Rajendran
Sound
Joint Analysis of Latent Dimensionality and Frame Rate in Continuous Audio Encoders
Kyudan Jung, Sehyun Lee, Song-ha Jo et al. (+2 more)
Continuous audio encoders compress audio along feature and time axes through latent width and frame rate, but their joint effect on downstream performance remains unclear. We train sixteen encoders spanning four widths and four frame rates, with downstream adapters and probes, using matched training protocols. Despite generally improved reconstruction at larger widths, automatic
speech recognition (ASR) and spoken question answering (SQA) favor moderate widths at higher rates, with the best observed widths shifting toward larger values under stronger temporal compression. Frozen-model PCA interventions reveal distinct reconstruction and recognition sensitivities: removing the trailing half of the components substantially degrades ASR in high-rate 512-dimensional encoders with comparatively small reconstruction penalties, whereas 1024-dimensional encoders largely preserve both. Yet the projected 1024-dimensional model underperforms unmodified narrower models on ASR at 12.5Hz. These findings identify a width–rate interaction in downstream utility and suggest that how representations are organized during training matters beyond reconstruction fidelity and compressibility.
Read the full abstract ▾
All authors Kyudan Jung, Sehyun Lee, Song-ha Jo, Jaegul Choo, Sanghyuk Choi
Computer Vision
Mind the Gap: Mesh-Guided Repair of Broken Vessels
Gniewosz Drwiega, Wojciech Szymanski and Marek Wodzinski
Vessel
segmentation is commonly optimized as voxel-wise classification, but small local errors can strongly disrupt vascular connectivity while having little effect on overlap scores. This is particularly problematic for downstream analyses that rely on centerlines, branches, connected components, or graph structure. We propose a mesh-guided post-processing framework for repairing broken vessel
segmentations produced by nnU-Net. For each predicted binary mask, a deformable template mesh is fitted to the mask surface in physical space and used as a case-specific
geometric scaffold. The fitted mesh is not voxelized as the final
segmentation; instead, it guides conservative reconnection of disconnected components by proposing or validating thin bridge candidates under foreground-growth constraints. We evaluated this approach in three vascular anatomies using AortaSeg24 and SEGA for the aorta, TopCoW for the Circle of Willis, and PARSE for the pulmonary arteries. Performance is measured using Dice, connected-component Dice (ccDice), and the Betti-0 number. Across these
datasets, repair substantially improved connectivity while preserving overlap: Dice remained nearly unchanged, whereas ccDice increased from 0.596 to 0.992 for aorta, from 0.722 to 0.835 for TopCoW, and from 0.028 to 0.862 for PARSE. The FOMAML meta-initialization further accelerated the fitting per-case, supporting practical mesh-based repair of the vascular
topology. These results suggest that explicit mesh representations can provide a useful
geometric prior for correcting topological failures in otherwise accurate voxel
segmentations.
Read the full abstract ▾
Cryptography and Security
Prefilling the Reasoning Channel: Output-Prefix Attacks on Reasoning LLMs
Lukáš Brůna, Robert Bridges and Adam Ek
Large
Language Models (LLMs) consume and produce a single sequence of text; hence, if text can be added to the beginning of the LLM's response, i.e., an output prefix, then all subsequent
tokens will be conditioned on it. This output-prefix attack technique is a cheap black-box
prompt injection. Prior work has shown this type of attack can reliably jailbreak non-
reasoning models. Most
reasoning models add an intermediate scratchpad
reasoning step before the assistant's final response. The ability to edit this
reasoning channel is exposed by some APIs and attack vectors can be leveraged for
reasoning injection attacks. We present the first systematic, controlled study that isolates the scratchpad
reasoning channel as an output-prefix attack vector, and the first to compare
reasoning-only, output-prefix-only and
reasoning-plus-output-prefix attacks across both exposed- and hidden-
reasoning models. Using a factorial design of 3 prefix types $\times$ 2
reasoning injections over $1{,}800$ test cases drawn from AdvBench, we attack three 2026-era frontier models Gemini 3 Flash Preview, DeepSeek V4 Flash, and Claude Haiku 4.5. We find that injecting malicious
reasoning alone is essentially inert ($\approx0\%$ attack success), but injecting the same
reasoning together with a trivial output prefix raises the attack success rate to as high as $99\%$ for some models. For this type of attack we find that contextual prefixes work better than static prefixes; and that susceptibility is dependent on the model.
Read the full abstract ▾
Machine Learning
An Analytical Theory of Auxiliary Learning
Federico Milanesio, Alessandro Ingrosso and Matteo Osella
Auxiliary learning is an optimization paradigm in which a neural network's performance on a target task is improved by jointly training it on additional tasks. However, the mechanisms behind this improvement remain poorly understood. We study this problem using a teacher-student framework and derive a closed system of differential equations describing the dynamics of online
stochastic gradient descent in the large-input limit. For linear networks, we obtain a closed-form expression for the generalization error to leading order in the learning rate, quantifying how task correlations and label noise determine the benefit of auxiliary learning. For non-linear activation functions, we develop a fluctuation-dissipation analytical theory that establishes a general relation linking the main and auxiliary errors to the corresponding single-task error. Numerical experiments support the theoretical predictions and show how auxiliary tasks improve generalization by balancing the forcing dynamics towards the optimal solution with gradient noise.
Read the full abstract ▾
Artificial Intelligence
Breaking the Environment Wall: A Unified Framework for Preparing and Evolving Agent-Native Environments
Yukai Wu, Yuanjing Yang, Le Zhou et al. (+8 more)
Many real-world tasks (e.g., office workflows, scientific experimentation) require LLM
agents to interact repeatedly with their environments for context-dependent operations. However, such environments are often not
agent-ready. First, information is often scattered and fragmented across the environment. Second, relevant evidence in the environment is often mixed with misleading information and conflicting versions. Third, environments evolve over time, introducing new noise and more challenging tasks. These challenges can substantially degrade performance for state-of-the-art AI
agents (e.g., from 83.9% to 57.6%). To address these challenges, we propose Env-Rethink (a system with 27B post-trained model) that supports three main capabilities: (1) It adaptively builds Collection Maps (for organizing related files) and Event Logs (for contextualizing cross-data relationships) to supplement necessary context; (2) It further leverages the post-trained model (through offline trajectory learning) to identify underlying noise issues in the environment; (3) It ultimately evolves environments through virtual event histories that alter environmental states and evidence relationships, producing more tricky ones for further
agent improvement. Experiments show that Env-Rethink can effectively improve downstream task performance (with a 15.1 percentage-point increase in mean rubric pass rate across nine models on 30 tasks).
Read the full abstract ▾
All authors Yukai Wu, Yuanjing Yang, Le Zhou, Shaokun Han, Haoyu Wang, Zirui Tang, Xuzhou Zhu, Weihuang Zheng, Maxm Pan, Xuanhe Zhou, Fan Wu
Machine Learning
WeatherDiagFlow: Evidence-Grounded Radar Nowcasting with Diagnostic Flow Refinement
Chunlei Shi, Yufeng Zhu, Yixiao Liang et al. (+4 more)
Radar nowcasting is essential for short-term warning and emergency response, yet conventional systems mainly return future radar fields and provide limited support for operational communication and post-event verification. We formulate radar nowcasting as an evidence-grounded forecast–bulletin–audit task, in which a numerical forecaster produces both future radar fields and structured diagnostic evidence. Forecast-time bulletins use only model-available evidence, whereas post-event audits incorporate future radar truth only after the forecast horizon is observed. Based on this task formulation, WeatherDiagFlow predicts motion, growth and decay, heavy-echo risk, and uncertainty to condition rolling flow refinement, while frozen-scaffold residual calibration improves long-lead strong-echo preservation. A multi-
agent layer converts the structured evidence into operational bulletins and independently generates verification audits without feeding textual outputs back into the forecaster. Experiments on FJRADAR demonstrate competitive overall performance and improved strong-echo event skill. WeatherDiagFlow therefore connects numerical prediction, evidence-grounded reporting, and auditable verification under a leakage-controlled protocol.
Read the full abstract ▾
All authors Chunlei Shi, Yufeng Zhu, Yixiao Liang, Dan Niu, Yongchao Feng, Qiliang Wu, Jiong Wang
Computation and Language
Decision Models vs. LLMs as Rubric Judges: Cheaper, Faster, and Wrong in the Same Places
Delip Rao and Chris Callison-Burch
LLM judges now score outputs against rubrics, in
benchmarks and as training rewards. Decision models return probabilities over permitted answers with a confidence score but no free text. Two such models are Jev and an open reproduction, Perplexity's Decider. We compare each with three flash-tier LLM judges on nine panels from seven
benchmarks with human judgments, giving every judge identical criterion texts. The LLM judges run in two setups, reading a whole rubric at once or one criterion at a time. Our findings suggest both decision models can often stand in for them. The LLM judges cost 16 to 357 times as much and take 5 to 350 times as long, yet in both setups each decision model trails them significantly in at most 6 of 27 comparisons. The two kinds of judge err alike, agreeing more with one another than with the human-annotated judgment labels on ordinal criteria. Over 85% of flash-tier LLM verdicts on either decision model's most confident errors repeat them, where independent errors would give about half. Each decision model's confidence ranks its errors on most ordinal panels, so each is a natural first stage for a cascade deferring uncertain verdicts to an LLM judge. Yet with flash-tier fallbacks, such cascades gained a mere 2.7 points at best over the strongest single judge, even with oracle thresholds, suggesting they mainly save cost. A cascade needs a fallback that is right where its first stage errs, but the LLM judges are mostly wrong in the same places as Jev, and the Decider is already the strongest single judge on most panels. Even each vendor's higher-tier model repeats those errors, and as a fallback it lifted no cascade more than 1.7 points above both tiers' strongest single judge. Holding across setups, effort levels, and tiers, these findings suggest designing future decision models afresh to get right what LLM judges get wrong, and vice versa.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from eess.AS
Anatomy-aware cross-speaker adaptation of complete vocal-tract acoustic-to-articulatory inversion
Nhat-Nam Nguyen, Pierre-Andre Vuissoz and Yves Laprie
Cross-speaker acoustic-to-articulatory inversion requires accounting for anatomical differences between speakers. We propose a
geometric adaptation framework that uses anatomical landmarks, primarily on vertebrae and dental structures,to transfer predictions from a fixed inversion model to unseen speakers. An affine transformation followed by thin-plate spline (TPS) deformation maps the predicted contours of 10 vocal-tract structures into each target speaker's geometry without retraining. Landmarks are identified in one selected /u/ frame per speaker as a common phonetic reference without assuming identical articulatory configurations across speakers, and the resulting mapping is reused across recordings. We train the model on a single-speaker rt-MRI database and evaluate adaptation on eight speakers from a separate multi-speaker rt-MRI database. We compare affine and TPS configurations using 12 or 14 landmarks. Affine12+TPS14 achieves the lowest mean point-to-closest-point error of 3.19mm. These results support the combined value of anatomical landmark information and nonrigid
alignment.
Read the full abstract ▾
Performance
Dense Matrices Are Alike; Sparse Matrices Are Sparse in Their Own Way: A Structure-Adaptive Tile Cholesky Factorization
Esmail Abdul Fattah, Hatem Ltaief, Håvard Rue et al. (+1 more)
Sparse direct Cholesky solvers fix one data structure for an entire
matrix, but symmetric positive definite systems range from nearly dense to irregular, sometimes mixing both within one
matrix. We let the data structure follow the sparsity structure, across
matrices and across tiles within a
matrix. Before numerical work starts, a lightweight selector captures the sparsity pattern of the Cholesky factor and routes the
matrix, on one static shared-
memory schedule, to one of three regimes: dense, sparse, or an intermediate semisparse regime. Dense tiles are stored in full; the semisparse regime uses a new active-column tile that keeps only the columns the factorization will touch, so banded or arrowhead-shaped structures common in spatial models still reach BLAS-3 efficiency. The approach suits the integrated nested Laplace approximation (INLA): one sparsity pattern factorized thousands of times with different values, so the one-time analysis cost is amortized and every factorization saving compounds. We evaluate the technique on 60 SPD
matrices, comparing against MUMPS, PaStiX, CHOLMOD, symPACK, and Intel oneMKL PARDISO on Intel Xeon and AMD EPYC nodes; the selector alone achieves the lowest total factorization time in every regime. Summed over the suite, it beats the best fixed single-structure mode by 1.6 to 2.6x, and every alternative by 1.8 to 12.5x on Intel and 2.6 to 10.1x on AMD, with the largest gains on the most expensive factorizations. It trades more one-time analysis for less time per factorization, pulling ahead by the third factorization of a given pattern. As a first GPU extension, the dense route on one NVIDIA A100, with the factor resident on the device, runs 1.2 to 6.3x faster than on the faster CPU node, the margin widening with factor size. Solver, Python/R/Julia interfaces,
benchmark suite, and results are open at https://github.com/esmail-abdulfattah/sTiles.
Read the full abstract ▾
All authors Esmail Abdul Fattah, Hatem Ltaief, Håvard Rue, David E. Keyes
Robotics
PolyUMI: Accessible Visual-Tactile-Audio Data Collection for Object Inference and Manipulation
Conor W. Hayes, Rickmer Krohn, Aravind Ramaswami et al. (+6 more)
Humans typically rely on
vision, touch, hearing, and proprioception to perceive contact and adapt their actions during manipulation. Providing
robots with comparable responsiveness therefore requires hardware that can retain and use these complementary sensory signals. Most imitation-learning systems, however, observe demonstrations primarily through
vision and proprioception, limiting access to contact information that is difficult to infer visually. We present PolyUMI, an open-source platform for scalable visual–tactile–audio demonstration collection and
robot deployment. Its lightweight, wireless handheld gripper records synchronized wrist-camera, optical tactile, contact-audio, and proprioceptive observations without requiring a tethered workstation. The same sensing finger can be transferred to the
robot end effector, preserving the sensing geometry between demonstration collection and policy execution. To effectively use these heterogeneous observations, we further introduce VisTA, a
token-level
multimodal policy that integrates information across sensors and time to predict contact-aware
robot actions. Experiments spanning object inference, slip control, and contact-rich manipulation show that touch and audio reveal task-relevant information beyond
vision and that VisTA is competitive with or outperforms existing
multimodal policies. Together, PolyUMI and VisTA provide an accessible pipeline for collecting
multimodal demonstrations and learning policies that perceive physical interaction beyond
vision. Project Page: https://polyumi-vista.github.io
Read the full abstract ▾
All authors Conor W. Hayes, Rickmer Krohn, Aravind Ramaswami, Anunth Ramaswami, Nils Dengler, Kevin M. Lynch, J. Edward Colgate, Georgia Chalvatzaki, Matthew L. Elwin
Cryptography and Security
OllamaDrama: Designing and Deploying a Honeypot to Measure Attacks on Exposed LLM Infrastructure
Karina Elzer, Niklas Netterstrøm Johansen and Emmanouil Vasilomanolakis
Publicly exposed large
language model (LLM) infrastructure creates a growing attack surface, yet real-world targeting remains poorly understood. We present Ollure, a low- and medium-interaction honeypot that emulates the Ollama API without a backend LLM. Spanning four deployments across cloud and university networks, Ollure operated for 84 days and recorded 290,887 interactions from 2,793 unique source IP addresses. Most of the activity consisted of automated discovery, fingerprinting, and model enumeration. However, we also observed concrete exploitation attempts against both the infrastructure and LLM layers. These included model management abuse, path traversal and SSRF probes, RCE and cryptocurrency mining payloads, resource exhaustion attempts,
prompt injection, information extraction, and
agent-oriented tool use. Our results provide empirical insight into real-world threats against exposed, self-hosted LLM services.
Read the full abstract ▾
Discrete Mathematics · Cross-listed from math.PR
Boolean threshold functions, neuron capacity, and memory retrieval
Xinyuan Xie
How much information can a single
neuron remember? How many
memories can neural networks retrieve without creating false
memories? These questions are related to a basic question: how many Boolean threshold functions $f(x)=\operatorname{sgn}(a_0+\langle a,x\rangle)$, $x\in\{-1,1\}^n$, are there? In this paper, we show that the number $T_n$ of distinct Boolean threshold functions is \[ T_n=2\binom{2^n-1}{n}\bigl(1+O(n^{-99})\bigr). \] Equivalently, the capacity of a single threshold
neuron is $n^2-\log_2(n!)+1+O(n^{-99})$ bits, improving the $O(n)$ error term in the result of Kahn–Komlós–Szemerédi to $O(n^{-99})$. To prove this, we show that, for $1\le r\le n-1$, and $v_1,\ldots,v_r$ are chosen at random from $\{-1,1\}^n$, \[ \mathbb P\!\left\{ \langle v_1,\ldots,v_r\rangle\cap\{-1,1\}^n =\{\pm v_1,\ldots,\pm v_r\} \right\} =1-O(n^{-99}). \] In the context of the Kanter–Sompolinsky
Hamiltonian for
memory retrieval, this identifies $r=n-1$ as a sharp threshold, at which, for almost every collection of $r$
memories, the only ground states are these
memories and their negatives, confirming a weaker form of the Kalai–Linial–Odlyzko
conjecture. It also settles a recent open problem posed by M. Anthony on the specification number of Boolean threshold functions. In addition, we show that, for every $1\le r\le n-1$, \[ \mathbb P\{v_1,\ldots,v_r\text{ are linearly dependent}\} =2\binom r2\,2^{-n}+O\!\left(2^{-n}e^{-cn}\right), \] confirming a
conjecture of Kahn–Komlós–Szemerédi.
Read the full abstract ▾
Neural and Evolutionary Computing
On Growth and Form, and Function: Reusable Regulatory Handles Control Phenotypic Variation
Benedikt Hartl, Milton L. Montero, Marcello Barylli et al. (+2 more)
How phenotypic transformations are implemented by changes in underlying regulatory dynamics remains a central question in developmental biology. Inspired by D'Arcy Thompson's 1917 "On Growth and Form", we ask whether coherent large-scale transformations of morphology can be encoded as low-dimensional modulations of a self-organizing developmental system. We use neural cellular automata (NCAs) as bio-inspired models of distributed development, in which a shared local regulatory network grows target morphologies from a single
cell. We apply low-rank adaptation (LoRA) to pretrained NCAs, representing each adapted developmental program as a low-rank modulation of a fixed regulatory scaffold. Horizontal and vertical scaling of a fully grown 2D emoji phenotype can each be implemented by rank-one adaptations. Their linear combinations parametrically control phenotype size, generalize beyond the training distribution, and compose with target-specific adapters. Strikingly, adaptations learned for one phenotype transfer zero-shot across structurally and semantically diverse phenotypes sharing the same reference scaffold, while largely preserving internal features. This suggests reusable system-level hyper-directions of scale rather than morphology-specific transformations. From approximately 25,000 independently trained phenotype-specific NCA adapters with a shared scaffold, we further identify latent low-dimensional directions that functionally control phenotypic variation including scaling, style, and symmetrical fission. Together, our results provide a computational realization of D'Arcy Thompson's remarkable grid transformations in a 2D NCA—a minimal cybernetic tissue in which variations of fully grown emoji phenotypes can be encoded, combined, and controlled through low-dimensional directions in regulatory weight space.
Read the full abstract ▾
All authors Benedikt Hartl, Milton L. Montero, Marcello Barylli, Sebastian Risi, Michael Levin
Software Engineering
SWE-PolyVision: Benchmarking Cross-Image Abductive Reasoning for Repository-Level Software Engineering
Jiajun Wu, Leixin Sun, Zihan Tan et al. (+12 more)
Current
multimodal software-engineering
benchmarks expose images as additional context, but do not test whether an
agent can integrate evidence distributed across images into a verified repository-level repair. We present SWE-PolyVision, an executable
benchmark of 92 real tasks from 36 open-source organizations, with 48 public tasks and 44 private holdouts. The release contains 402 static images and 6
videos, with at least two visual inputs per task. Each task pairs a fixed pre-fix repository with an isolated verifier and is evaluated under the supported conditions among three access modes: Text-only, Native
Vision, and Tool-mediated
Vision. Across eleven coding models, visual access changes which tasks are solved, but effects depend on both model and task. Two trace-linked Native
Vision cases illustrate how complementary visual and textual clues can lead to source-localized, verified repairs; controlled interventions show that this conversion is not yet stable across inputs. SWE-PolyVision thus separates the availability of multi-image evidence from its successful use in repository-level repair, without treating patch success alone as proof of explicit
reasoning.
Read the full abstract ▾
All authors Jiajun Wu, Leixin Sun, Zihan Tan, Yitao Liu, Zhenjun Zhao, Danyang Zhang, Shuo Li, Jiaru Qian, Yuxin Wu, Shanghaoran Quan, Chuangxin Zhao, Yangxu Liao, Yang Liu, Bin Chong, Guancheng Wan
Robotics
From Target Selection to Digging: A Learning-Based Framework for Continuous Autonomous Excavation
Shuai Zhao, Ji-an Pan, Quantao Yang et al. (+4 more)
Repeated excavation continuously reshapes pile geometry, requiring an autonomous excavator to adapt its digging targets and coordinate motion across successive excavation cycles. We present a learning-based framework for continuous autonomous excavation that integrates terrain-aware target selection with reinforcement- and imitation-learning controllers. The framework separates target-conditioned motion from local digging: a shared task-conditioned RL policy controls waypoint-guided approach and loaded transport, while an IL policy learns
vision-based digging and lifting from expert demonstrations. Digging targets are selected from
LiDAR elevation maps and converted into bucket-tip waypoints for motion control. The control architecture coordinates the learned policies and deterministic unloading through a shared motion interface. The complete system is deployed on a scaled hydraulic excavator with
multimodal sensing and closed-loop actuator control. Offline replay and physical experiments demonstrate more consistent target selection, shorter local motion time, and increased payload compared with the respective baselines. The learned digging policy achieves a mean payload of 6.52 kg per completed cycle, compared with 2.68 kg for Fixed Dig. Three five-scoop runs further demonstrate consecutive autonomous excavation under continuously changing pile geometry.
Read the full abstract ▾
All authors Shuai Zhao, Ji-an Pan, Quantao Yang, Zheng Wang, Chaoyi Chen, Qing Xu, Keqiang Li
Sound
Relative Mismatch: Local-Reference Calibration of Feature-Space Flows for Anomalous Sound Detection
Anbai Jiang, Xinhu Zheng, Lvxin Xu et al. (+6 more)
Anomalous sound detection (ASD) has long been dominated by k-nearest-neighbor (KNN) based detectors, which essentially perform implicit likelihood estimation over normal samples. In this work, we investigate whether generative models can better serve this role. We propose Relative Mismatch, a generative ASD backend powered by flow matching, which learns a velocity field that transports Gaussian noise to a representative feature space of normality. During inference, it measures the mismatch between the oracle and predicted path velocities and aggregates them through a two-level design. To mitigate the inherent mismatch offsets incurred by domain shift, each query is further calibrated with the mismatch of its local normal reference, thereby exposing only its deviation beyond normality. Extensive experiments on DCASE 2020–2025 demonstrate that Relative Mismatch outperforms state-of-the-art backends with the highest score of 71.01, along with strong robustness and training stability. Furthermore, we show that curating a compact and discriminative feature space is the key to unleash the power of generative models for ASD.
Read the full abstract ▾
All authors Anbai Jiang, Xinhu Zheng, Lvxin Xu, Shuwei Zhang, Wenrui Liang, Pingyi Fan, Wei-Qiang Zhang, Cheng Lu, Jia Liu
Cryptography and Security
Improving the Reliability of Anomaly Detection for Encrypted OPC UA Traffic over Private 5G
Song Son Ha, Florian Foerster, Henry Beuster et al. (+3 more)
Open Platform Communications Unified Architecture (OPC UA) is increasingly deployed over private 5G networks in industrial environments, where end-to-end encryption prevents payload inspection by network-based intrusion detection systems (IDSs). Although payload-agnostic statistical features extracted from encrypted traffic enable traffic-based anomaly detection, benign connectivity variations may alter observable user-plane (UP) behavior and increase the false-positive rate (FPR). This paper investigates this reliability problem and proposes a control-plane (CP)-aware decision adaptation for four frozen IDS models. CP indicators at the user equipment (UE) level are used to construct a temporal CP context in which a CP-specific threshold selected on adaptation validation data is applied, while the original threshold remains active outside the context. The traffic features, attack scores, preprocessing procedure, and trained model parameters remain unchanged. Evaluation on a real industrial private 5G testbed shows that benign connectivity variations increase the FPR for all four evaluated models and that false positives are concentrated within periods temporally associated with CP activity. The proposed CP-aware decision adaptation reduces both global FPR and FPR within the CP context while introducing a configurable trade-off between FPR reduction and retained recall over the complete attack campaign. These findings demonstrate that CP context can improve the operational reliability of encrypted-traffic intrusion detection without retraining the underlying models.
Read the full abstract ▾
All authors Song Son Ha, Florian Foerster, Henry Beuster, Tim Kittel, Dominik Merli, Gerd Scholl
Software Engineering
Between the Commits: Process, Error, and Claim Reliability in a Wholly AI-Authored Codebase
Douglas Leith
We present: (i) a new
dataset consisting of the full development history of a 21,000-line Python tool built entirely by Claude AI, with no human-authored code or tests, (ii) two code-provenance tracing tools, (iii) three taxonomies for instruction intent, commit provenance, and response reliability, (iv) application of these to analyse the
dataset. We find that: (i) user coding
agent CLI instructions differ in kind from IDE-chat instructions, with a greater focus on comprehension, planning and consultation, (ii) code development is mainly proactive, (iii) 14.3% of AI code-generation events contain a real error later caught by the AI-authored test suite, (iv) roughly 1 in 4-5 of the AI's interactive responses contains one or more factual errors.
Read the full abstract ▾
Artificial Intelligence
AI-based detection of worsening heart failure from low-resolution telemonitoring data
Erik Aerts, Yinan Yu, Annika Rosengren et al. (+5 more)
Objective: Heart failure (HF) presents a healthcare challenge due to its high comorbidity burden, aging patient population and frequent hospitalizations. Remote monitoring offers a promising approach to managing HF patients by early detection of health deterioration. Developing autonomous systems to detect signs of worsening in telemonitoring data is of interest to reduce the workload of healthcare personnel. Methods: We propose the TRACER model, a
Transformer with Contrastive Event Representation, designed to predict timelines leading to rare hospitalization events in low-resolution and irregularly sampled telemonitoring data. TRACER incorporates time-aware
embeddings for each biomarker, contrastive pre-training to enhance anomaly detection via representation learning, and independent binary classifiers for detection. We used measurement data containing remotely recorded biomarker sequences from 276 HF patients segmented into overlapping windows based on temporal rules, and labeled the windows based on the occurrence of HF relevant hospitalizations at the latter edge of the window. Results: TRACER was able to correctly predict 66.7% timelines leading up to HF hospitalizations in the highly imbalanced real-world
dataset with an overestimation of 7.9%. Reformulating the training of TRACER as an event detection problem improved the predictive performance compared with training directly on
forecasting windows, enabling more effective use of the limited hospitalization events. Conclusion: TRACER demonstrated superior performance in detecting signs of worsening status in real-world telemonitoring data compared to the other tested models. Significance: TRACER shows promise in identifying signs of clinical deterioration that allow for alerts to be generated to provide counteractive treatment in patients with HF.
Read the full abstract ▾
All authors Erik Aerts, Yinan Yu, Annika Rosengren, Michael Fu, Martin Lindgren, Falk Dippel, Martin Adiels, Helen Sjöland
Machine Learning
TopU-LBVS: A Realistic Multi Target Benchmark for Ligand Based Virtual Screening
Surbhi Kumar, Yuhe Zhou, Varun Shiralkar et al. (+2 more)
Ligand-based virtual screening (LBVS) is a practical first-pass tool in early-stage drug discovery, but existing
benchmarks can overestimate performance through random negatives, easy decoys, limited target coverage, and non-standardized evaluation protocols. We introduce TopU-LBVS, a multi-target
benchmark for LBVS under hard-negative screening conditions. Starting from curated ChEMBL~35 bioactivity data, TopU-LBVS covers 93
protein targets across 7
protein classes and constructs target-specific screening libraries with property-matched, structurally similar decoys at a fixed 1:40 active-to-decoy ratio. Libraries contain roughly 400 to 10,000 compounds and are designed to reduce simple physicochemical and nearest-neighbor fingerprint shortcuts. TopU-LBVS provides three fixed protocols. TopU-LBVS-full evaluates ChEMBL$^\ast \rightarrow$ TopU generalization across all 93 targets. TopU-LBVS-low evaluates low-data TopU $\rightarrow$ TopU learning within the hard-negative distribution. TopU-LBVS-mini provides a compact seven-target protocol with a paired random-decoy control that changes only the test decoys, enabling low-cost development and direct measurement of the gap between random ChEMBL$^\ast$ and TopU decoys. Across ten reference baselines spanning fingerprint methods, molecular GNNs, fingerprint hybrids, and modern molecular models, performance under random-decoy evaluation degrades sharply under hard-negative screening. We release data, fixed splits, evaluation code, and baseline implementations for reproducible comparison of future LBVS and molecular representation learning methods. Code and data are available at https://github.com/topu-
benchmark/topu-lbvs and https://huggingface.co/
datasets/topu-
benchmark/topu-lbvs.
Read the full abstract ▾
All authors Surbhi Kumar, Yuhe Zhou, Varun Shiralkar, Niu Huang, Baris Coskunuzer
Robotics
Combining Evasive and Braking Reactions for Safety Reference Models in Automated Vehicles
Riccardo Donà, Konstantinos Mattas and Biagio Ciuffo
Computational models of careful and competent human drivers are essential for scenario-based evaluation of automated driving systems (ADS). However, most existing safety reference models primarily focus on longitudinal braking, neglecting the role of evasive steering in human collision avoidance. This paper proposes a hybrid Fuzzy-Safety Model (FSM-H) that integrates longitudinal mitigation and lateral avoidance within a unified behavioral framework. The braking component is governed by Proactive Fuzzy Safety (PFS) metrics, representing the erosion of longitudinal safety margins, while the steering component is driven by Criticality Fuzzy Safety for lane-change (CFS-LC), capturing lateral conflict severity and maneuver feasibility. A finite-state architecture models the sequential escalation from nominal driving to braking and, when necessary, to evasive steering, incorporating perception-reaction time and lane-check delays to reflect human decision processes. The model is evaluated in reconstructed high-criticality cut-in scenarios and compared with braking-only and steering-only reference strategies. Results show that the hybrid approach expands the preventability envelope while maintaining behavioral plausibility and computational tractability. The proposed framework provides a transparent and explainable human reference model suitable for simulation-based ADS safety benchmarking and regulatory assessment.
Read the full abstract ▾
Sound
No Time to Collapse: Unlocking Robustness and Multiplexed Capacity in Frozen Audio Watermarkers
Xuanye Wang, Linxi Li, Yechen Wang et al. (+3 more)
Modern neural audio watermarking systems typically embed a message repeatedly across time and then collapse the resulting temporal evidence into a single payload using averaging, voting, or another fixed aggregation rule. We argue that this temporal collapse limits both robustness and the recovery of multiple payloads, and that the limitation can be addressed without retraining the underlying watermarker. We freeze a pretrained watermarker's encoder and detector and train only a low-latency Conformer-based decoder. The decoder consumes the detector's temporal soft outputs, which a system-specific adapter pools into a sequence of window-level representations, and predicts the embedded message. On three frozen watermarkers (AURA, AudioSeal, and WavMark), the learned decoder improves recovery of attacked messages and yields higher detection AUROC point estimates on all three. Under controlled full- and partial-coverage multiplexing, it improves joint-exact recovery of two alternating payload words by 9.7-48.0, 6.9-17.3, and 8.2-14.2 percentage points, respectively, under one to three chained attacks on feasible clips.
Read the full abstract ▾
All authors Xuanye Wang, Linxi Li, Yechen Wang, Liwei Jin, Qianwei Guo, Carsten Maple
Artificial Intelligence
C3M: Cross-Session Multimodal Memory Maintenance for Long-Horizon Tasks
Xueshu Chen, Yan Wang, Zihao Xue et al. (+5 more)
Long-horizon tasks require preserving and later recovering cross-session evidence under a bounded, query-blind
memory budget. Existing compression can discard fine-grained visual cues or conflate semantically similar but incompatible observations. We present C3M, a cross-session
multimodal memory organization that maintains a bounded active index over persistent source text-image evidence. Relation-aware updates consolidate safe redundancy while preserving complementary and incompatible records. At query time, budgeted routing selects useful index pages and expands their associated source evidence under a fixed reader budget. Together, these mechanisms establish a compact, provenance-preserving
multimodal memory organization for cross-session long-horizon tasks, retaining temporal distinctions and source links required for reliable downstream
reasoning. Code is available at https://github.com/HuzhouNLP/C3M.
Read the full abstract ▾
All authors Xueshu Chen, Yan Wang, Zihao Xue, Jiefu Li, Zhenfang Liu, Jayden Chen, Zhen Bi, Jungang Lou
Numerical Analysis · Cross-listed from math.AP
Eigendamage: an Eigendeformation model for the variational approximation of cohesive fracture in antiplane shear deformations
Veronika Auer-Volkmann, Lisa Beck and Bernd Schmidt
We set up and investigate an approximation scheme for a variational theory of cohesive fracture in antiplane shear deformations. We consider a family of functionals acting on scalar valued functions in general dimensions depending on a small parameter $0 < \varepsilon \ll 1$ and on two fields: the elastic part of the displacement field and an eigendeformation field that describes the inelastic response of the material beyond the elastic regime. We measure the inelastic contributions of the latter in terms of a non-local energy functional. Our main result shows that, as $\varepsilon \to 0$, the approximate functionals $\Gamma$-converge to a cohesive zone model.
Read the full abstract ▾