Computer Vision
Beyond Recognition: Compact Multi-Domain Arabic Manuscript HTR with Candidate-Selection Analysis and Evidence-Preserving Review
Abdullah Ahmed Ali, Mohammed Thamer Abdulhadi, Ali Haider Safaa et al. (+1 more)
Historical Arabic manuscript transcription is not only a recognition problem. A usable scholarly system must cope with shifting hands and layouts, preserve uncertain readings, distinguish visual evidence from linguistic plausibility, and record the researcher's final decision. We present Phoenix, a 4.99-million-parameter CNN-BiLSTM-CTC recognizer, and Athar, an evidence-aware review workflow built around it. Phoenix is adapted across archival, Maghrebi, and historical manuscript domains using document-aware replay, an expanded 81-symbol codec, and forgetting guards that reject checkpoints that improve a new domain at unacceptable cost to previous domains. In a pre-specified held-out comparison against the preceding checkpoint, frozen before evaluation and scored with greedy decoding and raw references, Phoenix reduced CER from 22.12% to 17.86% on 10,594 Agapet lines and from 17.72% to 11.84% on 11,684 Omar lines, while regressing from 10.39% to 10.72% on 164 TariMa lines. Across the two large held-out sets, character-weighted CER fell from 19.98% to 14.93%, a 25.3% relative error reduction. A separate same-protocol development diagnostic found the lowest CER for Phoenix on four of four comparable domains (9.59% unweighted macro CER). An N-best diagnostic revealed a 2.15-point oracle gap between beam decoding and Oracle@25, while neural text rerankers, consensus MBR, CTC-posterior quality estimation, and local pre-CTC hidden-state quality estimation recovered less than 4% of this gap. Athar therefore preserves the visual reading, exposes bounded alternatives, uses local
language models conservatively, retrieves source parallels with unique, ambiguous, or abstain states, and exports auditable TEI and PAGE-XML records. The results support evaluating manuscript HTR as auditable evidence management rather than silent text replacement.
Read the full abstract ▾
All authors Abdullah Ahmed Ali, Mohammed Thamer Abdulhadi, Ali Haider Safaa, Dhulfiqar Mahdi Wadi
Numerical Analysis
A high-order, meshless, Lagrangian–Eulerian RBF-FD method for advection–diffusion–reaction on moving manifolds
Matthew Lowery, Grady B. Wright and Varun Shankar
We present a high-order radial basis function-generated finite difference (RBF-FD) method for partial differential equations on moving
manifolds $\mathcal M(t)\subset\mathbb R^3$ of co-dimension one. Our method builds on the tangent-plane formulation of surface RBF-FD and combines Lagrangian and Eulerian treatments: the
manifold and material derivative are evolved in a Lagrangian fashion, while the remaining surface differential operators are reconstructed on the instantaneous point cloud and stabilized, when necessary, by a quasi-analytical hyperviscosity formulation. Lagrangian marker drift is handled by adaptive rearrangement using a compact global parametric model of the moving surface, which also supplies accurate normals and geometry-based quadrature. After rearrangement, we reconstruct the multistep history by backward semi-Lagrangian tracing and interpolation before resuming the Lagrangian time discretization. We exploit temporal coherence through three update strategies: defect correction for the local RBF-FD weights, a
curvature-based update of the hyperviscosity coefficients between spectral recomputations, and a global defect-correction iteration that reuses an incomplete LU (ILU) factorization before preconditioned generalized minimal residual (GMRES) iterations. Finally, we enforce the prescribed global mass balance through a scalar projection based on the evolving surface quadrature. Numerical experiments demonstrate high-order convergence, conservation to roundoff in source-free problems, stable long-time integration, and substantial savings from the proposed update strategies.
Read the full abstract ▾
Social and Information Networks
Fairness-Aware Network Embeddings: Methods, Applications, and Challenges
Ella Has, Harshith Kumar Yadav, Gaurav Dixit et al. (+2 more)
Network
embedding methods learn low-dimensional representations of graph-structured data to support downstream tasks such as node classification, link prediction, and influence maximization. However, real-world networks often reflect structural inequalities arising from demographic imbalances, homophily, and other societal biases, which
fairness-agnostic
embedding methods can encode and amplify. To address this issue, numerous
fairness-aware network
embedding methods have been proposed to mitigate bias while preserving
embedding utility. This survey presents a comprehensive overview of
fairness-aware network
embeddings for complex networks. We propose a taxonomy that categorizes existing methods along three main complementary dimensions: underlying
embedding approach (spectral, random walk, graph neural network,
Bayesian, and method-agnostic),
fairness intervention strategy (pre-processing, in-processing, and post-processing), and
fairness objective criterion (
embedding- or task-level). We further compare methods with respect to group versus individual
fairness and assumptions regarding sensitive attributes. Finally, we discuss current limitations and highlight promising future research directions. This survey provides a unified perspective on
fairness-aware network
embedding and serves as a reference for developing fair and trustworthy network representation learning methods.
Read the full abstract ▾
All authors Ella Has, Harshith Kumar Yadav, Gaurav Dixit, Mykola Pechenizkiy, Akrati Saxena
Computer Vision
CAViAR: A Causal Video Dataset for Fine-Grained Accident Reasoning in Real-World Scenarios
Sparsh Garg, Yi-Wen Chen, Vijay Kumar B G et al. (+1 more)
While modern autonomous driving systems excel at perception tasks such as object detection and trajectory prediction, they lack the high-level causal
reasoning required to interpret traffic accidents. In particular, determining responsibility, such as identifying who is at fault and which traffic rule was violated, remains largely unexplored in current
benchmarks. To this end, we introduce CAViAR (Causal Accident
Video and Incident Analysis Repository), a human-annotated dashcam
benchmark comprising 2,249 real-world accident
videos collected from CarCrashDataset (CCD) and Nexar. Each
video is annotated with structured labels spanning environmental conditions, accident type, causal explanation, apparent At-Fault
Agent, affected
agent, and apparent rule-violation category. We
benchmark state-of-the-art
vision-
language models (VLMs), including Cosmos-Reason2, Qwen3-VL, and InternVL3. Once class imbalance is accounted for with majority/random baselines and balanced metrics, perceptual competence is uneven–lighting is nearly solved, whereas weather and road-condition accuracy fall at or below the majority-class baseline—and all models degrade sharply on accident type and responsibility
reasoning. Overall, CAViAR exposes a practical Perception–
Reasoning Gap: current VLMs may recognize salient context, but do not reliably map visible
agent actions to annotated rule-relevant responsibility categories in safety-critical driving scenarios. Code, annotation schema,
prompts, and evaluation scripts are available at: https://github.com/nec-labs-ma/CAViAR
Read the full abstract ▾
All authors Sparsh Garg, Yi-Wen Chen, Vijay Kumar B G, Abhishek Aich
Computers and Society
Multi-Tier Mentorship with AI-Assisted Development: Authentic Engineering for K-12 and Undergraduates
Kelly Yuan, Ronald Liu, Daniel Crawford et al. (+1 more)
K-12 students often possess creative engineering ideas but lack technical skills to build them, while undergraduates have coding expertise but few opportunities to lead real-world projects or mentor others. The rapid development of AI-assisted tools offers a potential bridge to connect these groups, yet the structure for effective K-12 and university collaborations remains underexplored. This paper introduces a multi-tiered mentorship framework enabling high school students to engage in authentic engineering through AI-assisted development using large
language models and AI
agents, while undergraduate mentors provide architectural oversight. We test this framework through LuckyTag, a
privacy-preserving NFC-based lost-and-found system. The model positions high schoolers as product leads, undergraduates as technical architects, and faculty as minimal-intervention advisors. A pilot with four high school students, three undergraduates and two faculty yielded survey data showing high perceived barrier removal and gains in system architecture understanding. Thematic analysis reveals that AI amplifies rather than supplants mentoring demands, requiring human oversight for logic and security. These findings suggest a hybrid model for equitable K-12 and university collaboration on computing integration that emphasizes "AI micromanagement" and architectural
reasoning over traditional syntax.
Read the full abstract ▾
All authors Kelly Yuan, Ronald Liu, Daniel Crawford, Weihao Qu
Machine Learning · Cross-listed from stat.CO
Heteroscedastic Neural Surrogate Modeling for Robust and Rapid Bayesian Inference in Fusion Plasma Diagnostics
Liyun Zhang, Naoya Mamada, Kentaro Sakai et al. (+2 more)
Bayesian inference via Markov Chain Monte Carlo (MCMC) provides effective parameter estimation, but its real-time application in complex physical systems is hindered by heavy computational bottlenecks and extreme sensitivity to statistical noise. We address this by proposing a neural-network-based probabilistic surrogate framework for rapid and robust MCMC inference. Using fusion
plasma Thomson scattering diagnostics as a challenging, noise-dominated testbed, our approach employs a dual-head architecture to simultaneously estimate the expected physical emission spectrum and the channel-wise intrinsic measurement noise variance. By optimizing a Gaussian Negative Log-Likelihood (GNLL) objective, the learned aleatoric uncertainty dynamically buffers the sampler against pathological shot noise. Evaluations demonstrate that this surrogate framework achieves > 1500x acceleration over exact physical forward models, while simultaneously reducing inference error (RMSE) by >20% compared to standard homoscedastic neural baselines, offering a highly promising paradigm for real-time physical analysis.
Read the full abstract ▾
All authors Liyun Zhang, Naoya Mamada, Kentaro Sakai, Takeo Hoshi, Toru Aonishi
Computer Vision
Does Marginal Coverage Guarantee Class-Conditional Safety for Zero-Shot VLMs Under Shift?
Jai Kumar Sharma and Amartya Dutta
Split-conformal prediction provides marginal coverage under exchangeability and is increasingly used as an abstention layer for zero-shot
vision-
language models (VLMs). We audit this practice under deployment shift for CLIP, OpenCLIP, and SigLIP across ImageNet and non-ImageNet settings. Marginal coverage can remain relatively high while class-conditional tail coverage collapses: on ImageNet-Sketch, worst-class coverage falls to $\approx 0$ and 10-12% of classes lie below a finite-sample null floor, despite marginal coverage of about 0.86. The failure is aligned with target-domain class accuracy but is not predicted by the source-domain diagnostics we test. Source-side Mondrian calibration improves the in-distribution tail but does not transfer, while clustered conformal and Conf-OT improve marginal or average metrics without recovering the worst-class tail. Target-side class calibration substantially lifts the tail, but requires labels for every class and remains set-size-intensive. We further identify a 2-3$\times$ cross-family efficiency gap and show that native SigLIP sigmoid scores remove APS's probability-mass interpretation. The findings persist across the tested model scale, pretraining corpus,
prompt, miscoverage level $\alpha$, and shifted non-ImageNet settings. Marginal conformal coverage should therefore be treated as an average reliability statistic, not as a safety guarantee for the class tail.
Read the full abstract ▾
Robotics
Learning the Right Abstraction: Neural Reduced Dynamics for Complex Robot Control
Harry Zhang and Dan Negrut
High-fidelity
embodied AI simulators provide realistic evaluation of complex robotic systems, but their computational cost limits their direct use for large-scale reinforcement learning campaigns. We advocate the use of less accurate but more expeditious simulations, which might draw on data-driven, e.g., neural dynamics, models. This contribution argues that the practical value of a neural dynamics model for complex
robot control lies in learning the right abstraction: a reduced state that preserves the control-relevant physics of the high-fidelity system while enabling high-throughput policy learning. We develop a neural reduced dynamics (NRD) framework that separates the state the model propagates from what can be supplied as an input or recovered analytically, trains policies entirely inside the frozen learned model, and validates them back in the high-fidelity simulator. Two case studies instantiate it across three control tasks: terrain-aware HMMWV trajectory tracking on rigid, bumpy and deformable Continuum Representation Model (CRM) terrain; and goal reaching for a stock tracked vehicle and its front-mounted articulated arm. Every policy transfers back to the high-fidelity simulator. A single policy trained inside the terrain-conditioned dynamics model, and given no terrain input of its own, attains lower median and mean tracking error than both single-terrain specialists on all three terrains, including zero-shot bumpy terrain. Quantitatively, the tracked vehicle reaches 100 of 100 goals and the arm 97 of 100, with zero contacts or joint-limit violations. The NRD models advance roughly four orders of magnitude faster in simulated time than the high-fidelity simulator scenes they replace, making iterative on-policy learning practical and supporting neural reduced dynamics as a bridge between accurate but expensive physics simulation and scalable
robot learning.
Read the full abstract ▾
Robotics
The Missing Touch: Spatially Distributed Tactile Feedback Brings Teleoperation Closer to Human Dexterity
Rohan Kota, Gregory Reardon and J. Edward Colgate
A fundamental challenge in robotic teleoperation is enabling an operator to control a remote
robot as effortlessly and intuitively as their own hands. Despite the growing use of teleoperation to collect demonstration data for training autonomous
robot policies, teleoperated
robot performance still falls significantly short of human dexterity, even for basic tasks. Here, we present evidence that a key factor contributing to this performance gap is the absence of spatially distributed tactile feedback. Using a two-degree-of-freedom (DoF) bilateral force-feedback telemanipulator paired with a 32-DoF tactile fingertip display, we show that operator performance improves significantly when localized deformations on the remote manipulator are faithfully reproduced on the operator's fingertip. In a series of teleoperation tasks, reproducing distributed contact information not only accelerated task performance but also brought teleoperated movements closer to natural human behavior by minimizing corrective actions and task completion steps, thereby reducing the deviation between teleoperated and natural trajectories by 29$\unicode{x2013}$79%. Furthermore, we found that increasing the resolution of the tactile feedback$\unicode{x2014}$by refining how finely the measured displacements were quantized for reproduction$\unicode{x2014}$compressed the state-space distribution of teleoperated motions, which has been associated with improved training outcomes for autonomous
robot policies. Together, these results suggest that spatially distributed tactile feedback is essential for closing the gap between human and teleoperated dexterity and training the next generation of autonomous
robots.
Read the full abstract ▾
Information Theory · Cross-listed from quant-ph
Steven Rayan
These notes develop four interconnected ways of reading a
quantum circuit. A
circuit for us begins as an operational composition of gates; then, it becomes a diagram whose local equalities may be used as calculations; next, it becomes a protected process once errors, syndromes, and logical degrees of freedom are separated; and finally, it becomes
geometric when its connectivity,
topology, and boundary data are treated as physical design parameters. The development begins at the level of bits and
qubits before appealing to Deutsch's and Grover's
algorithms as basic examples of
quantum circuits. With the basics in hand, we interpret
quantum circuits diagramatically, leading us to compact closed string diagrams and the ZX-calculus. After that, we consider how to correct
quantum circuits by introducing the Knill–Laflamme condition, homological surface codes, and related concepts with a view towards thinking of these as operations on diagrams. The lectures eventually arrive at the properties of
hyperbolic quantum codes and the prospect of physical superconducting
circuits emulating the negatively-curved
lattices needed to support those codes. These mathematical ideas and physical experiments, taken together, represent one way to impart a
geometric layer onto
quantum circuits. By the very end, we bring the ideas nearly full circle by assessing the extent to which these device physics experiments operationalize the basic ZX diagrams encountered much earlier in the story. While the later material reports on original research, and while the discussion becomes increasingly mathematical as the sections progress, no prior knowledge of
quantum information,
quantum computing, or
quantum error correction is actually assumed.
Read the full abstract ▾
Computation and Language
Linguistic Holonomy and Statistical Watermarks: Inner Geometry of Meaning-Preserving Transformations
Daniele Corradetti
Statistical watermarks for
language models live in the freedom of the signifier: they choose among
tokens that are nearly equivalent in meaning, and they are therefore eroded by exactly those transformations which move the form of a text while leaving its content in place. The literature measures such transformations by their endpoint, through the semantic similarity between the original and the rewritten text. We show that the endpoint is the wrong statistic. Adapting the formalism of linguistic loops, we prove that the invariant of a chain of meaning-preserving transformations factorises canonically into an endpoint part and a holonomy in the stabiliser of the initial state, the second of which the semantic deficit cannot see; the loop rotation is parallel transport on the unit sphere of the
embedding space, so that the analogy with the Wilson loop becomes a
theorem rather than a figure of
speech. On the side of the detector we prove an exact identity: the residual statistic is proportional to the number of positions whose seeding window survived intact, from which the decay law $\rho^{h+1}$ follows as the independent-edit corollary. The identity has a disconcerting consequence, which we confirm to three decimal places: at one and the same retention rate the surviving signal may be one half of the original, one quarter of it, or exactly nothing, according only to where the edits fall.
Read the full abstract ▾
Numerical Analysis
A High-Order Rank-Adaptive Implicit Algorithm for Solving High Dimensional Diffusion Equations using the Hierarchical Tucker Decomposition
Paolo Bosques-Paulet
This paper presents a high-order rank-adaptive implicit integrator for the tensor solution of high-dimensional
diffusion equations. We extend the 3D version of this method from the Tucker decomposition to higher dimensions using the hierarchical Tucker (HT) decomposition, since the storage complexity for the Tucker decomposition increases exponentially with the number of dimensions $d>3$. The HT format avoids this issue by decomposing the solution according to a binary tree consisting of bases for each dimension and core tensors which connect the bases. Spectral methods are considered for spatial discretization, and diagonally implicit Runge-Kutta methods are considered for time discretization. At each stage of the Runge-Kutta method, the bases computed at the previous stages are augmented to predict the upcoming basis and construct projection subspaces. By projecting onto these enriched subspaces, the bases and cores can be updated in a sequential manner going up the tree from leaf-to-root. Unlike the 3D Tucker method which has a single core tensor, the HT method also updates the intermediate core tensors. Numerical experiments demonstrate that the method observes high-order accuracy, and test how well the integrator captures the solution rank for various sets of time-dependent
diffusion coefficients.
Read the full abstract ▾
Computational Engineering
Data-Driven Time-Varying Control Barrier Functions for Adaptive Safe-Set Learning with Online Decremental Support Vector Machines
Shawon Dey, Michael Budihartono and Hever Moncayo
Mission-critical intelligent systems often operate under time-varying limitations that reduce control authority and change the admissible safe operating envelope. In such settings, a safety certificate learned under nominal conditions may become invalid as system capability changes. To address this challenge, this paper proposes a degradation-aware, data-driven safety-filtering framework that learns a safe set from data, updates it online, and enforces the resulting learned barrier through a time-varying control barrier function (CBF). A nominal safe envelope is first learned from operational data using a radial basis function (RBF)-kernel support vector machine (SVM), whose decision function serves as the initial CBF candidate. To capture capability-induced safe-set contraction, a continuous-time decremental SVM update law is developed so that selected support-vector coefficients are reduced according to a degradation signal. A homotopy-smoothed SVM-CBF is then introduced to avoid discontinuous changes in the learned barrier during active-set transitions. The resulting time-varying learned barrier is enforced using a quadratic-program-based safety filter under degraded input constraints. Forward invariance of the learned time-varying safe set and recursive feasibility of the safety filter are established. Simulation results on a vertical takeoff and landing (VTOL) model show that the proposed method maintains safety under reduced control authority and avoids abrupt barrier-switching effects during safe-set contraction.
Read the full abstract ▾
Computation and Language
A Speech Corpus for Mizo Automatic Speech Recognition: Whisper and SraVaani 1.0 Fine-Tuning with Morphology-Aware Evaluation
Priyankoo Sarmah, Sanasam Ranbir Singh and Lalhmingmawia
This study reports the development of an Automatic
Speech Recognition (ASR) system in Mizo, a low-resource
language. The development included collecting 17.62 hours of
speech data, curating it, and fine-tuning the Mizo ASR system with three Whisper
multilingual models and with the SraVaani 1.0 Indic
multilingual model. Whisper-large-v3 achieved the lowest conventional WER (18.08%), while morphology-aware evaluation yielded a WER of 7.22%. Zero-shot evaluation of the SraVaani 1.0 Indic
multilingual model yielded a WER of 58.27%, while Mizo-specific fine-tuning reduced the conventional WER to 29.45% and the morphology-aware WER to 17.93%. The results demonstrate that the Whisper model can achieve a substantially low WER, even when adapted to an unseen
language. In contrast, SraVaani 1.0 supports the Mizo
language in its
multilingual model; however, fine-tuning with carefully curated Mizo
speech data substantially improves its performance.
Read the full abstract ▾
Social and Information Networks · Cross-listed from math.DS
Hodge Coercivity and Global Dynamics in Two-Field Edge-Cochain Systems with MHD-Type Cancellation
Moses Boudourides
A finite-dimensional two-field system for divergence-free edge cochains is introduced. Its MHD-type designation refers only to a quadratic exchange pattern and exact total-energy cancellation; it is not a physical MHD discretization. A general cancellation class is separated from a corrected explicit realization: the anticommutator $D(a)J+JD(a)$ is skew-symmetric for diagonal $D(a)$ and skew-symmetric $J$, and its projected bilinear map has the required trilinear antisymmetry. The central result is a Hodge coercivity criterion: the full divergence-free space admits the Poincaré-type estimate needed for dissipativity if and only if its harmonic $1$-cochain space is trivial. Under this condition, global existence, an exact energy identity, an absorbing ball, and a compact global attractor follow. When harmonic modes are present, a harmonic-decoupled interaction class yields invariant harmonic affine fibres and fibre-wise attractors. Deterministic disk, annular, and two-hole examples illustrate the spectral criterion, energy law, and distinction between general harmonic exchange and harmonic-fibre invariance.
Read the full abstract ▾
Multimedia
GRACE: Grounded Reasoning via Adapter Composition and Evidence-Aware Calibration for Educational Visual Question Answering
Xinjin Li, Yudi Xia, Xi Zhao et al. (+8 more)
Educational visual question answering, or VQA, requires models to solve curriculum-oriented multiple-choice questions using both
language and visual evidence. Compared with conventional open-ended VQA, educational examples often include structured assessment metadata, diagrams or image contexts, and semantically close answer options, creating strong opportunities for question-option shortcuts. We develop and evaluate a parameter-efficient adaptation framework for a frozen
multimodal large
language model in this setting. We introduce GRACE, Grounded
Reasoning via Adapter Composition and Evidence-Aware Calibration, a framework that uses the pedagogical state of each question to specialize lightweight
language and
vision adaptation. The state combines inference-visible subject, grouped skill, grade, visual-context, question-intent, and option-structure cues. GRACE uses factor-specific
prompts and lightweight visual adapters, then applies evidence-aware option calibration to score all candidates under a shared
multimodal context. On ScienceQA, GRACE improves a shared-adapter baseline from 90.5 percent to 93.1 percent overall accuracy and from 88.7 percent to 91.2 percent on image-context questions. Removing pedagogical composition, option calibration, or the visual adapter reduces overall accuracy by 1.4, 1.0, and 1.5 points, respectively. These controlled results show that structured educational state is an effective routing signal for parameter-efficient
multimodal adaptation.
Read the full abstract ▾
All authors Xinjin Li, Yudi Xia, Xi Zhao, Yiliu Xu, Yining Liu, Cheng Lu, Yujian Long, Yu Ma, Jinghan Cao, Liang Fan, Yeyun Xu
Machine Learning
Uncovering the Limits of Proof Sharing for Neural Networks
Kanak Das, Shubham Ugare, Bor-Yuh Evan Chang et al. (+3 more)
Robustness verification of neural networks is increasingly important, due to their use in many critical domains. In certain scenarios, proof sharing has been shown to accelerate incomplete verification techniques by reusing intermediate-layer abstract states, or templates, across queries. However, questions remain as to the robustness of template-based acceleration across varying network architectures, properties,
datasets, and training methods. In this work, we perform a systematic study of the effectiveness of template-based acceleration and its limits. Our study shows that template subsumption rates can vary widely across scenarios. We present a novel metric of jointly stable
neurons to explain this variation, showing that in some cases template-based techniques are very unlikely to provide any speedup. Then, we present FastCert, a novel technique for automatically distributing templates across neural network layers to increase performance impact, eschewing templates entirely if they are unlikely to produce a speedup. Across a large set of covering-design based $L_0$-verification tasks, FastCert achieved an average speedup of 1.13x over an extant template-based reuse technique.
Read the full abstract ▾
All authors Kanak Das, Shubham Ugare, Bor-Yuh Evan Chang, Sasa Misailovic, Gagandeep Singh, Manu Sridharan
Human-Computer Interaction
MultiVerse: A Creator-Centered Approach to Steering Context-Adaptive Lyrics
Alexander Wang, Chris Donahue and David Lindlbauer
Generative AI may enable new forms of context-aware creative expression by dynamically tailoring media content to its consumption context. For instance, AI systems could adapt song lyrics to the listener and their current activity. However, existing media adaptation systems primarily optimize for audience experience, often neglecting artists' intent, style, and preference. We address this challenge by introducing a novel creator-centered approach to adaptive media authoring and present MultiVerse, a system that instantiates this approach for steering adaptive lyrics. Our approach allows creators to explicitly author controls based on their intent, lyric structure, and audience context, and uses rule-based validations to ensure controls are followed. We conducted a study with 10 songwriters, comparing MultiVerse with a prompting-based workflow for composing adaptive lyrics. The comparison revealed that creators preferred to author how lyrics adapt by explicitly specifying relevant context and adaptation constraints, while recognizing trade-offs in flexibility and iteration speed. Interviews further revealed that creators viewed adaptive media as enabling new forms of audience connection, introducing a distinct creative process, favoring new compositional strategies, and reshaping notions of authorship.
Read the full abstract ▾
Software Engineering
Hype Meets Reality: Large Language Models as Mutators in Search-based Automated Program Repair of Simulink-Stateflow Models
Ayesha Irshad, Pablo Valle, Jon Ayerdi et al. (+1 more)
Search-based Automated Program Repair (APR) techniques rely on carefully designed mutation operators to explore the space of candidate fixes. Recent advances in Large
Language Models (LLMs) suggest that generative models could replace such operators by dynamically proposing repairs. In this paper, we investigate this hypothesis in the context of Cyber-Physical Systems (CPSs) modeled in Simulink/Stateflow. We extend the state-of-the-art FlowRepair approach by replacing a subset of its mutation operators with LLM-generated mutations, enabling more flexible and expressive patch generation. We evaluate the approach on a
benchmark of 19 real-world faulty Stateflow models across four CPS domains, using the same experimental setup as FlowRepair for controlled comparison under the same wall-clock budget. Contrary to expectations, in this controlled evaluation, the LLM-based mutation substantially degrades repair performance under the FlowRepair experimental setup. Across the tested LLM variants, the LLM-based repair produced plausible patches for 4-6 models and valid patches for 4 models, compared to 18 and 16, respectively, with the original approach. Our analysis reveals that, in this integration, LLMs struggle with precise symbolic edits, lack behavioral feedback, and generate a noisy search space that hinders effective exploration. Rather than showing a general limitation of LLMs for APR, these findings highlight fundamental limitations of naively integrating LLMs into search-based APR and motivate hybrid approaches that combine structured mutation with generative guidance.
Read the full abstract ▾
All authors Ayesha Irshad, Pablo Valle, Jon Ayerdi, Aitor Arrieta
Machine Learning
Mechanistic Tomography: Designed Measurement for Control-Oriented Interpretability
Vijay Erramilli
Mechanistic interpretability seeks quantities that models do not expose directly: represented states, component effects, interactions, and responses to interventions. Patching, gradients, Hessian-vector products, and subset interventions provide different measurements under different access assumptions and may target different quantities. We formulate their shared measurement structure as mechanistic
tomography: designed measurement for recovering internal mechanisms and intervention effects. For a chosen basis and intervention family, measurements take the form y = Ax + w, where A describes the interventions, x is the target map, and w contains nonlinear response, sampling error, and basis misspecification. This
language gives a practical procedure: start with the least costly measurements, test on held-out interventions at the intended scale, calibrate simple mismatch, and expand the measurement family when structured residuals remain. Control provides a demanding validation setting because an estimate that guides an intervention acts as an observer. In a two-HMM model, control error rises with observer error, while target improvement can hide nuisance-state movement. Under forward-only access, sparse aggregate measurements recover a finite-effect map with fewer interventions than coordinate patching. With gradient access, finite probes improve a local attribution map. Lifted measurements and Hessian-vector products recover interactions missed by first-order maps, while Tracr shows that the required family depends on the basis. On GPT-2-small IOI, the Name Mover-Negative Name Mover interaction is the largest held-out predictive term among three tested cross-group pairs. On Qwen-2.5-7B, finite calibration makes an additive refusal-response map adequate, so held-out error does not support pairwise lifting.
Read the full abstract ▾
Machine Learning · Cross-listed from hep-th
Deep neural networks as lattice gauge theories
Ro Jefferson and Shradha Ramakrishnan
We modify the NN/QFT duality [1] to incorporate the layerwise permutation
symmetry of the network, resulting in a $(0\!+\!1)$-dimensional
lattice gauge theory, in which each layer of $N$
neurons acts as an $N$-component
lattice site, and the weight
matrices play the role of gauge fields living on the links. In this framework, we compute the tree-level
neuron-
neuron propagator which describes the
evolution of layer variance in the network, and develop the Feynman diagram machinery to compute interactions in the perturbative expansion in $1/N$. In particular, we obtain a recursive expression for all corrections to the exact propagator at $O(1)$, representing statistical fluctuations in the ensemble of networks, including infinitely-many loop diagrams mediating the interactions from previous layers. We also present a preliminary analysis of
neuron scattering amplitudes that contribute order-by-order in $1/N$, which provides a field-theoretic framework for studying higher-point correlations, and by extension information propagation, in deep networks. We remark on some interesting directions for future work at the intersection of neural networks and
quantum field theory.
Read the full abstract ▾
Machine Learning
Improved Confidence Estimates for Black-Box Large Language Models
Sokhna Diarra Mbacke, Mouloud Belbahri and Gabriel Loaiza-Ganem
Uncertainty quantification (UQ) is essential for the safe deployment of large
language models (LLMs). Existing methods, from verbalized confidence to ones requiring multiple generations, are often zero-shot and produce scores quantifying uncertainty without the need for labelled data. Nonetheless, in practice one must always evaluate their performance on a
dataset of interest before deployment. In this work we show that, by leveraging this
dataset, we consistently outperform these existing scores. Specifically, we build simple classifiers that predict LLM response correctness by using these scores and the correctness of similar queries as features. Our method produces minimal computational overhead, making it a cheap and straightforward enhancement for UQ in LLMs for real-world applications.
Read the full abstract ▾
Computational Complexity · Cross-listed from quant-ph
Proof of the hiding conjecture for Gaussian boson sampling with an arbitrary number of squeezed input modes
Laura Shou, Alexey V. Gorshkov, Victor Galitski et al. (+1 more)
Gaussian
boson sampling (GBS) is a sampling task proposed to demonstrate
quantum advantage. We consider Gaussian
boson sampling on $M$ optical modes, with $K$ equally squeezed input modes and $N$ observed
photon counts. We complete the proof of the hiding
conjecture for Gaussian
boson sampling with an arbitrary number of squeezers $K$, which is a part of the argument for classical hardness of GBS. In particular, we show that for any $K$ and $N=o(\sqrt{K})$, the symmetric product $MK^{-1/2}U_{NK}U_{NK}^T$, for $U_{NK}$ the top left $N\times K$ submatrix of an $M\times M$ Haar random
unitary $U$, is close in total variation distance to both an $N\times N$ symmetric complex Gaussian
matrix $\mathbf G$ with independent entries, and the symmetric product $GG^T/\sqrt{K}$ for $G$ an $N\times K$
matrix of iid standard complex Gaussians. We show however that the density-based instance generating method of [Aaronson and Arkhipov, Theory Comput. 9, 143 (2013), Lemma 5.8] used to efficiently implement a hiding procedure fails for Gaussian
boson sampling with $K=cM$ if $c<1/2$. Instead we use approximate instance generating to implement the hiding for the usual classical hardness reduction.
Read the full abstract ▾
All authors Laura Shou, Alexey V. Gorshkov, Victor Galitski, Sarah H. Miller
Machine Learning · Cross-listed from quant-ph
Quantum Gaussian processes for prediction of channel observations
Jonas Jäger, Yaroslav Khmelnitskiy, Paolo Braccia et al. (+4 more)
Given a set of input states, we consider the task of predicting the expectation value of a Pauli observable at the output of an unknown
quantum evolution, using only a limited number of measurements. Recently,
quantum Gaussian process (QGP) regression was introduced for this task across various classes of
unitary evolution. Here, we extend the QGP framework beyond
unitary dynamics. In particular, we prove convergence of the channel's outputs to a QGP and derive the associated closed-form kernel under a uniform (Lebesgue measure) prior over
quantum channels. The kernel's dimensional factor, however, dictates the required observation precision. While manageable when the channel and observable are restricted to small subsystems, exponential suppression precludes learning when the subsystem grows extensively with the system size. Since the Lebesgue prior is overly broad for many applications, we propose an empirical Bayes heuristic that replaces the dimensional factor with a learnable scale parameter while retaining the kernel's state-overlap correlation structure. In numerical simulations of up to 64
qubits, channel QGP regression with the Lebesgue kernel exhibits a strong inductive bias for local channels, enabling faithful extrapolation. For global 64-
qubit channels, the rescaled kernel restores learnability, with predictions improving systematically with the shot budget. Results from a noisy
quantum computer further demonstrate the robustness of QGP regression under experimental conditions. Beyond regression, we validate QGPs as
Bayesian-optimization surrogates for state preparation under noisy XXZ dynamics.
Read the full abstract ▾
All authors Jonas Jäger, Yaroslav Khmelnitskiy, Paolo Braccia, Artur Miroszewski, Diego García-Martín, M. Cerezo, Piotr Czarnik
Machine Learning
Quantum Kernel Estimation for the Discovery of Early Lung Cancer Detection
Hamed Javidi, Alex Zajichek, Hakan Doga et al. (+3 more)
Lung cancer screening with low-dose chest computed
tomography reduces mortality, but its impact is limited by uptake, adherence, and management challenges. Blood-based
cell-free DNA (cfDNA) biomarkers offer a complementary approach, although early detection remains difficult because of lung cancer heterogeneity and high-dimensional, nonlinear molecular signals. We evaluated
quantum-classical hybrid machine learning for lung cancer detection using DNA fragmentomics and DNA methylation. After feature selection, models were trained using 20- and 40-feature subsets. Features were encoded into
quantum Hilbert space using angle and dense-angle feature maps with multiple
entanglement strategies. Fidelity-based
quantum kernels were computed with exact statevector simulation and integrated with precomputed-kernel SVM and kernel-PCA logistic regression and compared with an SVM model trained on the original features. This framework enabled systematic evaluation of how encoding and
entanglement design affect classification. Across repeated held-out evaluations,
quantum-kernel models achieved competitive performance on both
datasets. For fragmentomics, several 20-feature configurations improved AUC relative to a classical SVM baseline, suggesting effective capture of nonlinear cfDNA fragmentation structure. For methylation, the classical SVM achieved the highest AUC, although selected
quantum models remained competitive and improved specificity in some cases. Increasing features from 20 to 40 did not consistently improve performance and often increased variability. Overall, these results support
quantum kernel methods as a promising approach for cfDNA-based lung cancer detection.
Read the full abstract ▾
All authors Hamed Javidi, Alex Zajichek, Hakan Doga, Laxmi Parida, Filippo Utro, Peter J. Mazzone
Artificial Intelligence
Outcome Monitors: Recovery Affordances for Silent Tool Failures
Sugam Panthi and Rabab Abdelfattah
When a tool call times out, the
agent sees the failure and can route around it. A cached error page or negative price can instead arrive in the expected format and be consumed as fact. We introduce Outcome Monitors, which detect violations of outcome contracts mined from task-disjoint traces or derived from public schemas. On a violation, the monitor preserves the result and issues a nonbinding receipt naming the violated property and public recovery tools. In frozen, prespecified evaluations with injected failures, Outcome Monitors raise ToolMaze completion from 10.9% to 28.1% across four models in two provider families and replicate in a third. In tau-bench retail, completion improves by 14.0 and 12.0 points on two tiers. In separate ToolMaze controls, removing the recovery-tool list eliminates the measured gain and restoring it recovers the effect; diagnostic detail and timing produce no detectable differences. Gains concentrate where the fault blocks completion. On a suite transcribed from a published incident taxonomy, detection outside the mined vocabulary falls to 46%, though delivery continues and completion is unchanged. Recovery tools are the active receipt content in these controls; extending detection beyond the contract vocabulary remains open.
Read the full abstract ▾
Cryptography and Security
ABEAT: Efficient and Anonymous Encryption for ABE-based Dynamic Group Communication
Hongmiao Yu, Silas Richelson, Jiachen Chen et al. (+1 more)
Confidential communication among a dynamic group of participants that ensures flexible and efficient many-to- many communication is highly desired capability. We leverage attribute-based encryption (ABE) for confidential group communication and enhance it by a graph-based namespace to create an efficient framework that allows groups to be formed and changed dynamically. In this paper, we focus on the important additional need to maintain the anonymity of recipients of a message, when using ABE for group communication for a variety of usage scenarios (e.g., emergency response). We propose ABEAT, an efficient and anonymous dynamic group communication system that also minimizes overhead on receivers who are not the intended recipients of a message. In ABEAT, we propose a new anonymous KP-ABE approach to maintain recipient anonymity. ABEAT hides the clear attribute in the ciphertext of KP-ABE, and also prevents several attacks that seek to break anonymity. ABEAT provides fast recipient verification, dramatically lowering the decryption overhead for non-recipients by more than a factor of 90 versus the current state of the art such as hidden vector encryption (HVE). In fact, it is even 40% less than FABEO, which offers no anonymity.
Read the full abstract ▾
All authors Hongmiao Yu, Silas Richelson, Jiachen Chen, K. K. Ramakrishnan
Hardware Architecture
Performance Verification of the AmpereOne CPU Core
Doa'a Al-Otoom, Nicholas Kelly, Aaron Lindsay et al. (+16 more)
As process technology scaling slows, microarchitectural innovation has become the primary driver of performance gains, making pre-silicon Performance Verification (PV) more critical than ever. This paper presents the industrial-scale PV methodology applied across four generations of the AmpereOne custom CPU core, centered on the cycle-accurate correlation of the RTL design against a trace-driven performance model. The methodology integrates data-driven workload curation, a high-frequency daily regression system, and a unified event-stream framework for analysis. We demonstrate this methodology through case studies of the Branch Prediction Unit and L2 Prefetcher, highlighting a hierarchical strategy that first isolates individual units for focused correlation before proceeding to full-core verification. The results demonstrate that this disciplined, iterative process is indispensable for avoiding costly post-silicon bugs and ensuring complex processors meet their performance targets. We end with a look towards the future of PV in the microprocessor industry.
Read the full abstract ▾
All authors Doa'a Al-Otoom, Nicholas Kelly, Aaron Lindsay, Agreen Ahmadi, Ananth Kumar, Anthony Faubert, Benjamin Chaffin, Bret Toll, Eric Wallace, Lucas Crowthers, Mark Charney, Michael Chin, Michael Spradling, Scott Witscher, Sriyash Caculo, Syed Fakhri, Vivek Kothapalli, William Freelove, Mahesh Madhav
Artificial Intelligence
Air Traffic Control Using Large Language Models: Prompt Engineering, Architecture, and Evaluation
Mahyar Ghazanfari, Matthias Casanova, Jordan Kam et al. (+4 more)
Air traffic control (ATC) communication is a safety-critical dialogue that remains largely human-driven even as other parts of air traffic management have been semi-automated. In this article, we experimentally evaluate whether large
language models (LLMs) can generate operationally realistic ATC transmissions. An experimental general-aviation flight flying over the San Francisco "Bay Tour" route is hand-transcribed and used as ground truth (P0). Through a pilot-in-the-loop process we design five
prompt structures (P1-P5) of increasing constraint and embed them in a stateful multi-turn pipeline, where the model plays ATC to a fixed pilot transcript while conditioning on the accumulating dialogue history. Across nine open- and closed-source LLMs we vary the
prompt, the presence of a worked transcript from a different experimental flight as an in-context example, and whether the model conditions on its own prior replies or on injected ground-truth history. Turns are scored with lexical, structural, and semantic similarity metrics and by an LLM-as-judge (GPT-5.5) validated against human expert annotation. Supplying a worked example improves similarity, but tightening the
prompt does not: the lightest
prompts perform best and the most heavily scripted one collapses as its own errors accumulate through the dialogue, which injecting correct history repairs. These results outline a concrete path and its current limits toward LLM-assisted ATC.
Read the full abstract ▾
All authors Mahyar Ghazanfari, Matthias Casanova, Jordan Kam, Alex Zongo, Peng Wei, Torsten Darrell, Alexandre Bayen
Computer Vision
SceneGTMM: A Conformal Mapping-based Scene-Aware Transferable GNN-Transformer Dual-Graph Interaction Framework for Map Matching
Yongliang Zhang, Feng Song, Ji Chen et al. (+6 more)
Map matching is a key technology connecting positioning data with high precision road networks, but it faces challenges in noise robustness, cross regional transfer, and interpretability. To addr ess the limitations of existing methods in local global fusion, dynamic road network adaptation, and reliance on black box mod els, this paper proposes SceneGTMM, a transferable GNN
Transformer dual graph interaction map matching framework based on a conformal mapping based scene relative strategy. 1) Conformal mapping based scene relative strategy: constructs trajectory centric local coordinate systems to reduce dependence on the training road network, supporting cross regional transfer and dynamic road network updates; 2) GNN
Transformer dual graph interaction architecture: a GNN modeled road graph captures local topological constraints, while a
Transformer modeled trajectory graph captures global temporal dependencies, and cross graph
attention achieves noise suppression and semantic
alignment; 3) CRF enhanced structured prediction: combines the global context of the
Transformer with the topological transition constraints of CRF to improve path connectivity and robustness. Experiments show that SceneGTM achieves over 80% accuracy on multi source trajectories with positioning errors of 16 50 meters, representing a 5.3% improvement over HMM. In cross city transfer scenarios, it outperforms MTrajRec, GraphMM, and TMM, and enhances interpretability through
attention and relative coordinate visualization. This study provides a new paradigm for high precision, transferable map matching for real time traffic perception and autonomous driving path planning.
Read the full abstract ▾
All authors Yongliang Zhang, Feng Song, Ji Chen, Lishuai Guo, Yong Deng, Yue Zheng, Tianyi Liu, Zhixiong Chen, Qixin Zhang