Machine Learning
Learning from VAE Errors to support ECG-based Differential Diagnosis of Myocardial Scar
Shayan Sharifi, Riccardo Treu, Ilaria Gandin et al. (+3 more)
Late Gadolinium Enhancement (LGE) on cardiac
magnetic resonance is a key marker of myocardial scar, but its limited accessibility motivates routine ECG-based screening. We evaluated whether $\beta$-variational autoencoder (VAE)-derived ECG representations can discriminate LGE+ from LGE- cardiomyopathic patients in a local cohort of 300 subjects. We compared 32-dimensional features from the foundation ECGx.AI model with those from a shallower $\beta$-VAE trained on normal PTB-XL ECGs, evaluating downstream classification and Dynamic Time Warping (DTW)-based reconstruction errors. ECGx.AI reached an area under ROC of 0.686 with Random Forest, while the proposed $\beta$-VAE reached 0.577 with sensitivity of 0.775 with Gradient Boosting. Notably, DTW-reconstruction errors significantly differed between classes in 10 out of 12 leads according to Mann-Whitney U test and help in classification, leading to an area under ROC of 0.643 with Logistic Regression, supporting their potential as markers of scar-related ECG alterations.
Read the full abstract ▾
All authors Shayan Sharifi, Riccardo Treu, Ilaria Gandin, Federico Garoia, Marco Merlo, Giulia Cisotto
Information Theory · Cross-listed from math.CO
On the lengths of MDS codes with a two-transitive permutation automorphism group
Haihua Deng, Tao Feng and Andrey V. Vasil'ev
Let $C$ be an $[n,k]_q$ maximum distance separable (MDS) code with $4\le k\le q-3$, and suppose that it has a $2$-transitive permutation
automorphism group. In this paper we show that $n\le q+1$, so the MDS
conjecture holds for this class of codes.
Artificial Intelligence
Beyond Aggregate Scores: Behavioral Correctness Assumptions for Assessing Reference-Based Automatic Evaluation Methods
Maria Mahbub, Ashley Rice, Michael R. Munroe et al. (+2 more)
Automated reference-based evaluation methods play a critical role in assessing natural
language generation systems. Existing meta-evaluation primarily measures agreement with human judgments or
benchmark labels, providing limited insight into evaluator behavior under controlled conditions. We introduce behavioral correctness assumptions, a complementary framework for evaluating reference-based automatic evaluation methods. We define a taxonomy of correctness-preserving and correctness-altering assumptions and operationalize them through controlled response transformations that specify expected scoring behaviors. We evaluate diverse lexical, character-level, semantic, LLM-based, and hybrid evaluators and analyze their assumption-level behavior, stability, sensitivity, repeat-run variability, configuration sensitivity, and reproducibility. Our experiments reveal distinct behavioral trade-offs across evaluation paradigms: no evaluator satisfies all proposed correctness assumptions, and evaluators with similar aggregate performance can exhibit substantially different behavioral profiles. These findings demonstrate that behavioral correctness assumptions provide diagnostic information obscured by conventional aggregate meta-evaluation.
Read the full abstract ▾
All authors Maria Mahbub, Ashley Rice, Michael R. Munroe, Amidu Kamara, Amir Sadovnik
Programming Languages
Augur: Predicting View Serializability Violations in Relational Data Store Applications
Chujun Geng, Noah Charlton, Spyros Blanas et al. (+2 more)
Data stores are widely used because they provide persistence, scalability, and fault tolerance with a simple interface. However, most data store applications configure the data store to use weak isolation to achieve scalable performance, resulting in sporadic unserializable executions that are incorrect or fail. Prior work uses dynamic predictive analysis to infer violations from execution traces, but it cannot handle relational (i.e., SQL) queries with complex predicates, and it predicts executions that do not violate View Serializability. This paper introduces Augur, the first dynamic predictive program analysis that (1) supports data store applications with complex relational queries and (2) reports only executions that violate View Serializability. The evaluation demonstrates that Augur finds feasible, unserializable executions in the widely used OLTP-Bench programs and in the widely used e-commerce application Spree.
Read the full abstract ▾
All authors Chujun Geng, Noah Charlton, Spyros Blanas, Michael D. Bond, Yang Wang
Artificial Intelligence
GUT: Quantifying and Optimizing the Reasoning Uncertainty of LLMs via Graph Complexity
Shuang Liang, Xin-Yu Hu, Xiang-Jun Ou et al. (+1 more)
Recent years have witnessed great advances in the
reasoning ability of Large
Language Models (LLMs). However, the
reasoning processes of LLMs often exhibit uncertainty, where LLMs often produce a proliferation of divergent branches at each
reasoning step even when fed the same prompting inputs, and certain branches exhibit evidently incredible, even nonsensical,
reasoning chains and results. In this paper, we propose the Graph-complexity-based UncerTainty (GUT) method for investigating the
reasoning uncertainty of LLMs. The key idea of GUT is to characterize the potential branches of each
reasoning chain with a directed acyclic graph, thereby ensuring that all potential branches are comprehensively covered within the graph space. Building upon this recognition, we further build two modules of GUT, that is, a Quantification (GUT-Q) module and an Optimization (GUT-O) module, for quantifying and reducing the
reasoning uncertainty of LLMs, respectively. GUT-Q measures LLM
reasoning uncertainty by approximating the
reasoning space complexity with graph complexity. GUT-O implements uncertainty optimization by treating negative uncertainty as the reward function in reinforcement learning. Experimental results conducted on four LLMs and five
datasets validate the effectiveness of GUT.
Read the full abstract ▾
All authors Shuang Liang, Xin-Yu Hu, Xiang-Jun Ou, Shao-Qun Zhang
Robotics
Temporal Tactile Encoding and Compliance for Intent-Aware Robot-to-Human Bimanual Handover
Pasquale Marra, Stefano Berti, Gabriele Mario Caddeo et al. (+1 more)
Reliable
robot-to-human handover requires the
robot to infer when the person is ready to receive the object and release it safely, comfortably, and at the right time. This is challenging because visual observations alone may not disambiguate clear taking intent from accidental contact, weak grasping, wrong-direction forces, or transient interactions. In this work we treat human-
robot handover as an intrinsically
multimodal problem. Our approach couples a VLA model with a compliance controller that reduces interaction forces during object transfer. We finetune the VLA model with human demonstrations using RGB observation, temporally encoded tactile feedback and proprioception. We evaluate the complete system in a human-subject study against two baselines: one without tactile feedback and one using tactile feedback without compliance control. We hypothesize that combining compliance and temporal tactile encoding yields the most reliable and comfortable handovers, as compliance facilitates physical interaction while tactile history captures sustained taking intent. Performance is measured through objective metrics and an ad-hoc questionnaire. The results show that the two components provide complementary benefits and substantially outperform the baselines. Project page: https://hsp-iit.github.io/temporal-tactile-bimanual-handover/.
Read the full abstract ▾
All authors Pasquale Marra, Stefano Berti, Gabriele Mario Caddeo, Lorenzo Natale
Sound
KanAdapter: A Kolmogorov-Arnold Network-based Plug-and-Play Module for Efficient Fine-tuning of Foundation Speech Models
Phuong Tuan Dat, Phuong Khai Minh and Tran Huy Dat
Fully fine-tuning self-supervised learning (SSL)
speech models for downstream tasks is computationally prohibitive, and existing parameter-efficient fine-tuning approaches predominantly rely on MLP-based adapters whose fixed activation functions limit their representational expressiveness under tight parameter budgets. We propose KanAdapter, a lightweight adapter framework that replaces conventional MLP bottlenecks with Group-Rational Kolmogorov-Arnold Network (GR-KAN) modules for more expressive and parameter-efficient adaptation. Following a parallel bottleneck design, KanAdapter inserts trainable GR-KAN branches alongside frozen
Transformer encoder blocks and leverages weight transfer from pre-trained MLP layers for stable initialization. Across speaker verification,
speech emotion recognition, and deepfake detection, KanAdapter achieves up to 97.5% reduction in trainable parameters relative to full fine-tuning while remaining highly competitive, and consistently outperforms AdaptFormer under comparable parameter budgets. In continual learning, it yields up to 83.6% error reduction over full fine-tuning and MLP-based adapters, which we attribute to the localized nature of GR-KAN's rational activations that mitigates catastrophic forgetting. To our knowledge, this is the first work to explore KAN-based modules for parameter-efficient fine-tuning of
speech foundation models.
Read the full abstract ▾
Artificial Intelligence
Interchangeable in Role, Not in History: Replacing Members of Formed LLM Teams
Jianxin Gao, Runze Li, Tianyi Yu et al. (+3 more)
Multiagent LLM systems often treat a role as a slot: when a member is replaced, any
agent competent at the role is expected to fill it. We test this view on teams whose members keep short written notebooks. A one-seat swap replays a formed, frozen team with its own member, with a same-role newcomer carrying another team's notebook for that role, or with a newcomer carrying none. In cooperative cooking, wildfire response and medical question answering, the experienced newcomer, averaged over seats, outscores the one without a notebook in every setting, so the usual comparison would approve it. Against the original team, the same replacement falls short in every setting, and the team spends more messages per unit of progress. On the hardest cooking level, the shortfall appears only after the team has worked together, persists across model families and decoding temperatures, and narrows by two thirds with added planning-only members. Because the team's history is written down, we can take it apart. In the default configuration on that level, notebooks from the same donor teams leave a newcomer that leads, holding the recipe, worse off than no notebook and one that follows better off. The notebook lines about the partner reproduce this whole difference between the seats. Whether an
agent can replace a teammate depends on the seat and the team it enters.
Read the full abstract ▾
All authors Jianxin Gao, Runze Li, Tianyi Yu, Liangwei Ren, Bohan Chen, Zining Wang
Software Engineering
Ritgard: T(r)opical Islands of Socio-Technical Artifacts on GitHub
Adam Štěpánek, Marco Raglianti, Jan Byška et al. (+2 more)
A software project is more than just code. Non-code artifacts often document the human processes and decisions behind source code. The rationale behind a library change, an architectural decision, a problem encountered by a user are all examples of information typically present in socio-technical artifacts (STAs), created and persisted in channels separate from the repository itself (yet sometimes very close—e.g., GitHub Issues with GitHub repositories). These STAs are a trove of information about the project's architecture and its
evolution, containing details and insights that code alone cannot provide. Unfortunately, this information is not easily extracted and explored as STAs are frequently fragmented over different communication channels, and are written in natural
language. We present Ritgard, a tool that mines GitHub repositories for their STAs, namely Issues, Pull Requests, and Discussions, and visualizes them as 3D islands covered with trees. Each tree represents a single artifact and each island is a topic extracted from the artifacts through a combination of text
embedding and text summarization. The terrain of the islands rises out of the ocean as the topic becomes active and sinks back in when it becomes stale, thus depicting the
evolution of features and concerns throughout the project's lifetime. We describe the tool's usage and implementation, showing the numerous technical challenges behind Ritgard's visualization.
Read the full abstract ▾
All authors Adam Štěpánek, Marco Raglianti, Jan Byška, Barbora Kozlíková, Michele Lanza
Artificial Intelligence
Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and Inference
Mostafa Elhoushi, Alex Pretko, Nolan Dey et al. (+6 more)
Layer dropout (a.k.a.
stochastic depth) has been shown to enable faster training, higher accuracy, and robustness to zero-shot layer
pruning in both
language and
vision transformers. However, as models and
datasets have scaled, dropout - particularly layer dropout - has largely disappeared from large
language models (LLMs) pre-training recipes. While some prior work has reported that dropout can degrade accuracy, no comprehensive study has quantified, let alone mitigated, this effect. In this study, we show that layer dropout should be used in state-of-the-art LLM training, establishing best practices and scaling analysis for both training and post-training benefits. Concretely, with optimal layer distribution, time schedule, and optimizer hyperparameters, we observe that at the same training FLOPs layer dropout leads to lower loss. For a given number of training steps, LLMs can achieve lower or similar validation loss while saving upto 25% of training FLOPs. Moreover, layer dropout enables significant post-training optimizations, such as early exit, intermediate-layer skipping, and self-speculative decoding, yielding up to 1.5x inference speedup with negligible accuracy loss. Across more than 2400 training experiments, spanning models from 271M to 8.2B parameters and
datasets up to 160B
tokens, we demonstrate that these findings extend reliably to large-scale training regimes. All pre-training experiments were run on Cerebras CS-3 systems.
Read the full abstract ▾
All authors Mostafa Elhoushi, Alex Pretko, Nolan Dey, Bin Claire Zhang, Gavia Gray, Gurpreet Gosal, Abdulrahman Mahmoud, Shane Bergsma, Joel Hestness
Machine Learning
How to Speculate about Uncertainty in Agentic Coding? A Draft-Model Gate Method
Konstantin Grotov and Valentin Malykh
LLM
agents deployed for software engineering fail expensively: they act confidently wrong, and bad actions are recognized only after costly execution and retry. We present Speculative Uncertainty (SU), a method that recovers a predictive failure signal for a black-box
agent from its output
tokens alone, with no access to logits, weights, activations, or repeated sampling. Inverting speculative decoding, a small open-weight draft model scores the
agent's already-generated trajectory in a single forward pass. From these speculative cross-likelihoods we extract phase-aware features by separating the
reasoning and action spans, and calibrate them against a verifiable objective. SU produces a failure-likelihood score that any downstream policy, such as routing, human intervention, or extra test-time compute, can consume directly. To show the signal is actionable, we instantiate one such policy, a pre-execution veto gate, on software engineering
agents Qwen3-Coder-480B and closed-source Claude 3.5 Sonnet, cutting execution error rate by 6-8 percentage points and
token cost by 14-19% in deployment, transferring to out-of-distribution
benchmarks without retraining, and generalizing across
agent models.
Read the full abstract ▾
Artificial Intelligence
AI for Computational Design Science: A Responsible Human-AI Framework and Case Study on Short-Form Video Safety Surveillance
Wenli Zhang, Jiaheng Xie, Zhihe Pan et al. (+3 more)
Artificial intelligence (AI) is transforming not only what information systems researchers design, but also how design research is conducted. Yet existing literature offers limited guidance for computational design science (CDS) when AI actively participates in problem formulation, resource construction, design search, evaluation, and knowledge abstraction. We develop AI for Computational Design Science (AI4CDS), a five-phase methodological framework in which AI expands problem and design search while researchers retain responsibility for domain grounding, admissibility, verification, and scientific judgment. Collaboration is governed by graduated trust, reversibility, auditability, and differentiated reproducibility. We instantiate AI4CDS through ChildRiskGuard, an interpretable artifact for detecting short-form
videos inappropriate for children, while documenting AI interactions, rejected alternatives, corrections, and audit trails. The case translates audience-dependent safety and explanation faithfulness into three technical challenges and develops an artifact that separates generic from child-specific risk, represents distinct developmental-risk mechanisms, and makes concept-level explanations part of the predictive computation. ChildRiskGuard achieves an F1 score of 0.769, substantially outperforming direct application of a general-purpose content-safety model while remaining competitive with strong
benchmarks. The primary contribution is AI4CDS as a responsible framework for AI-enabled CDS; ChildRiskGuard provides process and artifact evidence of how AI-expanded, researcher-governed design can generate and evaluate novel computational design knowledge.
Read the full abstract ▾
All authors Wenli Zhang, Jiaheng Xie, Zhihe Pan, Yidong Chai, Xiao Fang, Sudha Ram
Cryptography and Security
CONTINUITY: Security-Context Contracts for Composable LLM Agent Controls
Chris Zheng and Geng Yang
LLM
agent systems increasingly combine provenance tracking, authorization, policy enforcement, protocol adapters, and execution controls. However, individually correct security mechanisms do not necessarily compose into an end-to-end secure system: security-critical context may be dropped, widened, rebound, or reinterpreted as actions cross component boundaries. We identify this failure mode as security-context discontinuity and introduce CONTINUITY, a framework for verifiable composition of
agent security controls. CONTINUITY models each component with an assume-guarantee contract and carries authenticated security context across transitions using signed root grants, provenance commitments, role-bound transition receipts, bounded typed releases, transformation witnesses, and effect-bound execution permits. We formalize end-to-end consequence integrity, requiring every realized external effect to be backed by a valid and current authorization witness linking the principal, task, provenance, delegation, policy state, canonical action, and finality boundary. We implement a reference verifier and deterministic cross-layer fault-injection suite covering 32 fault classes across four application domains. In 2,560 parameterized attack instances spanning 128 fault-domain classes, the full CONTINUITY configuration commits no harmful external effect, while completing all 700 benign tasks and escalating all 200 ambiguous cases. These results show that secure
agent execution requires not only sound individual controls, but explicit contracts that preserve their guarantees across the complete instruction-to-effect path.
Read the full abstract ▾
Robotics
TacPAC: Tactile Prediction and Real-Time Action Correction in World-Action Models for Contact-Rich Manipulation
Zipei Ma, Xiaofei Wei, Junzhe Jiang et al. (+2 more)
World-action models guide action generation with predicted future observations, but
vision-centric predictions miss the local contact cues that decide contact-rich manipulation. However, naively predicting future tactile observations as additional views recovers only a third of the achievable gain in our experiments. This gap reflects a timing mismatch: predictions precede execution, while tactile feedback arrives during it. We introduce TacPAC, which turns tactile prediction into real-time action correction. Once the base model has planned an action chunk, TacPAC caches the predicted contact that plan was conditioned on together with the plan's own representation, and a tactile expert reads each newly observed tactile image against that cache to correct the actions not yet executed. Feedback is thus interpreted against what the plan anticipated rather than in isolation, and one correction is a single pass over that cache, $20.7\times$ cheaper than regenerating the chunk. On five real-
robot tasks spanning precision insertion, fragile-object handling, object reorientation, and long-horizon manipulation, TacPAC leads every task and raises the average from 22% for its
vision-only base model to 64%. Code is available at https://github.com/LogosRoboticsGroup/TacPAC.
Read the full abstract ▾
All authors Zipei Ma, Xiaofei Wei, Junzhe Jiang, Shunlin Lu, Li Zhang
Numerical Analysis
Shallow neural network approximation in mixed Sobolev spaces
Yuwen Li and Guozhi Zhang
We investigate the best $L_2$ approximation of mixed Sobolev spaces by shallow neural networks with $n$
neurons and general activation functions. We first establish an activation-independent
Fourier-block principle: if an activation has univariate approximation order $\rho$ in the sense of the
Fourier-block property, then the global approximation rate has algebraic order $\min\{\alpha,\rho\}$ for target functions of mixed smoothness $\alpha$, up to explicit logarithmic factors. To verify this property for concrete activations, we introduce a structured univariate approximation condition that implies the
Fourier-block property with explicit parameters. For $\mathrm{ReLU}^k$, a matching algebraic lower bound identifies $\min\{\alpha,k+1\}$ as the optimal algebraic approximation exponent in any dimension, up to logarithmic factors in the upper bound. The framework also yields the exponent $\min\{\alpha,k+1\}$ for cardinal B-splines and soft-$\mathrm{ReLU}^k$, and the full mixed-smoothness exponent $\alpha$ for ELU and cosine activations, again up to logarithmic~factors.
Read the full abstract ▾
Computation and Language
Self-Supervised Lexical Representation Learning for Fast, Large-Scale Phylogenetic Inference
Tim Wientzek
Computational phylogenetics has become an essential tool in historical linguistics, yet its application at a global scale remains constrained by two factors: the labor-intensive manual annotation of cognacy judgments required for character-based methods and the substantial computational cost of inference on large
datasets. This paper introduces a fully self-supervised contrastive learning framework that learns lexical representations directly from raw IPA-transcribed wordlists, without requiring cognacy annotations,
alignments, or additional expert input. The model employs a dual contrastive objective: a word-level loss that organizes phonetically similar forms into a coherent space, and an auxiliary
language-level loss that encourages the lexical space to reflect broader phonological properties of
languages. From the resulting word representations, pairwise
language distances are derived and used to infer a global phylogenetic tree of 3,399
language varieties. The inferred tree achieves a generalized quartet distance (GQD) to the Glottolog reference tree competitive with multiple baselines, while requiring only minutes of computation on a standard notebook GPU. Furthermore, the same representations capture diachronic concept stability: variance in pairwise distances across
languages yields stability rankings that correlate significantly with established rankings. Ablation studies confirm that both the
language-level objective and the use of phonetic feature vectors improved the inferred trees
topology with regards to GQD. The framework thus provides a computationally efficient and fully automatic alternative for large-scale phylogenetic inference and offers a unified representation supporting downstream analyses at both the
language and concept level.
Read the full abstract ▾
Artificial Intelligence
Trace2Tower: Transition-Aware EigenTrace Induction of Multi-Level Skills for LLM Agents
Jiazheng Sun, Boyu Yang, Binhao Yuan et al. (+2 more)
Large
language model
agents increasingly rely on execution traces to master complex interactive tasks. However, current paradigms are bottlenecked by shallow trajectory
retrieval and flat skill summarization, fundamentally ignoring the temporal dependencies and outcome-conditioned
topology of
agent behavior. We introduce Trace2Tower, a transition-aware EigenTrace framework that distills raw trajectories into a robust skill hierarchy. Trace2Tower abstracts step-level interactions into canonical events, constructing a unified graph governed by semantic compatibility, transition dynamics, and outcome evidence. Through a novel contrastive spectral decomposition, it isolates stable, success-aligned behavioral modes while rigorously suppressing failure-prone shortcuts. These modes organically populate a dynamic skill tower of action templates, procedural routines, and overarching task strategies, continuously refined via verifier-guided feedback. On ALFWorld, Trace2Tower achieves 87.31% success requiring only 10.35 steps and 0.26 invalid actions; on WebShop, it reaches 50.67% exact success. Across both
benchmarks, Trace2Tower significantly outperforms existing baselines in task mastery and context-efficient experience reuse.
Read the full abstract ▾
All authors Jiazheng Sun, Boyu Yang, Binhao Yuan, Mingxuan Li, Xin Peng
Robotics
Yiwei Liu, Luwei Yang and Shunbo Lei
Changes in natural-
language instructions can directly alter the behavior ultimately executed by a
robot, but such changes do not always imply that the task itself has changed. We propose One Word, Different Action, a
language-conditioned executable decision
benchmark based on real-
robot physical decision anchors. It evaluates
robot behavioral responses under task-preserving and task-changing conditions and examines joint
reasoning over multiple task constraints. The
benchmark uses decision invariance and decision sensitivity to measure action stability when task semantics are preserved and correct decision updates when task requirements change. Matched atomic constituents directly relate correct handling of individual constraints to the corresponding joint executable decision. Experiments show that atomic-task correctness does not sufficiently represent compositional
reasoning ability: even when every constituent constraint is handled correctly, a model may still produce an erroneous final action decision on the corresponding compositional task. These results indicate that the key challenge in
language-conditioned
robot reasoning lies not only in understanding individual task requirements, but also in integrating multiple correctly handled constraints into consistent executable behavior.
Read the full abstract ▾
Discrete Mathematics · Cross-listed from math.CO
Order 14 is the largest order for which every 4-total coloring of every cubic graph is equitable
Matheus Adauto, Celina de Figueiredo, Diana Sasaki et al. (+1 more)
A total coloring of a graph is an assignment of colors to its vertices and edges so that adjacent or incident elements receive distinct colors, and it is equitable when the cardinalities of any two color classes differ by at most one. Stemock conjectured that every $4$-total coloring of a cubic graph of order less than $20$ is equitable. In this paper, we disprove this
conjecture: the circular ladder $L_{12}$ admits a non-equitable $4$-total coloring and, moreover, no smaller counterexample exists: order $4$ is vacuous, and every $4$-total coloring of a cubic graph of order $6$, $8$, or $10$ is equitable. We also prove that the same property holds at order $14$. Our proofs rely on a decomposition lemma, which states that, in any $4$-total coloring of a cubic graph $G$, each color class consists of an independent set $S$ together with a perfect matching of $G-S$. We use the lemma to determine all possible color class configurations for orders $12$, $16$, and $18$, and we show that every listed configuration is attained. Finally, we provide a splicing construction showing that, for every even $n\geq16$, some connected cubic graph of order $n$ admits a non-equitable $4$-total coloring. We may conclude that $14$ is the largest order for which every $4$-total coloring of every cubic graph is equitable.
Read the full abstract ▾
All authors Matheus Adauto, Celina de Figueiredo, Diana Sasaki, Rafael Schneider
Artificial Intelligence · Cross-listed from math.OC
Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization
Sihan Ge, Yichen Lin, Chenyu Zhou et al. (+3 more)
Large
language models (LLMs) are increasingly used to formulate optimization models from natural-
language problem descriptions, yet realistic operations research (OR) requests are often incomplete: missing objectives, constraints, or business rules can change the resulting mathematical program. Existing evaluations largely assume a complete specification and therefore overlook whether an
agent knows when clarification is needed before modeling. We introduce OR-Clarify, a
benchmark for pre-formulation clarification. Each task presents a partial public problem description, withholds structured hidden slots, and evaluates
agents through bounded interaction with a simulated user. The
benchmark supports both openended and choice-based clarification, and measures slot recovery, stopping behavior, silent assumptions, and interaction cost. We further propose Interactive Optimization (InterOPT), a two-stage framework that identifies unresolved formulation-critical gaps and uses them to guide whether to ask the next question or to stop. In our choice-based experiments, InterOPT substantially outperforms all baselines in exact slot recovery; in the open-ended setting, it remains competitive with strong prior methods. Together, OR-Clarify and InterOPT reframe OR assistance as a selective completeness decision: clarify when needed, stop when ready, and quantify what remains missing.
Read the full abstract ▾
All authors Sihan Ge, Yichen Lin, Chenyu Zhou, Jianghao Lin, Tao Yao, Dongdong Ge
Artificial Intelligence
Commonsense Reasoning in Computer Vision: Foundations, Recent Advancements, and Future Directions
Bahar Uddin Mahmud, Sumit Barua, Guan Yue Hong et al. (+2 more)
Commonsense
reasoning in computer
vision encompasses integrating visual data and contextual knowledge, crucial for enhancing AI's understanding of everyday scenarios. This understanding not only improves machine learning models but also enhances their ability to interact meaningfully with humans and the environment. Unlike CNN-based conventional
vision models, which are designed to identify objects within a specific image, incorporating commonsense knowledge enables models to interpret scenes in a more holistic manner, thereby improving their spatial ability to reason about relationships among objects and actions. This integration not only enhances object recognition but also facilitates a deeper understanding of the contextual factors, ultimately leading to more precise predictions and interactions in real-world applications. This paper presents a comprehensive survey of recent developments that integrate commonsense knowledge into computer
vision tasks. We systematically review approaches based on knowledge graphs, scene graphs, neuro-symbolic models, and commonsense-augmented
transformers. We also outline current limitations related to
dataset bias, knowledge incompleteness, and integration challenges. Finally, we highlight prospective research trajectories in cross-modal
reasoning, scalable commonsense knowledge injection, and neuro-symbolic hybrid architectures to develop truly intelligent visual systems.
Read the full abstract ▾
All authors Bahar Uddin Mahmud, Sumit Barua, Guan Yue Hong, Ajay Gupta, Hexu Liu
Computer Vision
Compact Neural Appearance Models for Efficient Gaussian Splatting
Florian Hahlbohm, Jorge Condor, Linus Franke et al. (+2 more)
Explicit primitive-based radiance fields such as 3D Gaussian Splatting typically model view-dependent appearance using low-order spherical harmonics (SH). Although efficient to evaluate, SH coefficients dominate per-primitive storage and
memory traffic, while their band-limited basis restricts angular detail. We present a thorough, end-to-end comparison of SH and recent spherical appearance models and introduce an implicit alternative that decodes compact per-primitive latent codes using a tiny shared MLP. We integrate all models into the same optimized pipeline, fusing their forward and backward passes into a differentiable CUDA rasterizer and provide a portable WebGL viewer for laptop and mobile GPUs. Our evaluation across reconstruction quality,
memory use, and optimization and rendering performance shows that recent spherical models offer the strongest overall quality-efficiency trade-off. Our neural representation is the most compact model evaluated and, compared to third-degree SH, reduces the per-primitive appearance footprint from 192 to 28 bytes, accelerates optimization by 1.3$\times$, while improving reconstruction quality. We further analyze how appearance parametrization shapes optimization, identifying differences in recovered geometry and the tendency of expressive models to absorb non-static scene content. Together, our framework and analysis provide practical guidance for replacing SH beyond what image metrics alone can capture.
Read the full abstract ▾
All authors Florian Hahlbohm, Jorge Condor, Linus Franke, Martin Eisemann, Marcus Magnor
Software Engineering
T(r)opical Islands: Visualizing & Understanding Socio-Technical Artifacts
Adam Štěpánek, Marco Raglianti, Vít Rusňák et al. (+3 more)
Projects hosted on collaborative software development platforms, such as GitHub, include many non-code artifacts documenting the project's lifecycle, with its challenges, plans, design, and even community. These socio-technical artifacts include, for example, bug reports, feature requests, and forum posts, offering a useful prospect on the project's
evolution. However, these artifacts are dispersed over multiple communication channels and written in natural
language, making their analysis difficult, as they are fragmented and with considerable noise. We present a 3D visualization approach mapping topics found across a project's socio-technical artifacts onto vegetation-covered islands, where the individual artifacts are depicted as trees of various types. The topic islands rise out of the ocean as they become discussed, to sink again when they are no longer so. We built a prototype implementing the entire visualization pipeline, from data mining to interactive rendering, leveraging machine learning techniques to cluster the artifacts and extract their topics. We present, through several case studies, the insights that our approach elicits about discussions of development topics throughout a project's history. The user study we conducted (N=34) further strengthens our conclusions about its suitability for understanding socio-technical artifacts and their
evolution.
Read the full abstract ▾
All authors Adam Štěpánek, Marco Raglianti, Vít Rusňák, Jan Byška, Barbora Kozlíková, Michele Lanza
Machine Learning
GLASS: Graph-Language Alignment with Spherical Scoring for Transferable Graph-Level Anomaly Detection
Xudong Wang, Chris Ding, Tongxin Li et al. (+1 more)
We introduce GLASS, a framework for graph-level anomaly detection (GLAD) that achieves robust cross-domain transferability through graph-
language alignment on the unit hypersphere. GLASS builds a unified representation space by aligning a structure-aware graph encoder with an instruction-aware text
embedding via a multi-slice soft cosine objective. Our framework serializes local, global, and semantic graph properties into a compact Graph Descriptor
Prompt (GraphDP), creating a text bridge that enables domain-agnostic anomaly scoring. By enforcing multi-scale consistency through Matryoshka representation slices, the model captures anomalous deviations at multiple levels of granularity. We formulate anomaly detection as density estimation on the aligned hypersphere and introduce Spherical Multi-Modal Scoring (SMS), which instantiates von Mises-Fisher kernel density
estimators in both graph and text
embedding spaces. This probabilistic formulation recovers angular 1-nearest-neighbor scoring in the high-concentration limit, motivates the practical mean k-nearest-neighbor scorer, and provides a principled fusion of structural and semantic anomaly signals. The shared text
embedding space further serves as a cross-domain bridge: by encoding a target domain's GraphDP without target-domain training data, GLASS performs zero-shot anomaly detection, and with only a handful of normal examples, few-shot adaptation via reference-set calibration. For
privacy-sensitive deployment, we extend reference-set calibration with a bounded joint graph-text kernel summary that provides graph-record differential
privacy while keeping the encoders fixed independently of the private target references. Across twelve
benchmarks and three meta-domains, GLASS obtains the best average AUROC and rank compared with recent advanced GLAD baselines and enables effective cross-domain transfer.
Read the full abstract ▾
All authors Xudong Wang, Chris Ding, Tongxin Li, Jicong Fan
Artificial Intelligence
A Unified Physics-Aware Quantum Machine Learning Framework across Power GaN HEMTs and Logic Nanowire FETs: Predicting Unseen Process Splits and Held-Out Geometry Combinations with Lower Error and Tighter Split-to-Split Variability
Rushat Rai, Yun-Yuan Wang, Autsada Kakaen et al. (+10 more)
We present a unified reinforcement-learning (RL) framework that discovers compact parametrized
quantum circuits (PQCs) for data-scarce device modeling. A graph neural network (GNN) policy optimized by proximal policy optimization (PPO) searches
circuit architectures using leave-one-group-out cross-validation (LOGOCV) error on held-out process or geometry groups as the reward. The framework achieves the lowest mean absolute error (MAE) on all 11 targets versus six classical baselines, with 59% lower error (Ioff) and 81% tighter fold variability (VTH) for HEMTs and 84% lower error (VTH, SS, Ioff) and 82% tighter fold variability (Ioff) for NWFETs. These results demonstrate the potential of RL-selected, classically simulated PQCs as compact surrogates with low OOD error and improved physical consistency, despite imposing no explicit physical constraints, penalty terms, or device-specific equations, on the two evaluated device
datasets.
Read the full abstract ▾
All authors Rushat Rai, Yun-Yuan Wang, Autsada Kakaen, Pei-Jie Chang, Doan Viet Nguyen, Yuan-Chieh Chiu, Doldet Tantraviwat, Niall Tumilty, Simon See, Wen-Jay Lee, Tai-Yue Li, Nan-Yow Chen, Tian-Li Wu
Hardware Architecture
Proton Irradiation Characterization of an Open-Source ML Accelerator on a Zynq UltraScale+ MPSoC
Saad Memon, Rafal Graczyk, Jan Swakoń et al. (+3 more)
As spaceborne computing systems increasingly rely on neural network (NN) accelerators, the opacity of commercial, black-box architectures severely restricts the development of verifiable radiation mitigation strategies. Open-source, register-transfer level (RTL)-accessible accelerators resolve this limitation by enabling user-defined instrumentation, yet few have empirical radiation-response baselines. This work establishes a foundational system-level
proton-irradiation baseline for an unmitigated open-source Tensil NN accelerator deployed on a Zynq UltraScale+ SoC executing ResNet-20 inference. Under 20 to 58 MeV
proton irradiation, we delivered $4.29 \times 10^{10}$ p/cm$^{2}$ within monitored operational windows. Seven workload interruptions required two restarts of the notebook process, four reboots or board resets, and one power-cycle sequence. Two output-corruption events returned incorrect CIFAR-10 classes without loss of service. In the longer event, the accelerator returned a class absent from the ten-image CIFAR-10 pool for 39 consecutive inputs at normal cadence. The process remained alive, while the kernel log, limited
memory test, and sampled power showed no anomaly. Observation of the stuck-class sequence ended with scheduled bitstream reconfiguration. All nine onsets occurred under the nominal 4 cm beam, which exposed the SoC, LPDDR4, and additional board circuitry; none occurred under the 2 cm SoC-centered field. This pattern shows a field association but does not establish LPDDR4 as the cause because field size was confounded with run order and dose. Linux-managed accelerators require end-to-end content checks and recovery that reaches the state in which corruption can persist. This baseline documents availability loss and silent output corruption, supporting future software hardening of COTS FPGA-SoCs for neural-network inference in space systems.
Read the full abstract ▾
All authors Saad Memon, Rafal Graczyk, Jan Swakoń, Leszek Grzanka, Sebastian Kusyk, Mike Papadakis
Numerical Analysis
A Generalized Scalar Auxiliary Variable Method for Structure-Preserving and Efficient Integration of Nonlinear port-Hamiltonian DAEs
Aashutosh Sharma, Andreas Bartel and Manuel Schaller
We develop an energy-optimal generalized scalar auxiliary variable (EOP-GSAV) framework for nonlinear index-one port-
Hamiltonian differential-algebraic equations (pH-DAEs). Exploiting the port-
Hamiltonian structure, we separate the nonlinear effort, interconnection, and dissipation terms from a constant implicit core. The resulting BDF-1 and BDF-2 schemes require one linear solve per time step with a reusable factorization, while retaining discrete passivity and accurate tracking of the
Hamiltonian. The schemes are compared with the implicit midpoint method equipped with full, modified, and frozen-Jacobian Newton iterations. Numerical experiments ranging from a strongly state-dependent nonlinear stress test to large-scale
benchmarks demonstrate robust and competitive performance, with substantial efficiency gains in matched-accuracy regimes. A comparison with SUNDIALS IDA shows comparable work-precision behavior at equal order despite a non-specialized Python/SciPy implementation, while unrestricted variable-order adaptive IDA is faster in the high-accuracy regime.
Read the full abstract ▾
Artificial Intelligence
Do LLMs Exhibit Coherent Knowledge Structures in Mathematical Reasoning? A Perspective from Knowledge Space Theory
Peng Cui, Heejin Do and Mrinmaya Sachan
Human knowledge is inherently structured and interdependent: mastery of a concept requires prior mastery of its prerequisites, a principle formalized by Knowledge Space Theory (KST). While LLMs achieve strong performance on complex
reasoning tasks, it remains unclear whether they exhibit coherent, human-like knowledge structure. We introduce a KST-grounded framework for evaluating LLM knowledge structure in mathematical
reasoning, using it as a normative framework to analyze whether LLM behavior adheres to principled knowledge dependencies. Evaluating eight open- and closed-source LLMs against real human learners, we find that (1) LLMs do not adhere to human knowledge structure – they frequently violate knowledge dependencies and fail to leverage related knowledge provided in context to improve performance on dependent questions; (2) LLMs do not share a consistent knowledge structure among themselves, as reflected by low overlap in their knowledge distributions. Furthermore, these structural deficiencies remain largely invisible to accuracy-based and LLM-as-judge evaluations. Together, our results provide behavioral evidence that current LLMs knowledge does not follow a human-like structure.
Read the full abstract ▾
Computer Vision
Few-Shot Video Recognition via Hierarchical Metric Learning
Jiaxin Zhang, Haoran Gao, Xizhan Gao et al. (+3 more)
Few-shot action recognition (FSAR) aims to recognize unseen action categories with only a small number of annotated
video samples. Recent works typically apply single-prototype supervision at the network output and fail to sufficiently exploit rich cross-frame global spatial information in
videos. Even existing multi-level metric schemes only impose parallel prototype constraints on intermediate layers, without progressive supervision along the full feature pipeline, which results in limited generalization ability of the learned class prototypes. Inspired by this, we present a novel method, hierarchical metric learning for few-shot action recognition (HML-FSAR). First, a spatial-enhanced module is developed to capture cross-frame global spatial representations. Combined with temporal MHA, heterogeneous
alignment, spatial-temporal feature fusion and dictionary learning modules, it constructs the complete feature processing pipeline. Second, a hierarchical metric learning (HML) strategy is embedded into HML-FSAR. Composed of center metric,
alignment metric, contrastive metric, dictionary metric and prototype metric, HML imposes progressive multi-stage complementary constraints from frame-level representations to final class prototypes, so as to jointly optimize feature compactness, heterogeneous spatial-temporal
alignment, inter-class discriminability and anti-noise robustness. The proposed HML-FSAR method is validated on five widely-used FSAR
datasets, and experimental results fully demonstrate its effectiveness.
Read the full abstract ▾
All authors Jiaxin Zhang, Haoran Gao, Xizhan Gao, Zihao Dong, Tingwei Wang, Sijie Niu
Artificial Intelligence
Uncensored Open-weight Models: Redistribution as the Persistence Layer
10a Labs: Juliette Garcia, Hailey May, Bobby McKenzie et al. (+5 more)
A rapidly expanding ecosystem of actors is removing built-in safety guardrails from open-weight AI models. We profile this ecosystem by identifying key producers, downstream reproductions, and emerging applications. Between January 2024 and March 2026, we identified 3,471 original uncensored models on HuggingFace, each repackaged an average of 2.4 times; three actors account for 52% of all 8,164 compressed redistributions. Once quantized and mirrored across separate accounts, formats, and registries such as Ollama, these models persist regardless of upstream removal and become easier to deploy downstream. Of the 1,643 identified GitHub applications integrating uncensored large
language models (ULLMs), 25% were classified as explicitly malicious.
Read the full abstract ▾
All authors 10a Labs: Juliette Garcia, Hailey May, Bobby McKenzie, David Pham, Matthew Swain, Joshua Valdez, Corie Wieland, Zachary Yahn