Information Theory
Average-Radius List-Decodability of Random Linear Codes
Venkatesan Guruswami, Shilun Li and Mihir Singhal
We prove that for every
prime power $q$ and every $p \in (0, 1-1/q)$, a random $\mathbb{F}_q$-linear code of rate $1 - h_q(p) - \epsilon$ is $(p, C_{p,q}/\epsilon)$-average-radius list-decodable with probability at least $1 - q^{-\Omega(n)}$, i.e., for every center $y \in \mathbb{F}_q^n$, the $C_{p,q}/\epsilon$ codewords closest to $y$ have average fractional Hamming distance at least $p$ from $y$. This extends a similar result for (standard) list-decoding due to Guruswami, Håstad, and Kopparty (2010) to the stronger average-radius guarantee, with the same $O(1/\epsilon)$ list size. For average-radius list-decoding, such a result was previously known only for binary linear codes (Guruswami, Li, Mosheiff, Resch, Silas, and Wootters, 2021) and for general (non-linear) random codes over arbitrary alphabets (Elias, 1991).
Read the full abstract ▾
Computational Complexity
Step Recursion: Resource Profiles and Descent Quotients
Kirill Osipov
We develop a resource representation for step recursion in which mutable-state width and recursion descent are explicit and independent parameters. A width bound $u$ controls the size of the encoded machine state, while an effective descent $\rho$ determines the available recursion depth $\delta_\rho(u)$. For generalized-inverse descents, we derive the depth directly from generator growth and characterize the increasing sequences that can occur as generator orbits. We then connect this depth–width geometry to standard finite-branching computation. Every deterministic bounded-state dynamics is realizable by a single ordinary bounded step recursion over a fixed finite numerical basis. Using deterministic, existential, universal, or alternating aggregation on the same local dynamics yields the corresponding machine semantics. After closure under the width reparameterizations needed to absorb fixed local cost, the resulting
language classes are exactly the machine time–space classes on profiles $(\delta_\rho(u),u)$. Finally, profile domination quotients effective descents by admissible width reparameterization. Some depth curves collapse, yet
polynomial widths support an explicit infinite strict hierarchy between the canonical
polynomial- and exponential-depth profiles. Thus descent remains a nonredundant resource coordinate after
polynomial width reparameterization; standard complexity classes are calibration points.
Read the full abstract ▾
Systems and Control
Expanding the Transient Stability Region of Attraction of Networked Grid-Interactive Inverters: A Probabilistic Active Learning Framework
Zhong Liu, Jialin Zheng, Junjie Qin et al. (+1 more)
The continuous integration of inverter-based resources makes transient stability analysis increasingly important for power system modernization, in light of the intricate dynamics arising from large-scale inverter deployment. However, analytical transient stability analysis methods consistently yield overly conservative stability boundary estimates, which constrain grid dispatch and operational flexibility. Although recent neural Lyapunov methods attempt to enlarge these stability boundaries to obtain less conservative estimates, they remain trapped within restricted domains due to the out-of-distribution problem. To break this bottleneck, this paper proposes a probabilistic active learning framework. Starting from a deterministic inner stability region certified by neural Lyapunov functions, the framework constructs a Gaussian process surrogate and deploys an uncertainty-guided frontier search. By intelligently coupling electromagnetic transient simulations with active boundary exploration, the
algorithm systematically drives the estimated stability boundary outward. Comprehensive evaluations across multi-machine grid-forming
benchmarks demonstrate that the proposed framework substantially reduces estimation conservatism. Across test systems ranging up to four interconnected grid-forming inverters, the methodology achieves up to a $20$-fold volumetric enlargement of the certified stability region over classical baselines, while requiring at most 220 time-domain simulation queries per system, far fewer than the 1,600 queries that exhaustive EMT evaluation demands even for the simplest single-inverter
benchmark.
Read the full abstract ▾
All authors Zhong Liu, Jialin Zheng, Junjie Qin, Xiaonan Lu
Computers and Society
Evaluation in the Age of AI: Output as Evidence of Learning
Md Zarzees Uddin Shah Chowdhury and Samin Rahman Khan
The rapid adoption of artificial intelligence (AI), particularly large
language models (LLMs), has fundamentally disrupted how learning is demonstrated and evaluated in higher education. Tasks that once served as proxies for understanding-such as writing essays, solving problem sets, or producing computer code-can now be generated superficially by AI systems with minimal human effort. This paradigm shift raises a critical ethical question: how should learning be evaluated when traditional indicators of competence are easily outsourced? This paper examines the ethical challenges of educational evaluation in the age of AI from a university-level perspective. We argue that the core problem extends beyond academic dishonesty to a deeper misalignment between assessment practices and the learning outcomes they are intended to measure. Evaluation regimes that rely on artificial constraints risk measuring compliance, access, or concealment rather than genuine understanding,
reasoning, or judgment. By analyzing institutional responses and presenting empirical survey data, we highlight the need for alternative assessment models that emphasize process over product. The goal is to establish ethically informed assessment strategies that preserve student agency and accountability in an automated age.
Read the full abstract ▾
Robotics
Physical Agentic AI: An Architecture for Orchestrating a Robot Crew with LLMs
Xinyuan Liu, Eren Sadikoglu, Riana Chatterjee et al. (+1 more)
Agentic AI frameworks interpret open-ended task goals and decompose them into multi-step plans. Richer information about embodiment-specific capabilities, physical preconditions, and cross-
robot coordination improves grounding, but does not eliminate infeasible, mistimed, or unsafe physical actions. Physical
robot crews therefore require an explicit architectural interface between semantic planning and execution, where every planned action is verified against
robot capabilities, system state, and workflow constraints before actuation. This paper introduces Physical Agentic AI, a framework for skill-grounded
robot agent orchestration, in which each
robot exposes a typed library of executable skills while a foundation model planner decomposes a task into phases and assigns each phase to a
robot-skill pair. A
Robot Orchestration layer exposes the skill library,
robot state, named locations, and workflow contracts to a non-actuating Mission Planner, while a deterministic
Robot Orchestrator validates and authorizes one skill at a time. We evaluate on a drone-UGV search-and-dispatch mission, where every mission in every condition is executed live in Gazebo, and on a
humanoid-quadruped transportation task using hardware-equivalent skill interfaces plus two physical trials on a Unitree G1 and Go2. Varying planner knowledge and runtime enforcement independently, we find that
retrieval raises skill grounding from 51% to 96% yet leaves informed planners dispatching 23-29% of faulted steps. Per-dispatch enforcement reduces false dispatch to 0% with no false blocks, and a held-plan ablation confirms that the gate, not plan variation, is responsible. Live execution makes the difference physical: without enforcement all eight injected faults crossed the orchestration boundary and six produced
robot motion; with enforcement all eight were refused before motion.
Read the full abstract ▾
All authors Xinyuan Liu, Eren Sadikoglu, Riana Chatterjee, Ransalu Senanayake
Computer Vision
Multiple View Neural Regression of a Facial Shape Model
Xiang Li
Creating re-topologized 3D facial meshes is essential for high-quality facial animation but remains labor-intensive and time-consuming. This dissertation explores more efficient approaches for capturing production-ready facial meshes through: (1) the development of VarIS, a custom light sphere for capturing high-resolution stereo geometry and reflectance maps; (2) analysis of camera parameters affecting automatic 2D and 3D landmarking; (3) synthetic-data methods for training neural face regression; and (4) techniques for improving neural multi-view face-shape regression. While VarIS enables photorealistic face capture, its operational and processing costs motivate a more scalable approach. A deep learning framework is therefore proposed to directly predict re-topologized facial meshes from synthetic multiview images generated with Visage Craft, an in-house physically based rendering system using an Appearance 3D Morphable Model (A3DMM). The system produces standardized meshes ready for rigging and animation with minimal human supervision. Results show that incorporating accurate camera intrinsics and extrinsics improves landmark accuracy and
geometric consistency, while 3D landmark regularization further improves reconstruction quality.
Read the full abstract ▾
Software Engineering
Evaluating Inference-Time Defenses Against Package Hallucination in LLM-Generated Code
Alberick Euraste Djire, Iyiola E. Olatunji, Melissa Tessa et al. (+3 more)
LLMs are increasingly used for code generation, yet they frequently hallucinate non-existent software packages, creating exploitable entry points into the software supply chain. We make four contributions to this problem. First, we show that prior evaluation methodologies systematically inflate
hallucination rates by misclassifying standard-library modules as
hallucinations in some
languages. For Python, the overestimation reaches 9.4 percentage points. Second, we evaluate seven inference-time defenses for mitigating package
hallucinations, including five guided decoding strategies (Greedy, Contrastive, DoLa, Nudging, and Active Layer-Contrastive Decoding), an iterative self-refinement approach (Self-Refine), and a
Retrieval-Augmented Generation (RAG)-based defense.. Across eight models spanning five families and four programming
languages (Python, JavaScript, Ruby, Rust), RAG reduces the package
hallucination rate (PHR) in 18 of 32 model–
language configurations. Third, we introduce Package Utility (PU) to assess whether defenses preserve valid and task-relevant recommendations. Among strategies evaluated, Greedy decoding provides the strongest average mitigation–utility trade-off. Fourth, we stress-test all strategies under
adversarial prompts seeded with fabricated package names and find that PHR surges by up to 45 percentage points relative to standard
prompts, with Ruby consistently the most vulnerable
language (80.9–95.2%). Under
adversarial conditions, RAG and Self-Refine outperform all decoding-only strategies, indicating that robust defense requires either external grounding or iterative self-verification when
prompts are actively hostile. Our results recast package
hallucination as both a measurement problem and a decoding-time control problem, and they demonstrate that the choice of defense must be matched to the threat model and recommendation utility.
Read the full abstract ▾
All authors Alberick Euraste Djire, Iyiola E. Olatunji, Melissa Tessa, Earl T. Barr, Jacques Klein, Tegawendé F. Bissyandé
Computation and Language
Iteration Without Elaboration: A Simple ReAct Architecture Suffices for Text-to-SQL Generation
Jian Lu, Haiwei Yu, Raymond M Xiong et al. (+2 more)
Modern text-to-SQL systems have become increasingly elaborate, relying on schema-linking modules,
retrieval-augmented prompting, candidate generation, and multi-stage refinement pipelines. While effective, these additions introduce substantial latency and engineering overhead. To this end, we present ReAct-SQL, a simple yet effective zero-shot ReAct-style framework built solely on iterative
reasoning and a constrained action space defined by a typed Domain-Specific
Language (DSL) of 15 relational operations, rather than free-form SQL generation. The model incrementally issues DSL calls, observes compiled-SQL execution feedback, and revises its
reasoning through interaction. On corrected BIRD mini-dev and EHR-SQL, ReAct-SQL achieves 84.5% and 73.9% accuracy, respectively, matching substantially more elaborate baselines while running up to $8\times$ faster. Incremental ablations further show that iteration primarily improves grounding, while the DSL improves compositional reliability.
Read the full abstract ▾
All authors Jian Lu, Haiwei Yu, Raymond M Xiong, Anru Zhang, Danyang Zhuo
Machine Learning · Cross-listed from eess.SP
Lightweight Multi-scale Hierarchical Anomaly Detection and Localization for Geospatial Big Data Applications at the Edge
Thomas Benton Townsend, Joshua Bean, Benjamin K Tkach et al. (+2 more)
As an increasing number of critical applications, including environmental, emergency, meteorological, and agricultural, rely on real-time anomaly detection in geospatial data streams, challenges related to the storage, processing, and communication of this data arise. Traditionally, large volumes of data have been sent to centralized processing locations for insight extraction. Given the big data context of these applications, this approach becomes increasingly infeasible as data volume and velocity continue to increase. This paper proposes a lightweight edge-oriented approach for anomaly detection and localization for geospatial data streams. By leveraging the H3 discrete global grid system and a multi-scale drill-down logic, the proposed approach significantly reduces computational overhead, achieving a 99.7% reduction in evaluations compared to traditional flat-scan methods. Furthermore, by filtering out noise-induced flickering anomalies at lower resolutions, spatially-persistent anomalous signals can be efficiently identified. The results demonstrate that the proposed framework effectively distills massive geospatial data into actionable insights.
Read the full abstract ▾
All authors Thomas Benton Townsend, Joshua Bean, Benjamin K Tkach, Narcisa Gabriela Pricope, Dimitrios Michael Manias
Artificial Intelligence
CAI-DLLM: Convergence Aware Inference for Diffusion Language Models
Farhana Amin, Sabiha Afroz and Dimitrios S. Nikolopoulos
Diffusion language models can generate many
tokens in parallel, but they still require repeated denoising steps during inference. This makes generation costly, especially when the model continues to recompute
tokens that are already stable. To address these limitations, we propose CAI-DLLM, a training-free inference method that uses first-step confidence to guide denoising and reduce inference time. Specifically, CAI-DLLM commits easy
tokens earlier, allocates more denoising steps to harder
tokens, and adjusts decoding schedules across output blocks. As it relies only on first-step confidence signals, it does not require retraining, extra predictors, or weight updates. We evaluate CAI-DLLM on LLaDA-8B-Instruct and Dream-7B-Instruct across math, code,
reasoning, commonsense, and long-context tasks. CAI-DLLM achieves up to 18.2x wall clock inference speedup on LLaDA GSM8K while improving accuracy from 76.27% to 77.41%, and up to 13.1x speedup on Dream HumanEval while achieving higher pass@1 than no-cache inference, 48.17% compared with 46.95%. On harder
reasoning tasks, speedups reach 44.8x, with a largest accuracy drop of 4.4 points, while energy consumption is reduced by up to 95.3%.
Read the full abstract ▾
Cryptography and Security
Obscura-PQ: Post-Quantum Privacy-Preserving Protocol for the Algorand Blockchain Using Lattice-Based Linkable Ring Signatures
Navid Azimi
Public blockchains expose the complete transaction graph, and the
privacy protocols deployed to obscure it rely almost exclusively on
elliptic-curve cryptography, whose discrete-logarithm foundations fall to Shor's
algorithm. Because ledgers are immutable, every anonymity set published today under classical assumptions can be retroactively deanonymized by a future
quantum adversary. Transitioning to post-
quantum alternatives remains challenging, as strict smart-contract resource limits prohibit native on-chain verification of computationally intensive post-
quantum proofs. To address these challenges, we present Obscura-PQ, a decentralized, non-custodial post-
quantum privacy protocol that verifies natively on the Algorand blockchain. Its core is a setup-free
lattice linkable ring signature over the cyclotomic ring $\mathcal{R}_q = \mathbb{Z}_q[X]/(X^{512}+1)$. A deposit is a Ring-SIS binding commitment to a short secret; a withdrawal proves knowledge of a ring opening via an AOS/Borromean-style challenge chain over two response-sharing linear relations with rejection-sampled short responses, while publishing a deterministic Ring-LWE serial number for double-spend detection. We reduce double-spend soundness and linkability to Ring-SIS, theft resistance to Ring-SIS for honestly generated deposits, and anonymity to Ring-LWE and an explicit decisional linking assumption in the classical random-oracle model. To overcome strict on-chain opcode and storage limits, Obscura-PQ evaluates verification relations entirely in the NTT domain. We split forward NTTs across opcode-pooled execution phases and stream oversized proofs through refundable box storage, enabling $O(1)$ membership and double-spend checks. We provide a complete Algorand testnet implementation, demonstrating native on-chain verification of a post-
quantum privacy protocol under strict smart-contract limits.
Read the full abstract ▾
Networking
Advanced LLM-Enhanced Intent-Based 5G Network Management using Dynamic Semantic Routes
Thomas Benton Townsend and Dimitrios Michael Manias
As the use of Artificial Intelligence (AI) and Large
Language Models (LLMs) is becoming common in everyday applications, their ability to interpret natural
language has increased significantly. An emerging application of AI is integration with network management and orchestration practices. An instance of this integration is LLM-enhanced intent-based networking, where network operators will control a network using natural
language. This work presents the use of dynamic routes with a semantic router to identify an intent from a network operator's
prompt and extract necessary details for intent fulfillment in intent-based 5G+ core networks. Furthermore, the performance of static route selection is assessed by evaluating multiple encoders and dynamic route detail extraction accuracy against a series of realistic operator
prompts. The presented results show that static and dynamic routes are successful in detail extraction and schema formatting.
Read the full abstract ▾
Distributed Computing
NeuroPrefetcher: Storage-Aware Sparse LLM Inference via Delta Prefetching
Nobel Dhar, Md Romyull Islam, Xuechen Zhang et al. (+4 more)
Deploying large
language models on edge devices is increasingly limited by a widening gap between model size and available
memory. Existing approaches such as quantization, smaller models, and offloading can raise the effective
memory limit, but they still assume that the model can be compressed or partitioned to fit within some budget. We target the harder model-exceeds-
memory setting, in which the model remains larger than resident
memory throughout execution and storage becomes an active source of weights on the critical path. We observe that MLP activity during autoregressive decoding has strong temporal locality: approximately 82-85% of active
neurons persist from one
token to the next. This means that most sparse weights needed for the current
token are already resident, and only the newly needed rows must be fetched from storage. We present NeuroPrefetcher, a storage-backed LLM inference system that exploits this property through predictive delta prefetching. After layer 0, a single GPU-resident predictor, occupying 2.86% of base model parameters, predicts sparse activity for all downstream MLP layers in one forward pass. The runtime compares these predictions against resident GPU buffers and issues application-scheduled NVMe reads only for incoming delta rows, replacing reactive operating-system demand paging with explicit, model-aware weight movement. On real unified-
memory edge hardware, NeuroPrefetcher achieves 7.9-12.0x speedup over llama.cpp across constrained
memory budgets.
Read the full abstract ▾
All authors Nobel Dhar, Md Romyull Islam, Xuechen Zhang, Gongjin Sun, Sahidul Islam, Bobin Deng, Kun Suo
Machine Learning
Mol-JEPA: A multimodal Joint Embedding Predictive Architecture for Molecules
Florian Rottach, Sebastian Schieferdecker, William Rudman et al. (+2 more)
Despite recent advances in molecular foundation models, several limitations remain, such as chemically invalid augmentations, modality collapse, and incomplete representation of biochemical environments. To address these challenges, we present Mol-JEPA, a scalable framework for learning molecular world models. Rather than relying on suboptimal molecular perturbations, our model uses modality masking to exploit information from molecular structures, cellular phenotypes, binding affinities, ADMET profiles,
quantum chemistry simulations and other drug discovery data. Across various
benchmarks, we show that the representations learned by Mol-JEPA deliver strong performance, demonstrating the value of incorporating biochemical context through latent space prediction.
Read the full abstract ▾
All authors Florian Rottach, Sebastian Schieferdecker, William Rudman, Randall Balestriero, Carsten Eickhoff
Human-Computer Interaction
Poetic Heritage for Culturally Grounded Emotional Support: An Interaction Design Framework and Its Multimodal Agentic Instantiation
Yangming Zhang, Zhiqian Li, Bin Wu et al. (+4 more)
Digital systems increasingly mediate emotional support, yet their interactions often remain culturally generic. Accordingly, we examine how a poetic tradition can be operationalized as a culturally grounded interactive medium and how generative AI can support such engagement. The resulting interaction design framework translates staged literature-based support and tradition-specific poetic aesthetics into guidance for digital system design. Poemithy instantiates the framework as a
multimodal, LLM-enabled multi-
agent system for guided reflection through classical Chinese poetry. A controlled between-subjects study with 50 participants compared text-only and
multimodal versions. Both conditions showed medium-to-large within-session improvements in affect, anxiety, and
emotion regulation, while between-condition tests detected no differences in these changes. Among secondary post-session user-experience measures, the clearest observed differences favored multimodality in perceived attunement, perceived task success, and engagement; usability and hedonic quality were descriptively higher, while workload did not differ detectably. Post-only cultural ratings were descriptively favorable in both conditions for cultural identification, poetry-engagement and dissemination intentions, and perceived cultural enrichment. Together, the findings suggest that culturally grounded content and structured guidance should anchor system design, while
multimodal presentation may strengthen resonance and engagement. More broadly, the work shows how generative AI can mediate engagement with poetic heritage in culturally grounded emotional-support interactions.
Read the full abstract ▾
All authors Yangming Zhang, Zhiqian Li, Bin Wu, Qi Li, Jie Xu, Yunpeng Song, Liang Zhao
Software Engineering
Do Not Copy/Paste: Soft Barriers for Copying in AI-Assisted Programming
Iyiola E. Olatunji, Alberick Euraste Djire, Jacques Klein et al. (+1 more)
Copying a function from a chat window into an editor takes less than a second. For many uses of AI coding tools, that speed is the point; in settings such as programming education, code review, and security-sensitive development, it can also be the problem. This paper frames copy-paste as an AI code handoff problem: the moment model-generated text crosses from a conversational context into executable or committed software is a design boundary that current tools leave largely unmanaged. We argue that AI coding assistants should not only be evaluated by the code they generate, but also by how they mediate the transfer of that code into software artifacts. We propose soft barriers as one class of handoff-aware mechanisms. Soft barriers preserve access to AI assistance while making unexamined transfer less frictionless. As an initial technical probe, we instantiate this idea using Unicode output perturbations that preserve visual readability but disrupt naive copy-paste execution. We introduce Copy-Paste Resistance (CPR), the fraction of functionally correct clean solutions that become syntactically invalid after perturbation. Across HumanEval and MBPP with four LLMs and four perturbation families, we find that output-level barriers can achieve high copy-paste resistance, but their effectiveness is highly model- and task-dependent. An exploratory pilot with 18 participants provides early evidence that soft barriers can shift users from direct transfer toward editing and reconstruction. We do not present Unicode perturbations as a deployment-ready solution; rather, we use them as a minimal probe for a broader research agenda on practical, transparent, and policy-aware AI code handoff.
Read the full abstract ▾
All authors Iyiola E. Olatunji, Alberick Euraste Djire, Jacques Klein, Tegawendé F. Bissyandé
Computer Vision
OmniCAD: A Large-Scale Benchmark for 3D Spatial Reasoning in Robotics Assemblies
Mingjia Wang, Taiting Lu, Ziwei Dong et al. (+25 more)
Recent
vision-
language models (VLMs) show strong capabilities in robotic perception and spatial
reasoning, yet their ability to reason about complex mechanical assemblies remains underexplored. We introduce OmniCAD, a large-scale
benchmark for assembly-aware 3D spatial
reasoning across diverse industrial systems, including robotic mechanisms, automotive components, aerospace structures, and agricultural machinery. OmniCAD contains 25k mechanical assemblies, with an average of 12 parts per assembly and 21 types of mate relationships. Each assembly includes a human-verified ground-truth 3D model and renderings from 20 viewpoints. The
benchmark evaluates three capabilities: (1) component-level 3D spatial
reasoning, requiring prediction of part positions and orientations; (2) part-to-part relational
reasoning, requiring identification of mating relationships and assembly constraints; and (3) tool-augmented agentic
reasoning, where models iteratively select viewpoints, inspect visual evidence, and refine predictions. Experiments show that current VLMs struggle with industrial assembly
reasoning, often producing inaccurate poses, invalid mating relationships, part interpenetration, and degraded performance as assembly complexity increases. We will open-source the
benchmark, evaluation code, and tool interfaces to support research on accurate, physically valid, and scalable 3D assembly
reasoning.
Read the full abstract ▾
All authors Mingjia Wang, Taiting Lu, Ziwei Dong, Sisong Bei, Jingying Zeng, Runze Liu, Kaiyuan Lin, Hongxing Pan, Kai Zhang, Yizheng Hou, Yangshoudu Zheng, Chenchen Guo, Weiyuan Meng, Shubin Lyu, Zhijun Zheng, Dexu Wang, Xinyu Bai, Shurui Qian, Zhangzixin, Mengyu Pan, Guoliang Shi, Ling Ma, Yifan Yang, Qi He, Yi-Chao Chen, Yincheng Jin, Sung-Liang Chen, Mahanth Gowda
Machine Learning
Q-Learning with Stable Infinite-Dimensional Linear Function Approximation
Shengbo Wang
Q-learning with linear function approximation can be unstable because an arbitrary approximation architecture need not preserve the Bellman contraction. We develop a stable infinite-dimensional linear function approximation framework for Q-learning from a single Markovian behavior-policy trajectory. The learning variable is a coefficient field $\theta\in C(\mathbb L)$ on a compact latent metric space $(\mathbb L,\rho)$. The framework uses a reconstruction operator that maps $\theta$ to a continuous Q-function and a compression operator that maps Bellman updates back to latent coordinates. Nonexpansiveness of both operators induces a contractive latent Bellman map on $C(\mathbb L)$, with a unique fixed point $\theta^*$ whose reconstruction approximates the optimal Q-function up to representation error. We propose two
stochastic approximation (SA)
algorithms and establish their sup-norm convergence bounds with a leading term of order $\widetilde O(n^{-1/2})$. The infinite-dimensional formulation provides a powerful abstraction for identifying the structures that govern statistical difficulty. Smoothness of the compression map in $\rho$ is inherited by $\theta^*$ and the SA iterates, allowing uniform estimation errors to be controlled through covering numbers of $(\mathbb L,\rho)$ rather than the dimension of $C(\mathbb L)$. Remarkably, the SA
algorithms we propose are agnostic to the choice of $\rho$, and thus can automatically adapt to both the smoothness and the geometry. We further illustrate the framework through Q-measure-learning with linear density approximation and output-layer neural weight training under a frozen pretrained network.
Read the full abstract ▾
Computation and Language
GeoRisk-RAG: A Hierarchy-Aware Risk Framework for Improving RAG Reliability through Selective Answering
Meenu Ravi, Shailik Sarkar, Lulwah AlKulaib et al. (+2 more)
Current work on improving reliability in large
language model (LLM)- generated answers has primarily leveraged
Retrieval-Augmented Generation (RAG), knowledge-graph augmentation, and reinforcement learning. While these methods are adept at enhancing and measuring reliability through semantic similarity and faithfulness, they often struggle to distinguish semantic similarity from geographic validity. This is especially critical in natural hazard management domains where geographic granularity (i.e., town vs. city vs. state) is significant for decision-making, as responses valid in one municipality may not transfer to another. In such domains, a confidently wrong answer carries greater risk than abstaining. We present GeoRisk-RAG, a novel hierarchy-aware framework that addresses this geographic-validity gap through selective answering. This framework explicitly estimates geographic applicability using a Directed Acyclic Graph (DAG)-based distance for context
retrieval before response generation. Experiments on a novel held-out wildfire-related question-answering (QA)
dataset show that GeoRisk-RAG significantly reduces false confidence rates for location-dependent questions, lowering the rate to 0.009 compared with ~0.090 for standard semantic similarity and reranking baselines, while consistently achieving higher human preference
alignment. This work provides a more comprehensive assessment of end-to-end RAG pipelines by integrating geographic validity and selective-answering behavior for safer decision-making in geospatial domains.
Read the full abstract ▾
All authors Meenu Ravi, Shailik Sarkar, Lulwah AlKulaib, Yordanos Tessema, Chang-Tien Lu
Systems and Control
Scaling-Based Reciprocal Control Barrier Functions for Nonholonomic Mobile Robots
Tianyu Han and Bo Wang
This paper studies the construction of control barrier functions (CBFs) for force-controlled nonholonomic mobile
robots subject to relative-degree-two safety constraints arising from position-level obstacle avoidance. A scaling-based reciprocal barrier construction is proposed, in which a positive motion-dependent scaling factor is placed in the numerator of a reciprocal barrier associated with the original physical safety function. The resulting barrier is defined exactly on the interior of the physical safe set and becomes singular on its boundary, thereby preserving the certified interior domain of the original safety constraint while recovering first-order control authority. For a force-controlled nonholonomic
robot model, sufficient conditions are derived under which the proposed construction defines a reciprocal CBF, and the interior of the physical safe set is forward invariant under controllers satisfying the induced reciprocal-CBF condition. A scalar strict-feedback system is further used to provide a structural interpretation of the underlying higher-relative-degree cascade under explicit structural assumptions. Numerical simulations demonstrate the induced safe-set geometry and its integration with an optimization-based control framework for obstacle avoidance.
Read the full abstract ▾
Logic in Computer Science
Reasoning with Probabilities: Relating Weighted Model Counting and Probabilistic Model Checking
Bahare Salmani and Vincent Derkinderen
Weighted model counting (WMC) and probabilistic model checking (PMC) are two well- established frameworks that are independently developed, the former for probabilistic inference, the latter traditionally for probabilistic verification, though recently also applied to inference. The formal relationship between the two frameworks, however, remains largely unexplored. In this paper, we lay the foundations for how they relate: we present (1) a mapping from cycle- free parametric Markov chains (pMCs) to arithmetic
circuits (ACs), enabling the reduction of reachability probability computations in such pMCs to a weighted model counting problem on the corresponding ACs, and (2) a mapping from a subclass of arithmetic
circuits – with probabilistic semantics – back to parametric Markov chains. We propose a detailed correspondence between the entities of WMC and PMC, and discuss how our mappings enable transferring optimization techniques such as bisimulation minimization across the frameworks.
Read the full abstract ▾
Machine Learning
Learning Generalizable Behaviors for Terminal Agents
Yihang Yao, Bo Pang, Xuan Phi Nguyen et al. (+3 more)
Terminal
agents are a compelling application of large
language models (LLMs), with the potential to integrate deeply into users' daily workflows. Reinforcement learning (RL) is a key technique for improving their capabilities, making scalable training environments a central challenge. Since public real-user interaction data are scarce, synthetic environments provide a practical alternative, but often suffer from domain gaps and limited fidelity, leading to poor generalization. Existing work mainly scales the quantity and diversity of synthetic environments, while reward-signal quality and the mechanisms governing generalization remain under-explored. We study how RL improves terminal
agents and propose the Agentic Compositional Generalization hypothesis: rather than teaching new domain-specific skills from scratch, RL primarily shapes high-level decision-making behaviors that compose and route low-level skills acquired during pre-training and supervised fine-tuning (SFT). This account is consistent with our empirical results and suggests that verifier quality, which determines which behaviors are reinforced, is more important than simply increasing environment quantity or diversity. Motivated by this insight, we propose River, a simple training recipe that improves reward quality by filtering low-quality environments and augmenting outcome rewards with process-level behavior regularization. Using this recipe, our RL-trained
agent achieves the best performance among evaluated open-source RL-trained 8B models across four terminal-
agent benchmarks. River also generalizes across model families, scales,
agent harnesses, and RL objectives. Using fewer than 30% of the TMax training environments, River improves RL gains by 106% and 30% on average for models ranging from 2B to 27B on Terminal-Bench-Lite and Terminal-Bench-v2.1, respectively.
Read the full abstract ▾
All authors Yihang Yao, Bo Pang, Xuan Phi Nguyen, Ding Zhao, Shafiq Joty, Semih Yavuz
Programming Languages
VeGo: Direct Deductive Formal Verification of Go Programs for Computer Science Education
Tina Massoudi and Chris Dutchyn
As formal methods are rapidly becoming accessible and practical due to AI coding
agents, priority passes to assisting developers and students in generating specifications. Leveraging native HMX/SSA verifiers provide that support with rigorous mathematical guardrails. We present VeGo (Verified Go), a deductive formal verification system that enables direct verification of standard Go source code. VeGo incorporates Hoare-style contracts, loop invariants and integer variants, well-founded recursive measures, block-level scope invariants, and equational
reasoning chains with primed variables directly as non-intrusive Go comments. We detail the
language selection rationale justifying Go as an ideal balance over C, C++, Java, and Rust, strategically adopting Go's native multiple return values. We detail the tool architecture, exploiting the theoretical equivalence between Static Single Assignment (SSA) form and first-order functional programming to annotate code, desugar of clopen interval quantifiers, add Reynolds' skip statement, provide weakest precondition calculus, and native Hindley-Milner constraint inference, and verification condition resolution over the SSA form. We formalize contract-precision checking (weakest precondition vs. strongest postcondition) using an explicit analogy to type inference. Finally, we evaluate VeGo across educational textbooks and outline a roadmap for formal concurrency specifications using epistemic temporal logic.
Read the full abstract ▾
Robotics
Enhancing Sim2Real Transfer for Torque-Controlled Robots through Real2Sim Dynamics Estimation and Reinforcement Learning
Davide Bargellini, Alex Pasquali, Andrea Govoni et al. (+2 more)
Transferring reinforcement learning policies from simulation to Real-World
robots remains a major challenge, particularly when dealing with low-level torque control, where even small modelling inaccuracies can lead to unstable or unsafe behaviours. In this work, we propose a Real2Sim2Real pipeline that improves Sim2Real transfer for torque-controlled robotic arms by combining trajectory matching, parameter optimization via genetic
algorithms, and domain randomization. Using the 7-DOF Franka Emika Panda
robot, we first identify friction, inertia, and
gravity compensation parameters by minimizing the error between real and simulated joint trajectories. These calibrated dynamics are then used to train a TQC-based reinforcement learning
agent in simulation. The trained policy is evaluated in both Gazebo and MuJoCo environments, and finally deployed on the real
robot. Our results demonstrate a significant improvement in tracking accuracy and policy robustness after parameter tuning, with smooth policy transfer from simulation to the Real-World across multiple target-reaching tasks. This work highlights the effectiveness of accurate physical modelling in enabling stable and generalizable torque-based reinforcement learning policies.
Read the full abstract ▾
All authors Davide Bargellini, Alex Pasquali, Andrea Govoni, Riccardo Zanella, Gianluca Palli
Numerical Analysis · Cross-listed from stat.ME
A general-purpose multi-path stacked coupling for stochastic reaction networks
David F. Anderson and Jingyi Ma
Stochastic reaction networks are continuous-time Markov chain models for interacting populations, with applications in biochemistry, epidemiology, ecology, and related areas. Coupling multiple
stochastic reaction networks effectively is a fundamental challenge in
stochastic simulation. Existing variance-reducing coupling methods are typically designed for pairs of processes, though specialized multi-path constructions have been developed for particular applications. To fill this gap, we introduce the multi-path stacked coupling (MSC), a space-time Poisson construction that jointly simulates a finite collection of
stochastic reaction networks with common reaction channels and reaction vectors, but possibly different intensity functions and initial conditions. Each pairwise marginal of MSC has the same law as the corresponding split-coupled pair, allowing existing variance bounds to transfer directly; in finite-state settings, we also obtain first-order expansions for the mean and second moment of finite-difference numerators. We demonstrate the framework through three sensitivity estimation tasks requiring several nearby parameterized paths: estimating many first derivatives simultaneously, estimating a single first derivative using a wider finite-difference stencil, and estimating higher-order derivatives. Numerical experiments on a processive phosphorylation network demonstrate strong performance in each of the three application areas considered, consistent with the theoretical advantages of MSC: across all three applications, MSC achieves the smallest root mean square error (RMSE) among the methods considered over the tested computational budgets.
Read the full abstract ▾
Programming Languages
Rust for Secure Backend Development: A Critical Review and Extended Vulnerability Comparison with Node.js and Django
Md Zarzees Uddin Shah Chowdhury, Rabib Jahin Ibn Momin and Rifat Shahriyar
The Rust programming
language is widely credited with eliminating entire classes of
memory-safety and concurrency vulnerabilities, but the security implications of adopting it in practice extend well beyond
memory safety. This paper presents a critical review of prior work on Rust's security posture in industrial settings, and extends that analysis in a direction the original study did not cover: backend web development. We first assess the strengths and limitations of the existing vulnerability classification of Rust against C, C++, and Java under the SANS Top 25, OWASP Top 10, and the 19 Deadly Sins of Software Security frameworks, identifying gaps including limited empirical validation, a small interview sample, and the absence of a secure development lifecycle discussion. We then contribute an original comparison of Rust against Node.js and Django using the same three-level classification (Rare and Difficult, Safeguarded, Unprotected), supported by side-by-side code experiments for out-of-bounds writes (CWE-787), use-after-free (CWE-416), and race conditions (CWE-362). Our results indicate that Rust's compile-time guarantees dominate at the systems layer, while managed backend frameworks offer stronger built-in defenses at the application layer, suggesting that Rust adoption in web contexts requires complementary safeguards rather than reliance on
language-level safety alone.
Read the full abstract ▾
Computation and Language
Teaching LLMs How ICU Physicians Approach Clinical Reasoning Through OMOP-Aligned Retrieval Improves Reasoning Across Clinical Domains
Miguel Contreras, Scott Siegel, Subhash Nerella et al. (+30 more)
Clinical decision-making relies on identifying relevant patient information to guide diagnosis and treatment, a challenge that is especially difficult in the data-dense and rapidly changing intensive care unit (ICU). Large
language models (LLMs) could support this task. However, existing applications and
datasets mostly emphasize surface-level
retrieval or factual recall rather than the inductive and deductive
reasoning clinicians practice to select and reason over decision-relevant evidence. We hypothesized that training LLMs on expert ICU
reasoning could yield clinical
reasoning skills that generalize beyond critical care. Here we introduce ICU-REACT, a
reasoning dataset developed with 19 clinicians through a clinician-in-the-loop framework to teach LLMs to perform information
retrieval and context-aware clinical
reasoning in the ICU. Using ICU-REACT, we fine-tuned Clin-REACT models spanning 8B-70B parameters and three model families. Across five clinical
reasoning benchmarks, Clin-REACT consistently outperformed its backbone models and open-source general-purpose and medical LLMs. Gains extended to different tasks including script concordance tests, and downstream diagnosis and treatment tasks. These findings suggest that expert
reasoning supervision in critical care can improve broader clinical
reasoning, although prospective evaluation is needed before real-world clinical use.
Read the full abstract ▾
All authors Miguel Contreras, Scott Siegel, Subhash Nerella, Jessica Sena, Jiaqing Zhang, Heng Sun, Hruday Tej Akkaladevi, Peiyu Lu, Jordan Rosen, Sumit Kapoor, Sasank Desaraju, Grace R. Thompson, Jacob Purcell, Michael Petrauskis, Philip KW. Hong, Meghan Brennan, Sarah Chrabaszcz, Tierra Smith, Ronnie Ren, Michel S. Kabbash, Ceyhun Haziroglu, Rushi Patel, Gabriel Gomez, Charlotte Chaiklin, Randy Leung, Kenneth N. John, Whitman Wiggins, Philip Kayser, Vincent Bird, Maria Bruzzone, Tyler J. Loftus, Azra Bihorac, Parisa Rashidi
Computer Vision · Cross-listed from eess.IV
GET: Generative Embedding Translation for Medical Image Segmentation
Md Maklachur Rahman, Md Hasan Al Banna, Saraf Anjum et al. (+2 more)
Generative
segmentation provides an alternative to direct pixel-wise prediction by operating on learned latent representations, but effective image-to-mask translation must preserve target structure while remaining computationally efficient. We propose Generative
Embedding Translation (GET), a structured
embedding-translation framework that progressively transforms image
embeddings into mask
embeddings within the frozen latent space of a Stable
Diffusion VAE. GET uses a U-Net-style
Embedding Translation Network with 1.07M trainable parameters, combining Mobile Bottleneck Convolutions, Subsampled Self-
Attention, and Multi-scale Feature Enrichment for local modeling, global context, and multi-scale refinement. Across five medical
segmentation datasets, GET outperforms generative, CNN, and
Transformer baselines. Compared with the strongest generative baseline, GMS, GET improves average Dice and IoU by 0.93% and 1.26%, reduces HD95 by 0.81 pixels, and uses 31.41% fewer trainable parameters. Under bidirectional BUS-BUSI domain shift, GET further improves Dice and IoU by 3.51% and 3.39%, while reducing HD95 by 27.37 pixels. Our code is available at: https://github.com/maklachur/GET.
Read the full abstract ▾
All authors Md Maklachur Rahman, Md Hasan Al Banna, Saraf Anjum, Mahmudul Hasan, Tracy Hammond
Machine Learning
KMGen: A Skill-based Approach for Synthetic Individual Patient Data Generation
Jalen Jiang, Chufan Gao, Ethan Rasmussen et al. (+2 more)
Individual patient data (IPD) from clinical trials is the substrate for survival modeling, meta-analysis, and safety research, yet IPD is rarely released. Prior work has addressed only half of this gap: reconstructing Kaplan-Meier (KM) curves from published plots – typically requiring manual digitization or human-in-the-loop correction – while offering no mechanism for generating the adverse-event (AE) streams that constitute the other half of a patient record. We introduce KMGen, the first end-to-end framework that (i) fully automates KM curve extraction at accuracy competitive with human-guided tools, and (ii) generates synthetic per-patient AE trajectories from public trial registry records. The extraction stage is a fully automated agentic pipeline – an
agent generates code to extract each step in the KM curve – achieving a mean Integrated Absolute Error (IAE) of 0.0151 on a 32-plot
benchmark spanning clean, edge-case, and
adversarial conditions. The IPD generation stage decouples patient archetype extraction from statistical sampling: an LLM distills the trial record into arm-specific statistics, adverse events, patient demographics, and risk multipliers. A mechanistic sampler generates patient events via clinical archetypes, bootstrap rank-correlation coupling to the empirical KM curve (preserving the marginal survival distribution exactly), and cycle-based AE scheduling with an induction/maintenance split. Across three held-out oncology trials spanning an order of magnitude in cohort size and 30 independent regenerations per trial, KMGen achieves mean integrated KM absolute difference $\Delta_{\text{KM}}\,{\leq}\,0.051$, sex/ECOG JSD ${\leq}\,0.013$ on 5 of 6 demographic slots, and recovers ${\geq}\,71\%$ of the top-15 AEs by exact MedDRA term under a single fixed parameter set. The pipeline is released as open source at https://github.com/chufangao/kmgen.
Read the full abstract ▾
All authors Jalen Jiang, Chufan Gao, Ethan Rasmussen, Stephen Z. Xie, Jimeng Sun
Computer Vision
AI-based worker guidance in assembly and disassembly operations using multimodal ego/exo-centric data capture and structured task knowledge
Vivek Chavan and Jörg Krüger
Assembly and disassembly processes rely on expert knowledge that is difficult to document, reuse, and transfer. This paper presents a data-centric approach for extracting structured task knowledge from expert demonstrations using
egocentric and exocentric recordings. Temporal and
multimodal information from
video and narration is jointly encoded to derive structured task representations that enable procedural documentation and context-aware worker guidance. The approach is evaluated on a real-world disassembly case study, demonstrating that
video-based representations capture procedural structure and execution context beyond static image-based methods. The results highlight the potential of
egocentric video understanding for repair, training, and circular manufacturing applications. Project website: https://indego-assistant.github.io/
Read the full abstract ▾