Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science (sign in to use)

Wednesday 12 August

Numerical Analysis

A Positivity-Preserving Expectation Scheme for Hamilton–Jacobi–Bellman Equations with Oblique Robin Boundary Conditions

For anisotropic diffusion with mixed derivatives, standard compact coordinate-aligned stencils and some local finite-volume or finite-element constructions can lose nonnegative coefficients unless suitable coefficient or mesh conditions are imposed. Here nonnegative coefficients are generated directly from conditional expectation rather than from an algebraic stencil decomposition. We construct a positivity-preserving scheme for possibly degenerate Hamilton–Jacobi–Bellman equations with controlled oblique Robin boundary conditions. At interior nodes the construction stems from a one-step reflected Feynman–Kac identity: an $m$-dimensional Rademacher vector generates $P=2^m$ equally probable weak-Euler branches, an exterior branch is mirrored about its oblique projection, and twice its overshoot serves as the discrete boundary local time $D$. The Robin coefficient enters only through the attenuation factors $e^{-\kappa D}$ and $De^{-\kappa D/2}g$, leaving the equal branch probabilities unchanged. Boundary nodes use a separate same-level closure over a spatial offset $\ell_h\asymp h$, which may be implicit; uniform obliqueness and $\mathbb P_1$ interpolation give a mesh-independent positive weight on interior nodes, so fixed linear Robin data yield a sparse nonsingular $M$-matrix system and the general control set yields a monotone contraction. Positivity is preserved for nonnegative data without a diagonal-dominance condition and without any CFL-type relation between $\Delta t$ and $h$.
Read the full abstract

Computer Vision

Dual Anchors, Do It Better: Hierarchical Group Merging for Zero-Shot Anomaly Detection

Zero-shot anomaly detection (ZSAD) aims to identify anomalies in unseen domains, a setting that is particularly critical for industrial and medical applications where domain shifts are prevalent. However, most CLIP-based ZSAD methods anchor semantics solely on the text modality, making performance highly sensitive to prompt design and leading to weak visual grounding. To mitigate these limitations, we propose a Dual-Anchor framework that complements conventional text anchors with hierarchical image anchors constructed via a top-down grouping mechanism. This mechanism progressively aggregates local-to-global image features to form normal and abnormal group tokens, which serve as image anchors and act as gating signals in a Group-Gated Token Refiner to enhance the global representation. The refined image anchors are then fused with text prompts to construct dynamic state prompts. By jointly reinforcing visual and textual semantics, our framework stabilizes image-text alignment, reduces prompt dependency, and achieves strong generalization across 8 industrial and 6 medical benchmarks.
Read the full abstract

Discrete Mathematics · Cross-listed from math.CO

Nonisomorphic Graphs Can Share an Arbitrarily Large Fraction of Their Vertex-Deleted Cards

For a graph $G$, its vertex deck is the multiset of graphs obtained by deleting one vertex. Bowler, Brown, and Fenner (BBF) proposed $2\lfloor(n-1)/3\rfloor$ as the maximum possible overlap between the decks of two nonisomorphic $n$-vertex graphs, for all sufficiently large $n$. We first give an explicit pair of connected nonisomorphic graphs on $78$ vertices with at least $51$ common cards, exceeding BBF's predicted value of $50$. We then construct, for every even $r\ge4$, families at arbitrarily large orders whose overlap fraction is asymptotically at least $1-1/r$. Consequently, for every $\alpha<1$, infinitely many pairs have more than $\alpha n$ common cards, so the attainable fraction is arbitrarily close to the full deck. For representative instances, the predicted overlaps were also checked by complete deck generation and isomorphism testing with Brendan McKay's nauty tools.
Read the full abstract

Systems and Control

Coordinated Dynamic Operation of Integrated Electrolyzer-Compressor Systems

The increasing interaction between power and hydrogen sectors highlights the importance of coordinated operation of electrolyzers and electric-driven compressor stations (EDCSs). This becomes particularly of higher importance under transient disturbances. However, coordinated dynamic interactions of these coupled subsystems remain largely unexplored. This article addresses such gap by developing a dynamic model for an integrated electrolyzer-EDCS system and designing appropriate PID control schemes to address the potential disturbances affecting either component. To this end, linearized models of the electrolyzer and EDCS are first derived to enable systematic controller design. Then, two PID controllers, representing conservative and fast-tracking designs, are developed to coordinate the system response. The developed coordinated model is examined and verified under four different cases. The results demonstrate the effectiveness of the proposed model under disturbances from the compressor driver or the electrolyzer. Controlling the electrolyzer flow in response to EDCS disturbances coordinates system dynamics and mitigates undesirable transient fluctuations. Conversely, under electrolyzer disturbances, regulating the EDCS torque eliminates inconsistent responses in pressure, flow, and rotational speed, while preventing hazardous transient undershoots and overshoots. Overall, the proposed framework guarantees transient stability and operational reliability of the integrated electrolyzer-EDCS system.
Read the full abstract

Computer Vision

Seed2GS: Camera-Free, Training-Free Object Extraction from 3D Gaussian Scenes via a Single Reference-View Grounding

Extracting a target object from a pre-built 3D Gaussian Splatting (3DGS) scene enables interactive 3D editing. Existing methods either train for tens of minutes per scene, sacrifice accuracy, or require original reconstruction cameras that pre-built assets may not include. We present Seed2GS, which achieves the highest reported LERF-MASK accuracy without original reconstruction cameras or scene-specific representation training. Its key insight is to separate target identity from 3D coverage. QD-SAM3 selects one reliable reference mask from several open-vocabulary candidates, fixing identity once. Seed lift and visibility-adaptive virtual orbits then expose the object from new viewpoints, while tracking propagates the seed without repeated detection. Because the scene remains frozen, these masks supervise only one temporary foreground logit per Gaussian. On LERF-MASK, Seed2GS reaches 92.1% mean intersection over union (mIoU) with a measured compute-only latency of 9.3 seconds, 3.7 points above the strongest scene-trained baseline and 7.6 points above the closest camera-free baseline. With one fixed test reference per scene, the complete pipeline retains 91.1% mIoU; replacing its predicted seed with a ground-truth mask improves mIoU by only 0.72 points. On 3D-OVS, Seed2GS reaches 95.7% mIoU.
Read the full abstract

All authors Zongjian Ding, Yudong Gao, Jiale Liu, Xinglin Yu, Junxing Ren, Dong Wei, Yajing Chen, Shan Huang, Mingjun Cheng, Min Li

Logic in Computer Science

Comparing Call-by-Name and Call-by-Value Reduction and Reduction Strategies in Calculi for Classical Logic

We define call-by-name and call-by-value reduction and reduction strategies for the calculi slmu (symmetric lmu), lmmt, and Xs (X with implicit substitution). We establish a strong relation between these notions through defining a single interpretation from slmu to lmmt that respects normal reduction, as well as the call-by-name and call-by-value reduction in slmu within the their counterpart in lmmt; for the strategies, we will show similar, but weaker results. We also define a single mapping from lmmt to Xs, and show that this also respects all three notions. We then continue with studying the natural encoding of Xs into lmmt, and show that only full reduction is respected, but that reduction steps are needed to model substitution, so the CBN and CBV strategies cannot be respected. We conclude with studying the combination of our efforts and define an interpretation of slmu into Xs, and show that CBN and CBV reduction are respected. This result underlines that Xs and lmmt are similar, but different calculi, and that the nature of slmu makes that any encoding into either can never fully respect the strategies.
Read the full abstract

Computation and Language

Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill

Turning a research idea into a complete paper requires more than text generation: the system must retrieve literature, design and execute experiments, revise claims according to evidence, produce publication-ready figures, and maintain consistency across a long generation process. We present Spark-to-Paper, an end-to-end research paper generation system implemented as thirteen composable skills inside an existing coding assistant, without requiring a separate agent platform or orchestration service. Spark-to-Paper separates model-based judgment from deterministic operations that can be directly executed and checked. It further separates experiment planning from reporting, so that required evidence is specified before results are observed and manuscript claims are revised according to measured outcomes. To improve reliability over long research trajectories, the system combines deterministic integrity checks with self-critique and bounds a failure mode we call the Self-Refutation Loop, in which repeated experiments continue to reject the original research objective. Spark-to-Paper also produces editable vector figures through programmatic plotting for experimental results and code-based reconstruction for generated method diagrams. Across eight controlled research topics, Spark-to-Paper achieves 99.5% citation validity and 96.4% figure editability. A controlled ablation increases fabrication detection from 14% for a single-pass draft to 92% with the full integrity and review stack, while adversarial review achieves 74% precision. The full system uses 11.9M tokens, costs $8.1 per manuscript, and requires 3.2 hours on average. These results show that end-to-end research paper generation can be implemented as a lightweight, composable workflow inside existing coding assistants while keeping experimental evidence central to how claims are accepted, revised, or abandoned.
Read the full abstract

All authors Zhuoyang Qian, Biao Wu, Yiran Wang, Chris D Yan, Desan Dai, Liangwei Zheng, Jin Jiang, Junsheng Zhang, Wenhao Wang

Social and Information Networks

Twitter and disability activism: leadership and relevant topics in the online conversation

The dissemination and viralization of information on social media has been widely studied from various perspectives, including that of digital activism. On the other hand, disability-related activism has conquered the online environment, thus obtaining a reach that goes beyond the offline space and generating dialogue in the digital sphere. This article analyses the conversation generated on Twitter, taking as a sample all the tweets with the #disability hashtag before and after the International Day of Persons with Disabilities. More than 18,000 tweets, containing almost as many mentions, were analysed and interpreted as the weighted edges of a graph created using Gephi software and applying the Force Atlas 2 brute force algorithm. The focus was placed on the conversational communities generated around that hashtag, their main themes and the prominent participants in them. In conclusion, although the network of mentions is very dispersed, Twitter is the setting for assertions that receive certain institutional and political support in the Latin American environment, for organisations related to the cause (such as the ONCE Foundation) and, above all, the clear predominance of female activists.
Read the full abstract

All authors Terese Mendiguren-Galdospin, Koldobika Meso-Ayerdi, Jesús Ángel Pérez-Dasilva, María Ganzabal-Learreta, Ainara Larrondo-Ureta, Simón Peña-Fernández

Computation and Language

LODESTAR: Robust Entropy-Based Answer Selection in Retrieval-Augmented Generation for Question Answering – Directing Frozen-LLM Entropy with a Reinforcement-Learned Prompt Polarizer under Misleading Passages

Predictive-distribution entropy is a strong answer-selection rule in retrieval-augmented generation (RAG) for question answering: across five QA benchmarks, selecting the answer a frozen respondent LLM produces with the lowest answer-token entropy lifts mean $F_1$ from 0.4769 to 0.5148 over the retriever's top-ranked passage, without gold answers. Yet this rule, which prior entropy-based selectors adopt, fails: a misleading passage makes the respondent confidently wrong, driving entropy down where the uncertainty signal looks most trustworthy. The failure comes from the passage the respondent reads, and the context it is read in is an input we can intervene on. We introduce LODESTAR: to our knowledge the first method to score a text intervention by the uncertainty it induces in a third-party frozen respondent, compared within one question. LODESTAR uses reinforcement learning (GRPO) to train, once and offline, a polarizer – a short fixed natural-language string inserted into the respondent's prompt and never into its weights, directing entropy so that entropy-based answer selection stays robust to misleading passages; training labels are built from gold answers and two LLM judges, and inference reads neither. With every competing selector under the same frozen respondent and candidate pools on 5,008 questions, LODESTAR attains the highest mean $F_1$ of any inference-ready selector (0.5339), the highest macro exact match (0.4136), and the highest GPT-4o judge score of the frozen-respondent configurations judged (0.6435); its three-seed mean wins all 70 $F_1$ cells against fourteen published configurations and is paired-significant on $F_1$ against every one. The gain holds in-domain on NQ-Open and out-of-domain over SQuAD, TriviaQA, EntityQuestions and WebQuestions. Ablating the polarizer shows it is what makes the respondent read a misleading passage less often (26.0% vs 30.3%).
Read the full abstract

All authors Hung-Chun Hsu, Po-Jen Ko, Che-Cheng Wu, Li-Yang Chang, Chuan-Ju Wang

Hardware Architecture

NITRO: High-Performance 3D NAND Flash-Based In-Storage Computing with Enhanced Activation Dataflow

In-storage computing (ISC) is considered a next-generation memory architecture for its ability to relieve the data bottleneck between the host and the memory. While the required resources of large language models (LLMs) have increased significantly in recent years, the memory density has not scaled accordingly. Recently, several works have studied NAND flash-based processing-in-memory (NAND-PIM) schemes to exploit the high density of the memory. However, they do not address the dataflow/buffer for the intermediate values, so a simple method is to deal with the values in the slow flash memory array. To overcome such a limitation, we propose a high-performance NAND flash-based ISC architecture with enhanced activation buffering. Instead of using the very slow flash memory array for the intermediate values, our architecture buffers the values in a fast DRAM subsystem. This approach effectively handles the high-latency penalties when activations are programmed into slower TLC NAND flash. We also introduce a distributed dataflow approach for the NAND-PIM array. This approach maximizes computational parallelism by employing efficient intra-plane data mapping. The results show that our proposed architecture achieves significant performance improvements, reducing the inference latency by up to 85% compared to the baseline.
Read the full abstract

All authors Sanghun Shin, Sangyeon Kim, Gisan Ji, Sungju Ryu

Computation and Language

LazyTrain: Limited-resource Allocation toward Zero-waste Yield Optimization in Large Language Model Training

Training large language models on limited hardware is increasingly a scheduling problem across GPU compute, host memory, PCIe transfer, and storage bandwidth. Existing offloading systems reduce GPU residency, and MegaTrain shows that a CPU-master layer-streaming executor can train large models on a single GPU, but fixed checkpointing and placement heuristics still leave communication exposed on the critical path. We propose LazyTrain, an optimization layer over a layer-streaming executor. LazyTrain formulates checkpoint selection, activation placement, recomputation, and CPU-GPU-NVMe communication overlap as a mixed-integer scheduling problem, then executes the solved policy during training. It further couples 8-bit optimizer states with fast gradient clipping as a single Hybrid 8-bit operator: state compression reduces optimizer-state memory, while fast clipping counteracts the additional CPU-side update overhead. Across H800 experiments from Qwen2.5-3B to Qwen3.6-27B, LazyTrain improves sustained TFLOPS over matched baselines runs by approximately 1.24$\times$; RTX 3090 experiments likewise increase the maximum feasible batch size by one at each model scale. In the primary Qwen3.6-27B H800 MetaMathQA run, LazyTrain reaches 219.95 TFLOPS and 1361 tokens/s at batch size 72, peaks at 68.84\,GB of GPU memory, and obtains 95.42% exact-match accuracy on the full evaluation split. The source code is available at https://github.com/DataArcTech/LazyTrain.
Read the full abstract

All authors Xiaojun Wu, Cehao Yang, Honghao Liu, Xueyuan Lin, Xuhui Jiang, Chengjin Xu, Jia Li, Jian Guo

Machine Learning

A Factor Graph Approach to Scalable Multi-Output Gaussian Process Regression

Multi-output Gaussian process regression scales cubically in the number of observations times outputs, and dense kernel-matrix methods need bespoke handling whenever different outputs are observed at different inputs. We express multi-output Gaussian process regression as a Forney-style factor graph in which a nearest-neighbor chain orders a fixed candidate set of $C$ inputs into a one-dimensional sequence. Along this chain, latent Matérn processes evolve through linear-Gaussian transition factors, while the linear model of coregionalization mixes $L$ latent processes into $D$ outputs through a deterministic mixing factor and per-output scalar observation factors. Posterior computation reduces to exact Gaussian message passing on the chain at cost $\mathcal{O}(C(DL^2 + L^3))$ after chain construction, and missing observations omit their local factor without any covariance-matrix restructuring. The formulation therefore scales in the number of data samples and in the rate of missing observations, while remaining best suited to candidate sets in low input dimension. We compare the factor-graph formulation against an exact kernel-matrix baseline, a sparse-variational inducing-point baseline, and a nearest-neighbor baseline on a synthetic input-dimension sweep and on electricity time series forecasting. At low input dimension the factor-graph posterior tracks the exact kernel-matrix posterior closely, and the gap grows gradually as input dimension increases while staying competitive with both approximate baselines. On the electricity time series our factor-graph formulation matches all three baselines in forecast accuracy while scaling linearly in the number of data points, where the exact kernel-matrix method becomes infeasible and the inducing-point baseline remains substantially slower.
Read the full abstract

All authors Wouter W. L. Nuijten, Esther G. van Pelt, Albert Podusenko, İsmail Şenöz, Wouter M. Kouw

Numerical Analysis

Positive quadrature and mobile sampling of multivariate trigonometric polynomials

The geometric properties of quadrature points in one and multiple dimensions are a classical topic in numerical analysis. Recently, generalized quadrature methods, where discrete points and weights are replaced by integration along curves, have attracted growing interest. This paper focuses on positive generalized quadratures that are exact for multivariate trigonometric polynomials. We derive upper bounds on the covering radius of such quadratures using sign-localized test functions, a technique that also extends naturally to algebraic polynomials on intervals, spherical polynomials, and hyperbolic cross trigonometric polynomials. For lower bounds on the length of quadrature curves, we compare two recent approaches in the context of multivariate trigonometric polynomials. The second part of the paper studies a well-known, geometrically simple curve that underlies rank-1 Korobov lattice rules for periodic functions. We prove that these curves are quasi-optimal with respect to multiple optimality criteria and demonstrate its adaptability to the 2-sphere.
Read the full abstract

Computer Vision

HarmoniDPO: Video-guided Audio Generation via Preference-Optimized Diffusion

Video-to-audio (V2A) generation faces significant challenges in achieving precise temporal synchronization and high perceptual quality due to the complex, ambiguous relationship between visual and auditory cues. Existing methods typically compress video inputs into single feature representations, leading to significant loss of temporal dynamics and fine-grained visual information. These approaches also rely on reconstruction-based training objectives that poorly correlate with human perceptual judgments of audio quality and appropriateness. We propose HarmoniDPO, a novel framework that integrates preference-based optimization into diffusion-based V2A generation to address these limitations. (1) Our approach leverages a dual video representation: combining global context with frame-wise features to preserve temporal dynamics and semantic detail. (2) Inspired by reinforcement learning from human feedback (RLHF), HarmoniDPO employs online Direct Preference Optimization (online-DPO) to fine-tune a diffusion-based V2A model from preference judgments, enhancing perceptual quality and alignment. (3) Additionally, we introduce Dual-scale Diffusion Search (DDS), a test time scaling algorithm that adaptively optimizes output fidelity during inference. Experiments demonstrate that HarmoniDPO outperforms state-of-the-art methods in audio-video synchronization and subjective audio quality, offering a robust solution for generating realistic, human-preferred audio from video.
Read the full abstract

Computational Engineering

Comparative Analysis of Low-Rank Adaptation in Large Language Models versus Dense Embedding Regression for Headline Click-Through Rate Prediction

Optimizing digital content headlines for click-through rate (CTR) is an important problem in online media and recommendation systems. While large language models (LLMs) have demonstrated strong generative capabilities, their effectiveness for discriminative ranking tasks, such as selecting the highest-performing headline from a set of candidates, remains less well understood. In this work, we compare a LoRA-fine-tuned causal language model, LOLAQwen (0.6B), with a dense embedding regression model for headline selection. We formulate headline selection as a winner-take-all classification problem and evaluate both approaches using a dataset of 3,263 A/B-tested headline groups. Performance is measured using Top-1 accuracy, defined as the proportion of groups for which the model correctly identifies the highest-performing headline. The embedding regression model achieves a Top-1 accuracy of 42.79%, compared with 35.70% for the LoRA-fine-tuned language model. These results indicate that, for this headline selection task, a lightweight discriminative approach can outperform a small generative language model fine-tuned using parameter-efficient adaptation. The findings highlight the potential of embedding-based regression models as efficient alternatives to generative models for high-throughput content ranking applications.
Read the full abstract

All authors Samarth Sirsat, Anirudha Shinde, Amit Sethi, Aman Verma

Artificial Intelligence · Cross-listed from quant-ph

Hamilton-Zero: A Neural Tensor-Network Foundation Model for Ground States of Arbitrary Quadratic Qubit Hamiltonians

A central promise of useful quantum advantage is the ability to compute ground states of Hamiltonian systems beyond the reach of classical simulation methods. Here we demonstrate that this problem can be effectively amortized across an arbitrary and universal set of Hamiltonians by a foundation model with $\sim0.5$B variational parameters, trained with contemporary techniques from large language models and deep reinforcement learning. To do this, we formulate $\text{spin-}1/2$ quantum ground-state learning as manifold variational optimisation over centrally odd scalar functions on $\mathrm{SU}(2)^N$. This replaces explicit Hilbert-space vector amplitudes with manifold functions on which the Hamiltonian acts through Lie derivatives, evaluated by custom automatic differentiation primitives. We prove that the resulting variational principle on this manifold preserves the $\text{spin-}1/2$ sector's ground-state upper bound using the Peter-Weyl theorem and justify the choice of such a representation with a no-go theorem for pure state foundation NQS. We then pre-train our foundation model on a dataset of hundreds of thousands of different Hamiltonian systems, varying the connection topology, system size, interaction types and strengths, bringing together a century of many-body literature. Using a novel $\mathrm{SU}(2)$ replica-exchange Langevin sampler and sharded natural-gradient optimisation, we train our model with our own extension of the Kronecker-Factored Approximate Curvature (KFAC) optimiser on system sizes up to 64 qubits. On a held-out generalisation dataset, we fine-tune our model on system sizes of up to 1024 qubits, and evaluate on systems up to 8100 qubits.
Read the full abstract

All authors Timothy Heightman, Elena Orlova, Philip Mantrov, Aleksei Ustimenko

Machine Learning

Disentangling the Expressivity of RoPE

Two accounts recur in explanations of the success of rotary position embeddings (RoPE). Expressivity studies associate periodic position information with modular predicates, whereas mechanistic and long-context studies emphasize positional anchors and local offsets. We formalize both accounts for fully uniform, finite-precision soft-attention transformers. We find that, if every rotary component is periodic, RoPE transformers recognize exactly the languages definable in past temporal logic with modular predicates. Conventional RoPE is different: The rotations it computes never repeat. This yields a precision-dependent bounded simulation of fixed-offset look-back operators, rather than an all-length modular characterization. Controlled experiments match this separation: Constructed periodic schedules length-generalize on modular languages, while conventional RoPE behaves more like a bounded locality bias and can impair tasks requiring position-invariant access to distant context. Altogether, our findings shed light on RoPE transformers, bringing theoretical expressivity characterizations closer to models used in practice.
Read the full abstract

All authors Selim Jerad, Anej Svete, Jiaoda Li, Ryan Cotterell

Computer Vision

A Model-Internal Protocol for Assessing Multimodal Models as Integrated Systems

As Large Vision-Language Models increasingly aim to integrate visual generation and understanding within a single parameter space, evaluating such structural unification in a cohesive manner remains a critical challenge. Current evaluation protocols predominantly treat generative and discriminative capabilities as separate tasks, leaving a gap in system-level evaluation for unified multimodal models (UMMs). In this work, we propose Self-Generative-Understanding (SGU), a novel, annotation-free evaluation framework that probes the integrated capabilities of unified models through a semantic closed-loop challenge. Without requiring new annotations, SGU leverages the dual understanding-and-generation abilities of UMMs by asking them to first perceive an image and produce a textual description, subsequently reconstruct a visual context based on that description, and finally perform reasoning over the self-generated output. This pipeline provides a zero-cost testbed that yields an integrated performance score specifically tailored for evaluating UMMs as unified systems. Extensive experiments show that even high-performing UMMs often struggle to reason over their own generated contexts, revealing limitations that are not captured by separate evaluations of understanding or generation alone. Our work provides a complementary holistic evaluation framework and offers a foundation for benchmarking the development of next-generation unified multimodal models.
Read the full abstract

All authors Hao Zhang, Jiaxin Qi, Zhijiang Tang, Jianqiang Huang

Artificial Intelligence

Policy-as-logic for robust reasoning over rules

In many practical applications of generative AI systems, from tax rules to airline baggage allowance, responses to natural language queries must respect written policies or rules. We present a hybrid symbolic approach that expresses policies in formal logic and at inference time exploits the representation power of language models for fact extraction to ground predicates, and an answer set solver for reasoning such that responses are interpretable, auditable, and as we show, accurate and robust under input perturbations. Specifically, we show this separation of extraction and reasoning steps outperforms policy-as-prompt and policy-as-code methods in most cases with ~10x reduction in token usage. The results point to the value of structured reasoning and symbolic solvers in conjunction with generative models to make robust decisions involving objective criteria.
Read the full abstract

Robotics

DaViNCi: A Dataset Towards Outdoor Vision-and-Language Navigation with Continuous Actions and Dynamic Elements

Vision-and-Language Navigation (VLN) has progressively expanded from indoor to outdoor environments. However, existing outdoor VLN datasets still rely on fixed discrete topological graphs for construction. It fails to align with the rapidly changing real-world outdoor environments and impedes the sim-to-real transfer of VLN agents. To address this limitation, we propose DaViNCi (Dynamic Vision-and-Language Navigation in Continuous Environment), the first outdoor VLN dataset that simultaneously introduces both continuous and dynamic factors. The agent not only moves in the outdoor environment using continuous actions but is also required to handle unpredictable dynamic elements. The dataset encompasses six distinct maps with a total of 6,933 trajectories. Through comprehensive comparative experiments, we find that the success rate on DaViNCi decreased by more than 10% in discrete environments compared to previous datasets. And there is an even greater decline in continuous settings, demonstrating the challenge of DaViNCi. Furthermore, we clarify the impact of action granularity and dynamic elements. These results demonstrate the practical value of DaViNCi in advancing outdoor VLN toward more realistic environments. The website is https://xzh0312.github.io/DaViNCi/.
Read the full abstract

All authors Zihao Xie, Pingrui Lai, Yitong Wu, Hua Yang

Sound

Beyond Prompted Agreement: Instruction Effects on Key and Beat Grouping in Text-to-Music Generation

In music-generation models, an explicit instruction to realize a musical attribute can paradoxically make it less common. How, then, should we assess whether a model follows a musical instruction? We use matched inputs that omit an attribute, specify one target, or specify another target, and compare the resulting audio. We evaluate key and beat grouping in ACE-Step 1.5, Stable Audio 3 and LeVo2 on 2,304 primary outputs. In Stable Audio 3, a four-beat instruction reduces detected four-beat occurrence from 96.9% to 56.3%, even though four beats remain more common than three under their respective instructions. Further experiments show that rephrasing can improve attainment while reducing the difference between target instructions, and that ACE-Step shows larger changes in target occurrence when text instructions retain its native attribute field. Our findings suggest that evaluating musical instruction following requires both target attainment and comparisons with generation with an omitted target instruction and with a different specified target.
Read the full abstract

Robotics

Scalable Multi-Agent Maze Traversal with Local Communication

Cave networks, pipe systems, and similar maze-like environments pose significant challenges for multi-agent navigation in unknown settings with limited communication. We propose a distributed algorithm that enables agents to collectively traverse an unknown, possibly cyclic graph. Agents enter sequentially at a designated start node and are tasked to localize and reach an undisclosed goal while avoiding collisions. They coordinate via local communication using leader-follower relationships and leader switching. At any moment in time, exploration is performed by only one of the agents, which runs a single-agent maze solver. We prove that the algorithm is complete, that its makespan is asymptotically equivalent (in the number of agents) to that of an optimal full-knowledge strategy, and derive its time and space complexity. Simulations with up to $625$ agents show a decreasing average sum-of-fuels as the number of agents increases and demonstrate that the proposed approach outperforms a naïve baseline in which all agents independently execute the single-agent solver.
Read the full abstract

All authors Julian Rau, Jahir Argote-Gerald, Grace McFassel, Genki Miyauchi, Paul Trodden, Roderich Groß

Numerical Analysis

Fast eight-order Pade schemes based on Chebyshev polynomials for direct Zakharov-Shabat problem

In this work, we construct fast eighth-order Pade schemes for the direct Zakharov-Shabat scattering problem. The schemes are based on an eighth-order exponential integrator obtained from the Magnus expansion. A direct extension of the conventional fast Pade representation to the eighth-order case leads to insufficiently accurate fast variants in the considered tests. To overcome this difficulty, we reformulate the spectral dependence on a finite real interval using the Joukowski mapping and represent the local numerators and denominators in the Chebyshev polynomial basis. This makes it possible to construct the global transition matrix by a fast product tree while retaining a compact polynomial representation. Numerical experiments for chirped hyperbolic secant potentials with both signs of dispersion show that the proposed Chebyshev-based fast schemes substantially improve the accuracy of the corresponding direct fast variants and can be used for efficient computation of the continuous nonlinear spectrum.
Read the full abstract

All authors Sergey Medvedev, Igor Chekhovskoy, Irina Vaseva, Mikhail Fedoruk

Computers and Society

Benchmark-Based Comparative Assessment of Publicly Benchmarked Indian Foundation Models: A Capability and Evaluation-Maturity Framework

Purpose: Governments increasingly fund indigenous foundation models to strengthen national AI capability, digital sovereignty, and multilingual computing. This paper assesses India's foundation-model ecosystem and examines whether apparent capability gaps in public benchmark evidence may also reflect gaps in evaluation maturity. Approach: The paper presents a structured, benchmark-based comparative assessment of Indian foundation models against global frontier and comparable-scale models across eight capability domains: general-purpose reasoning, coding and software engineering, agentic AI and computer use, cybersecurity, vision and image understanding, video and multimodal understanding, scientific research, and Indic language capability. Using only publicly reported results, it proposes an exploratory four-dimension Benchmark Maturity Index (BMI), scoring each domain on standardization, participation, independent verification, and national Findings: Indian models achieve strong scores on established benchmarks such as MMLU and MATH-500. However, these are now widely regarded as saturated, and frontier developers no longer report them. Indian models participate far less frequently in newer, agentic, and domain-specialized evaluations, and participation is highly uneven across organizations. Sarvam AI reports the broadest coverage by a substantial margin. The BMI refines, and in some cases revises, the maturity judgments a purely descriptive review would produce. Practical implications: Many apparent capability gaps cannot be distinguished, on available evidence, from evaluation-ecosystem gaps, with direct implications for how national AI programs should design monitoring and funding criteria. Originality: The paper proposes BMI as a reusable instrument for scoring evaluation-ecosystem maturity at the domain level and demonstrates its application to the Indian foundation-model ecosystem.
Read the full abstract

Databases

DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation

Prompting-based (i.e., non-fine-tuning) Text-to-SQL methods, where underlying large language model parameters are not changed for the task, face three problems: (i) relying on coarse-grained schema information that may not reveal the fine-grained relationships needed to distinguish ambiguous columns, (ii) failing to capture recurring SQL-generation failures, and (iii) suffering from omission or hallucination of components in complex questions. This paper develops DexterSQL, a prompting/non-fine-tuning-based Text-to-SQL system that improves SQL generation with three novel components: (i) deep schema explorator that identifies ambiguous columns, analyzes their individual and joint data distributions to uncover their relationships and the distinct role of each, (ii) database-agnostic rule creator that mines mismatches between generated and gold SQL only on the training database and converts them into database-agnostic corrective rules that capture recurring LLM failure patterns; and (iii) multi-path SQL generation that introduces a dependency-tree-based intermediate representation that uses the question's sentence structure to guide its decomposition into an SQL skeleton for final SQL generation. DexterSQL achieves a higher accuracy compared to the state-of-the-art using both open-source/weight and closed-source/weight models. Particularly, DexterSQL shows a high improvement of at least 5.5% using an open-weight model (GPT-OSS-120B) on BIRDDev, with total accuracy 70.4%. DexterSQL also shows better improvement of at least 1.4% using closed-weight models, with total accuracy 72.1% and 72.9% on BIRD-Dev with GPT-4o and GPT-5.2.
Read the full abstract

All authors Anik Pramanik, Murat Kantarcioglu, Vincent Oria, Shantanu Sharma

Artificial Intelligence

Agent Skills Can Be Harmful: An Empirical Study of Skill-Induced Failures in LLM Agents

Agent skills are the de facto mechanism for extending LLM agents with reusable guidance. A skill can shape the agent's task execution, including planning, tool use, problem-solving, and validation. Prior work reported mixed results of agent skills: some skills improve task success rates, while others have no effect, increase token use and execution time, and even reduce success rates. This paper presents a comprehensive analysis of skill-induced agent failures by attributing task failures and cost regressions to specific loaded skills. We introduce a differential analysis framework that attributes a failure or regression to a skill by comparing a target skill-guided run against a no-skill or semantically matched skill reference run that solves the same task, or solves it more cheaply. We instantiate this framework on SkillsBench and SWE-Skills-Bench, yielding 307 skill-induced failures, including 125 functional failures and 182 efficiency regressions. We also build SkillTriage, a taxonomy-guided attribution tool that normalizes paired cases, extracts differential evidence, and produces triage reports. Our major findings include: (1) Skill induced functional failures are rarely caused by obviously irrelevant skills; instead, seemingly relevant skills often make the agent incorrectly implement or omit task-required implementation elements. (2) Skill-induced efficiency regressions are not explained by prompt length alone. (3) The largest sources within Excessive Procedure are excessive verification and heavy implementation pipelines, contributing 67 and 30 cases, respectively. This shows that skills often turn validation checklists and construction recipes into mandatory work. Based on our findings, we propose research topics and tooling improvements for safer and more cost-aware skill reuse.
Read the full abstract

All authors Gen Dong, Yanjie Gao, Liqun Li, Tianyin Xu, Yu Hua, Fan Yang

Software Engineering

Testing Deep Learning Library APIs via Cross-Framework Differential Fuzzing

Deep learning libraries underpin many safety- and reliability-critical applications, yet existing API-level testing techniques often rely on intra-library properties or CPU–GPU differential oracles and may miss defects that behave consistently across hardware backends. We present Xamt, a cross-framework differential fuzzing approach for deep learning library APIs. Xamt constructs and tests execution-validated groups of APIs intended to implement equivalent operations across seven libraries. It uses explicit API aliases and parameter-role normalization to construct candidate correspondences and validates them through pairwise execution and a group-level behavioral check on canonical ordinary inputs. The resulting groups are explored using variance-guided differential fuzzing with ordinary, boundary, and non-finite inputs. Crash and inconsistency oracles flag executions exhibiting abnormal termination or inconsistent outputs for subsequent reproduction and analysis. Across the seven libraries, Xamt constructs 676 execution-validated groups containing 2,563 matched APIs. Among these, Xamt identifies 72 independently reproduced discrepancy cases, including 4 crash cases and 68 output inconsistencies. Among the 72 developer reports, 25 have been confirmed, including 23 that have been fixed.
Read the full abstract

All authors Bin Duan, Ruican Dong, Naipeng Dong, Dan Dongseong Kim, Guowei Yang

Artificial Intelligence · Cross-listed from quant-ph

CoQui: A Coordinate-Conditioned Quantum Implicit Generative Adversarial Network for End-to-End Image Generation

Quantum generative adversarial networks (QGANs) have attracted increasing attention for image generation using parameterized quantum circuits. Existing amplitude-based approaches face two key limitations: pixel locations are typically encoded by computational-basis indices or address qubits, causing quantum resources to grow with image resolution; meanwhile, jointly decoding many pixels from normalized quantum states introduces probability competition among pixels and limits precise pixel-wise control. To address these issues, we reformulate quantum image generation as coordinate-conditioned implicit function learning. Our method takes spatial coordinates and latent variables as inputs, uses a classical embedding network to generate input-dependent circuit parameters, and evaluates a variational quantum circuit at each coordinate. Pixel intensities are directly obtained from the expectation value of a dedicated color qubit, and a complete image is generated by querying all spatial coordinates. This design decouples image resolution from address-qubit requirements and avoids shared probability-normalization constraints across pixels. We further design a specialized variational quantum circuit to provide structural inductive bias for coordinate-conditioned generation. Simulated experiments on two benchmark datasets show that our method outperforms FRQI-based generation and PQWGAN in visual and quantitative quality while using fewer qubits, and also achieves better generation quality than the corresponding classical baseline.
Read the full abstract

All authors Xue Yang, Rigui Zhou, ShiZheng Jia, Dax Enshan Koh, Siong Thye Goh, Young-Wook Cho, YaoChong Li, Xuezhi Ma, Hongyu Chen, Xin Wang

Computer Vision

Warping Earth Observations for better ice labeling in the Marginal Marginal Ice Zone

Multimodal satellite imagery provides complementary information for Earth Observation, but accurately combining heterogeneous sensors remains challenging in dynamic environments. Fast-changing regions, such as the Antarctic marginal ice zone, cannot fully exploit multimodal information from different satellite sensors because surface features move between image acquisitions. This spatial and temporal mismatch challenges effective perceptual grounding, violating the assumption of pixel-level correspondence that underpins most multimodal reasoning and downstream classification pipelines. Antarctic sea ice provides a challenging benchmark due to the rapid, heterogeneous drift of individual ice floes and the differing responses of sea ice to radar, visible and thermal sensing modalities. Accurate, dense supervision of sea ice remains scarce because generating pixel-wise labels requires time-consuming expert interpretation of noisy data, leading to historical reliance on coarse-resolution maritime ice charts for model training. This paper presents a novel architecture based on mutual information warping to align multi-satellite (Sentinel-1 and MODIS platforms) multimodal (visible, thermal, radar) satellite scenes. To demonstrate the approach, we introduce a sparse expert-labeled dataset of 2,088 pixel-wise annotations (7,046 expert point classifications) located at the ice-water margin interface across 43 scenes. Our results demonstrate that spatially grounding and aligning modalities prior to segmentation improves classification accuracy, and enables accurate, dense sea ice segmentation from sparse point-wise supervision.
Read the full abstract

Distributed Computing

Evaluating OpenMP Offloading for Intra-node Multi-GPU Programming across NVIDIA, AMD, and Intel Architectures: A 3D Heat Transfer Case Study

Currently, most supercomputers are equipped with GPUs from manufacturers such as NVIDIA, AMD, or Intel, which provide substantial parallelism and high throughput. It is common for a single compute node (intranode) to host multiple GPUs, typically four or more. Therefore, effectively leveraging all these GPUs within a single compute node is essential for applications in scientific and engineering domains. However, several factors must be considered before utilizing these GPUs for scientific computing, including the implementation of data communication, the programming models available for use across these GPUs, and the level of performance that can be achieved with a single codebase across different GPU architectures and configurations within a single compute node. OpenMP Offloading is a prominent directive-based programming model that can be executed on all three GPU types: NVIDIA, AMD, and Intel. In this research, we present an analysis of the benefits and performance challenges of using OpenMP Offloading to address the 3D heat equations, which involve both primary computation, as well as halo computation and communication. For additional comparison and scalability study, we also consider the Conjugate Gradient method. We investigate how performance varies in relation to native GPU programming models-CUDA for NVIDIA, HIP for AMD, and SYCL for Intel. Furthermore, we demonstrate that OpenMP Offloading can achieve performance improvements of approximately 2x for 2 GPUs and around 4x for 4 GPUs when compared to single-GPU OpenMP Offloading implementations across all three GPU types. This analysis is conducted systematically through various OpenMP Offloading implementations that utilize different low-level APIs for memory allocation, memory transfer options (synchronous, asynchronous, and peer-to-peer), and other native GPU programming models such as CUDA(NVIDIA),HIP(AMD),and SYCL(Intel).
Read the full abstract