跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+479新增论文
+361其中 AI 相关
+63已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 13:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 19:54 — 2026-11-16 19:54(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-16 01:34最近发现新增版本:2026-11-16 13:44库内论文最新更新时间:2026-11-14 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

23,827 已收录论文19,941 AI 相关6,921 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 23,827 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2611.12346

ReVMap: Vectorized Global Mapping via Connectivity-Aware Local Map Fusion

Hongjae Shin, Jungho Kim, Donghyuk Kwak, Myeongjun Kim, Seunghoon Yu, Jiyong Oh, Jun Won Choi

原文摘要

Large-scale annotation of vectorized high-definition (HD) maps is labor-intensive and costly, motivating local-to-global auto-labeling approaches that incrementally construct global maps from local vectorized predictions. However, existing approaches often overlook prediction uncertainty and rely on heuristic map integration, potentially propagating errors and introducing topological inconsistencies. To address these limitations, we propose ReVMap, a reliable local-to-global framework that iteratively refines local map predictions and global map construction through uncertainty-guided prior utilization and connectivity-guided global map revision. Specifically, ReVMap leverages point-wise localization uncertainty to incorporate global map priors into local map prediction, improving robustness against inaccurate prior information. It then predicts local-to-global connectivity and selectively updates the global map through uncertainty-aware fusion based on the reliability of local predictions. By iteratively coupling local prediction and global revision, ReVMap progressively improves both local map accuracy and global map consistency. Extensive experiments on the nuScenes and Argoverse 2 benchmarks demonstrate that ReVMap achieves state-of-the-art performance in both local map prediction and global map construction.

cs.CV

新论文 · v1arXiv:2611.12345

TMT: Adapting CLIP to Infrared Imagery via Text-Derived Modality Knowledge Transfer

Ruofan Wang, Puzuo Wang, Xin Chen, Zibo Yu, Jungang Yang, Yi Hou

原文摘要

Vision-language models such as CLIP achieve strong performance across computer vision tasks, yet their image-text alignment is less reliable for infrared (IR) imagery because large-scale pre-training is dominated by visible-spectrum data. Due to the high cost of the infrared-text labeling, we investigate adapting CLIP to IR through only paired infrared-visible images, which requires considering modality-specific knowledge while preserving scene content and CLIP's image-text alignment. To achieve this, we propose TMT (Text-Derived Modality Knowledge Transfer), which adapts CLIP's image encoder through a text-defined infrared-to-visible direction and supervision from paired IR-visible images. First, we found that modality discrepancy can be described by corresponding text embeddings, thus using the direction of text embedding differences to guide the knowledge transfer between visible and infrared modalities without erasing infrared-specific information. To enhance the representation of semantics and details of infrared images, we introduce Generative-Perceptual Co-Supervision that combines semantic alignment from CLIP visible image encoder with diffusion noise-prediction feedbacks. On four source-disjoint IR classification benchmarks, TMT achieves the highest mean zero-shot accuracy among the compared methods (48.92%). It also achieves the best IR-text retrieval results among the compared methods without infrared-text supervision during adaptation and the highest open-vocabulary segmentation mIoU on both CART and SemanticRT among the CLIP-like methods.

cs.CV

版本更新 · v2arXiv:2611.09309

Interpretable Context-Aware Multi-Label Retinal Classification with Dual-Hub Heterogeneous Graph Neural Network

Proshanto Chanda, Munib Mesinovic, Tingting Zhu, Abhirup Banerjee

原文摘要

Multi-label retinal screening requires capturing co-occurring pathologies and clinical context, yet standard multimodal fusion remains opaque. We propose a dual-hub heterogeneous graph neural network (GNN) that couples spatial fundus features and structured clinical covariates through cross-modal message passing while providing inherent interpretability. Rather than relying on post-hoc saliency approximations, our architecture exposes multi-level decision pathways during forward aggregation: spatially biased self-attention captures lesion-level patch interactions, while modality-specific graph attention coefficients explicitly quantify the contribution of visual regions and clinical risk factors to each disease node. Evaluated on the BRSET dataset (16,266 photographs from 8,524 patients), the proposed model achieves 76.1% Macro-AUPRC across seven conditions, matching or exceeding image-only (75.9%) and ResNet-50+MLP fusion (75.9%) baselines, with largest contextual gains in macular edema (+3.5 percentage points, pp) and diabetic retinopathy (+2.1 pp). Codebase is available at: https://github.com/proshanto-c/ca-mlc-refactor.

cs.CV · cs.LG

版本更新 · v2arXiv:2608.06875

QCORE: A Quantum-Computing-Oriented,Resource-Efficient Runtime Architecture with Lifecycle Coordination

Heyue Li, Shaolin Xiang, Tian Tian, Qichun Liu, Tiefu Li, Zhihua Wang, Yanshu Guo, Hanjun Jiang

原文摘要

As quantum processors scale, online calibration, quantum error correction (QEC), and measurement-driven feedback require continuous classical processing and parameter updates. Sharing on-chip resources reduces hardware cost, but computation completion, the last parameter read, and result consumption occur at different times. Their dependencies must be managed separately while preserving quantum operations' real-time requirements. We present QCORE, a quantum-computing-oriented, resource-efficient runtime architecture that coordinates these lifecycles for safe resource reuse and parameter consistency. QCORE models resource occupancy, parameter protection, and consumer dependencies as independent lifecycles and provides three mechanisms: pre-use checks and parameter binding to verify timing, identity, and dependencies; access-aware protection through value snapshots, version references, or active-configuration windows; and joint admission of resource reservations and parameter installation. After request submission, hardware autonomously handles admission, protection, installation, and reclamation, reducing fine-grained Host coordination and providing a foundation for one Host to manage multiple controllers. We implement synthesizable RTL and validate FPGA timing at 100 MHz. Independent release reduces whole-program execution time by 16.83% in Ramsey calibration and QEC replay. Joint admission increases on-time completions from 5/15 to 15/15 under contention across five arrival phases. Under identical external deadlines, a shared NN backend reduces LUT usage by 12.28%-13.81% and DSP usage by 39.39% compared with two statically assigned backends. These results show that lifecycle coordination exploits inter-task timing slack for on-chip sharing, increasing service capacity under limited resources.

quant-ph · cs.AR

版本更新 · v2arXiv:2506.20267

X-SiT: Inherently Interpretable Surface Vision Transformers for Dementia Diagnosis

Fabian Bongratz, Tom Nuno Wolf, Jaume Gual Ramon, Christian Wachinger

原文摘要

Interpretable models are crucial for supporting clinical decision-making, driving advances in their development and application for medical images. However, the nature of 3D volumetric data makes it inherently challenging to visualize and interpret intricate and complex structures like the cerebral cortex. Cortical surface renderings, on the other hand, provide a more accessible and understandable 3D representation of brain anatomy, facilitating visualization and interactive exploration. Motivated by this advantage and the widespread use of surface data for studying neurological disorders, we present the eXplainable Surface Vision Transformer (X-SiT). This is the first inherently interpretable neural network that offers human-understandable predictions based on interpretable cortical features. As part of X-SiT, we introduce a prototypical surface patch decoder for classifying surface patch embeddings, incorporating case-based reasoning with spatially corresponding cortical prototypes. The results demonstrate state-of-the-art performance in detecting Alzheimer's disease and frontotemporal dementia while additionally providing informative prototypes that align with known disease patterns and reveal classification errors.

cs.GR · cs.CV · cs.LG

新论文 · v1arXiv:2611.12339

Evidence or Marginal? What Moment-Vector Propagation Computes in Polynomial Density Neurons

Przemysław Spyra

原文摘要

When a neuron's input is lost, or known through a belief $q$, what should it output? For a neuron storing a joint polynomial density $N$ with input density $D$, two formulas compete. $p_\mathrm{CD}=E_q[N]/E_q[D]$ costs one matrix-vector product; Hierarchical Correlation Reconstruction introduces it as a constant-denominator approximation to $p_\mathrm{EU}=E_q[N/D]$. For a density model both are exact answers to different questions: $p_\mathrm{CD}$ is Bayesian updating with the belief as virtual evidence; $p_\mathrm{EU}$ installs the belief as a new marginal (Jeffrey's rule). With a missing input $p_\mathrm{CD}$ returns the model's conditional; $p_\mathrm{EU}$ generally does not. This post hoc reading is proved, and illustrated outside the pair family up to $k=8$ inputs; it has no pre-registered test, only one exploratory real-data pilot. Post hoc, closed forms fall within a factor 2 of all 112 measured gaps, and negative density begins near input correlation $1/k$. In a pre-registered synthetic study (up to 32 inputs), 5 of 15 hypotheses are supported, 2 inconclusive and 8 not supported, including all three on transfer beyond equicorrelated Gaussians. Post hoc, where $p_\mathrm{EU}$ is defined, truncation usually outweighs the gap for Beta beliefs in pair neurons; triple neurons under flat and data beliefs are exceptions.

cs.LG · cs.AI

新论文 · v1arXiv:2611.12338

From Formal Methods to Fuzzing and Back

Alastair F. Donaldson

原文摘要

For the first twelve years of my career in computer science I mainly worked on formal methods. I had been drawn to the field as an undergraduate by its promise of a way to build software with strong, mathematically based correctness guarantees. But after many years of struggling to make formal methods scale, I was seduced by randomised testing---also known as fuzzing. Fuzzing is much less principled than formal methods, but it just works: it can be readily applied to very large systems, and it is extremely effective at finding real bugs that developers care about and fix. In this personal account I trace my path from formal methods to fuzzing, by way of the GPUVerify project on verifying GPU kernels and the GraphicsFuzz project on randomised testing of GPU compilers. I argue that the oracle problem provides an intellectual link between fuzzing and formal methods, describe my continuing, targeted uses of formal methods in the domain of GPU programming language design, and discuss work at the boundary between formal methods and fuzzing. Finally, I reflect on whether generative AI might be the missing ingredient that allows formal methods to scale, and set out my plans for large-scale formal methods via the Keystone project, through which my collaborators and I aim to find out how much of that promise can be realised in practice.

cs.SE

新论文 · v1arXiv:2611.12337

From LLM Hallucinations to Inspiration in Creative Work

Xinrui Lin, Heyan Huang, Shuning Zhang, Qi Wang, Youchao Zhou, John Vines

原文摘要

Large language models (LLMs) can introduce unexpected ideas through hallucinations, yet little is known about when creative practitioners find these errors inspiring or how these judgments shape interactions. We conducted a retrospective qualitative study with 20 experienced practitioners in research, design, and social media content creation, thematically analyzing 41 hallucination cases and 20 semi-structured interviews. Our framework links inspiration judgments of hallucinations based on goal relevance, task stage, content adaptability, and type-specific factors to behaviors across not-inspired, inspired-by, and inspired-to states. We characterize downstream interaction consequences, showing how hallucination-inspired experiences vary across creative stages and reshape role-differentiated trust, and propose these consequences as a dimension of hallucination evaluation. Finally, we derive design recommendations for stage-sensitive control of divergence and adherence, user-defined constraint priorities, differentiated hallucination labels, and salvage support for preserving useful ideas while correcting errors. These contributions deepen HCI understanding of hallucinations and responsible LLM design in creative work.

cs.HC

新论文 · v1arXiv:2611.12334

Rethinking Radar 3D Perception: Representation Learning from Raw Spectra

Miao Zhang, Mohamed Abdelsamad, Bin Yang, Sherif Abdulatif, Benedikt Loesch, Marco Altmann, Abhinav Valada, Bin Yang

原文摘要

Raw radar spectra are widely viewed as too cluttered and noisy for direct representation learning, motivating handcrafted reductions, sparse point clouds, or compact Doppler descriptors in radar perception. We challenge this assumption and argue that the main limitation lies not in the raw representation itself, but in the absence of a learning objective that separates structured signal from noise. Handcrafted reductions partially address this problem but impose rigid assumptions about what constitutes signal, discarding weak yet informative structure while retaining artifacts that fit the reduction model. Once removed, such information cannot be recovered by supervised learning. We propose an alternative: structure is the component of a radar spectrum that remains reconstructable under localized corruption, while noise is the component that does not. This perspective motivates self-supervised masked modeling for dense radar spectra without predefined signal-noise separation. We instantiate it with Leakage-aware Spectral MAE, a masked autoencoder for raw radar cubes using a corruption strategy inspired by cross-bin energy spreading caused by spectral leakage. We also demonstrate the importance of Doppler organization: treating Doppler as a primary spatial dimension in an x-y-D representation, with height encoded as features, substantially outperforms naive channel stacking and enables effective learning from dense 4D spectra. Without handcrafted reductions, our approach consistently outperforms state-of-the-art radar-based detectors and point-cloud-based self-supervised learning (SSL) counterparts. These results establish raw radar spectra as an effective representation for 3D perception when paired with an appropriate pretraining objective.

cs.AI · cs.CV · cs.LG · cs.RO

新论文 · v1arXiv:2611.12333

AMSchem: Automated Schematic Visualization of AMS Circuits via Verifiable Agentic Generation

Yichen Shi, Zhiyuan Wang, Jianing Cui, Yao Lai, Jinting Zhang, Zhuofu Tao, Hongyang Wang, Zhiping Yu 等 10 位作者

原文摘要

For decades, the netlist-to-schematic gap has remained a persistent challenge in design automation, especially for analog and mixed-signal (AMS) circuits. Netlists encode connectivity, not visual presentation, making their manual conversion into readable schematics time-consuming and dependent on expert conventions. The same gap leaves LLM-based design tools without structured visual feedback, forcing them to iterate on circuits they cannot see. We present AMSchem, a training-free, verifier-guided agentic framework that automatically generates human-readable schematics from AMS netlists. AMSchem separates circuit-aware visual planning (DrawingIntent) from executable schematic geometry (SchematicIR), and applies localized visual feedback with bounded, revalidated repair patches. Deterministic validators enforce device preservation, pin-net consistency, and geometric correctness throughout. For evaluation, we construct AMSchem-Bench comprising 64 circuits of 12 types. On the 40-circuit schematic subset, AMSchem with gpt-5.5 achieves 85.0\% validity (vs. 32.5\% direct generation). When integrated as a visual feedback module in LLM-based analog design, AMSchem resolves all 13 previously failed cases from AnalogCoder benchmark across five models, substantially improving the success rate. Our dataset and benchmark are available at https://www.amschem.com/benchmark

cs.AI

新论文 · v1arXiv:2611.12332

Do Machine Learning Models Predict?

Michele Pizzochero, Emanuele Ratti

原文摘要

Machine learning (ML) models are said to predict. Philosophers draw a line between accommodation and prediction, depending on whether or not the evidence a theory succeeds on was used in constructing it. Does this distinction survive when a theory is replaced by an ML model? We argue so, yet the dividing line becomes fuzzy. Whether an output of an ML model counts as an accommodation or as a prediction hinges upon the relationship between the patterns the input instantiate and those on which the model was selected through its training. Once this relation is taken into account, most successful outputs of ML models, we suggest, bear a strong accommodation character. We further trace the consequences of our account for confirmation, novelty, and scientific realism.

cs.CY · cs.AI

版本更新 · v3arXiv:2609.15825

Sharp Regret Bounds and a Task-Covariance Correction for Spectral Representation Learning

Dier Tang, Jing Yee Tan, Guangyue Han

原文摘要

Spectral contrastive learning keeps the $k$ directions along which two views of the data depend most strongly, while downstream tasks may need other directions. Existing guarantees for spectral features assume that the distribution of tasks has no preferred direction. We show that this isotropy condition is the wrong criterion. With linear probing, the task distribution affects the average probing gain only through the matrix $BΛB^\top$, where $B$ records the dependence between views and $Λ$ is the task covariance: optimal features span its top-$k$ eigenspace, whereas spectral features span that of $BB^\top$. Transfer therefore depends on alignment, and strongly uneven task preferences cost nothing when they favour the spectral directions. Otherwise the regret of spectral features is at most linear in the anisotropy of $Λ$. No representation chosen without task information improves this rate when the leading spectrum is flat, and a spectral gap makes it quadratic. With labelled tasks, the same matrix gives a correction: Fisher discriminant directions for a frozen encoder, or a one-term change to the spectral contrastive loss. We bound the regret of the correction by the error in estimating $BΛB^\top$, and compare this error with the misalignment of spectral features to decide when to correct. The analysis extends to finite samples, continuous variables and noisy views. Correction reduces synthetic held-out regret from $0.858$ to $0.003$ with $2000$ labelled tasks, and the decision rule gives the lowest regret among the tested rules at every bank size. On CIFAR-100, spectral features of frozen encoders keep most of the task signal on unseen classes, and where a bank of other classes would lower accuracy, the rule keeps them in every case.

cs.LG · cs.IT · stat.ML

新论文 · v1arXiv:2611.12330

Cut Conditions, Integrality, and Obstructions for Directed Multiflows

Srinwanti Debgupta, Martin Skutella, Philipp Warode

原文摘要

In contrast to the max-flow/min-cut theorem for single-commodity flows, the cut condition is necessary but not sufficient for the existence of directed multiflows, even with only two commodities. Poremba and Shepherd (IPCO 2023) conjecture that the cut condition is sufficient for all capacities and demands on a directed two-commodity topology if and only if it contains neither of two specific topologies as a relevant minor. We prove this conjecture. As a consequence, the fractional and integral flow-cut gaps of every directed two-commodity topology coincide and are either 1 or 2. We then investigate stronger necessary conditions for multiflow feasibility and their implications for integrality. We introduce a hierarchy of five conditions, ranging from the classical cut condition through conditions based on blocking edge sets and binary edge lengths to the linear programming dual characterization of fractional feasibility. The corresponding classes of sufficient topologies are strictly nested. We extend the Nagamochi-Ibaraki theorem: whenever one of the first four conditions is sufficient on a topology, integral capacities and demands satisfying that condition admit an integral multiflow, computable in polynomial time. Finally, we prove that recognizing topologies on which any of these four conditions is sufficient is coNP-complete, even for two commodities.

math.CO · cs.DM

新论文 · v1arXiv:2611.13046

SpatialSR: Spatial Resolution-Centric Pipeline for Arbitrary-Scale Remote Sensing Super-Resolution

Yan Zhang, Runfeng Luo, Liangke Gao, Lin Yuan, Bin Xiao, Xinbo Gao

原文摘要

Although remote sensing image arbitrary-scale super-resolution (RSI-ASSR) methods support reconstruction at arbitrary or continuous scales, they predominantly condition on the relative scale factor and have not sufficiently investigated the absolute spatial resolution itself as a reconstruction prior, thereby disregarding the inherent spatial context of objects, which frequently leads to spatial-related distortions and compromised performance in downstream remote sensing applications. To address these challenges, we introduce SpatialSR, a SRe-centric arbitrary-scale RSISR method that leverages the spatial resolution (SRe) of remote sensing images (RSI) as an essential prior for super-resolution reconstruction. Distinct from existing SR methods, SpatialSR aims to restore high-resolution remote sensing images with a target SRe (typically set to 0.1m/pixel to align with the metadata of commonly used downstream task datasets). Specifically, we design a Spatial Resolution Estimation Module (SREM) to estimate the SRe of low-resolution (LR) images, thereby dynamically determining the required arbitrary scaling factor. Next, we employ a pretrained SRe-to-image diffusion model to extract SRe-specified texture-style codes, which are further incorporated into a carefully designed Resolution-aware Style Consistency Module (RSCM) to constrain the SRe-aware texture consistency of reconstructed images. Furthermore, to overcome the high computational expense inherent in diffusion-based SR methods, we wrap the iterative diffusion process as a Trajectory Consistency (TC) loss, which enables comparable reconstructed texture quality of the generative model in SpatialSR within a single step. Extensive experiments demonstrate that the proposed SpatialSR achieves state-of-the-art (SOTA) performance on commonly used RSISR and downstream (image classification and segmentation tasks) datasets.

cs.CV

新论文 · v1arXiv:2611.12326

Tensor Network Kernel Machines for Nonlinear System Identification

Kim Batselier

原文摘要

Over the past ten years Tensor Network Kernel Machines have enabled efficient nonlinear system identification through the use of low-rank tensor networks. The goal of this article is to provide the reader with a basic understanding of this model class in terms of its two defining properties. Furthermore, both the optimization and regularization of such models are discussed, together with recent developments and starting points for further exploration.

eess.SY · cs.LG · math.OC

版本更新 · v2arXiv:2606.05107

Who Needs Labels? Adapting Vision Foundation Models With the Metadata You Already Have

Elouan Gardès, Seung Eun Yi, Kartik Ahuja, Théo Moutakanni, Huy V. Vo, Piotr Bojanowski, Wolfgang M. Pernice, Loïc Landrieu 等 9 位作者

原文摘要

We propose a label-free approach to adapt powerful but generic vision foundation models to specialized scientific domains. Standard supervised fine-tuning is often ill-suited to these settings: labels are scarce, and task-specific training can reduce the generality needed to cope with complex domain shifts. We instead leverage metadata to adapt representations to new domains in a weakly-supervised manner. Our method, FINO, combines a standard self-supervised objective with flexible metadata guidance that handles both highly granular discrete metadata and continuous metadata. It encourages the representation to preserve informative factors while suppressing spurious ones. Across subcellular fluorescence microscopy, Earth observation, wildlife monitoring, and medical imaging, FINO outperforms matched self-supervised and fully supervised adaptation baselines. Complete-adaptation repeats confirm consistent performance across domains. Without task labels for backbone adaptation, FINO also obtains higher reported scores than selected specialised systems on three domains and matches the fourth under differing cross-paper protocols. Code is available at github.com/facebookresearch/dinov3/tree/FINO.

cs.CV · cs.AI

版本更新 · v2arXiv:2606.27895

Mosaic: A Benchmark Suite for Differentiable Physics Solvers

Andrin Rehmann, Heiko Zimmermann, Dion Häfner

原文摘要

Differentiable partial differential equation (PDE) solvers underpin solver-in-the-loop MLtraining, gradient-based optimal control, and inverse problems, yet the practical cost of obtaining correct, usable gradients from a given solver on a given problem is largely undocumented. Integration effort, computational cost, memory, gradient accuracy, and numerical stability vary widely across solvers and are discoverable only by trial and error. We introduce Mosaic, an extensible benchmarking framework for differentiable PDE solvers that standardizes access to solver gradients. Each solver is packaged as a containerized component (Tesseract) exposing a uniform gradient API regardless of language or automatic differentiation (AD) strategy, enabling researchers to evaluate, compare, and build on non-trivial physical solvers. Our evaluation of 14 solvers across fluid dynamics, structural mechanics, and heat transfer demonstrates that the benchmark surfaces practically relevant differences: order-of-magnitude variation in computational cost and memory, alongside setup incompatibilities and instabilities that rule out solvers for specific tasks. Despite this variation, all solvers that produce gradients converge to similar optima on our tasks, indicating that the practical barriers are memory limits, numerical stability, and setup compatibility rather than gradient accuracy alone. Mosaic is open-source and available at github.com/pasteurlabs/mosaic.

physics.comp-ph · cs.LG

新论文 · v1arXiv:2611.12325

An Explicit Below Half Threshold Bound for the Local Leakage Resilience of Shamir's Secret Sharing Scheme

Cheng Zhang, Xin Wang, Xiangliang Kong

原文摘要

As a fundamental cryptographic primitive, secret sharing distributes a secret among multiple parties and allows certain authorized parties to recover the secret while preventing unauthorized parties from knowing the secret. However, local leakage from each party member allows an adversary to learn partial information from each share, which is not guaranteed by traditional security. In this paper, we study bounds on the reconstruction threshold of Shamir's secret sharing scheme over prime fields against arbitrary 1-bit local leakage. We show that, for all sufficiently large $n$ and every prime $p>n$, the $(n,t)$-Shamir's scheme is $\exp(-Ω(n))$-resilient whenever $t/n\geq 0.489$, for any choice of distinct nonzero evaluation points. Our proof refines the dual-code list recovery analysis and combines complementary Fourier estimates according to the support sizes and biases of the leakage functions, yielding an improved explicit reconstruction threshold bound.

cs.CR · cs.IT

版本更新 · v2arXiv:2611.09377

KineCouple: Substrate-conditioned residual readout for enzyme kinetic prediction

Chun Kang, Yunbo Zhang, Fanhu Zeng, Jian Liu, Siwei Deng, Lei Sha

原文摘要

Accurate prediction of enzyme kinetic parameters can support enzyme engineering and metabolic modeling by complementing experimental characterization. Existing prediction methods often pool residue-level protein features before combining them with substrate features. Such substrate-independent pooling cannot adapt residue weighting to the substrate during aggregation, potentially diluting information relevant to a specific enzyme-substrate pair. Since the contributions of individual residues to catalysis can depend on the substrate, substrate-conditioned aggregation offers a way to emphasize residue features relevant to the prediction. We introduce KineCouple, which uses substrate queries and residue-level keys and values in cross-attention, allowing the substrate to guide residue selection before aggregation. The model preserves the global protein representation and adds a gated correction defined as the difference between the conditioned readout and a uniform readout. ProtT5 and MolT5 remain frozen, and separate models predict kcat and Km on a logarithmic scale. In pooled out-of-fold predictions on the CataPro benchmarks, KineCouple reduces kcat RMSE from 1.333 to 1.330 and increases PCC from 0.492 to 0.496 relative to reproduced CataPro. For Km, RMSE decreases from 0.998 to 0.997 and PCC increases from 0.633 to 0.634. Spearman correlation also improves for both tasks.

cs.AI · q-bio.QM

新论文 · v1arXiv:2611.13045

MICRO: A Surgery-Phase Retinal Image Rigid Registration Benchmark and One-Step Frequency-Structure Similarity Registration Learning

Mingdao Gong, Yan Hu, Mingzhen Yuan, Jialu Zhang, Junming Feng, Yiming Jiang, Jing Ma, Jinghua Liu 等 12 位作者

原文摘要

Precise multimodal retinal image rigid registration (MRIRG) is essential for aligning cross-modal vessel structures, offering critical guidance for ophthalmic surgery. Despite its significance, the advancement of MRIRG is hindered by the lack of publicly available multimodal retinal image rigid registration datasets spanning various ophthalmic surgery phases (e.g., preoperative, intraoperative, and postoperative). To address this issue, we introduce the MICRO dataset, a large-scale MRIRG benchmark, comprising 1,365 cross-modal retinal image pairs with standardized annotations across all ophthalmic surgery phases. Moreover, existing deep registration methods achieve competitive MRIRG results via a two-step segmentation-then-detection framework, but segmentation quality heavily constrains their performance. We argue that this dependency stems from an implicit need for keypoint topology constraints, which have not been exploited for MRIRG through a one-step registration framework. Inspired by the above analysis, we propose a novel One-step Frequency-Structure Similarity Registration (OFS2Reg) learning framework for MRIRG that leverages the potential of cross-modal vessel structure similarities to construct keypoint topology constraints under a shared detection network. To be specific, OFS2Reg applies a well-designed frequency-guided structure preservation descriptor to construct coarse keypoint topology constraints in descriptors by highlighting significant vessel structures. Additionally, we develop a new cross-modal vessel structure similarity learning method that refines cross-modal keypoint topology constraints to precisely align pixel-level cross-modal vessel structures by leveraging cross-modal vessel structure similarity priors.

cs.CV

新论文 · v1arXiv:2611.12324

How Many Exposures Does a World Model Need? Learning Unseen Game Mechanics at Test Time

Ku Onoda, Haruto Kawano, Shota Takashiro, Kohei Hayashi

原文摘要

World models enable agents to plan and learn from imagined experience, but in an unfamiliar environment they must learn its mechanics from limited interaction. A mechanic is a rule for how an action or an interaction changes part of the environment. Each occurrence of a mechanic that the model observes is one exposure. We ask how many exposures a world model needs to predict the effects of a new environment's mechanics. We address this question on ARC-AGI-3, a benchmark of interactive games defined by their programs. We introduce MechEval, which labels 69 recurring mechanics across 20 games from these programs. It scores each prediction on the cells the mechanic changes at each exposure. As a test bed, we build WARC (World model for ARC-AGI-3), a 35M-parameter vision transformer that is pretrained on other games and updates all of its parameters after each transition. On held-out games, WARC learns to predict four in five mechanics with at least 80% accuracy on the cells they change and keeps that accuracy to the end of the recordings. Half of them reach that accuracy within about 80 exposures, in a single play of the game, and without updates only one in seven does at all. In closed-loop play on the public games, WARC-Agent, which pairs WARC with a fixed graph explorer, triples the explorer's official efficiency score from 0.15 to 0.46, mostly through test-time training. On the hidden games of the Kaggle leaderboard, our entry scores 0.20.

cs.LG · cs.AI · cs.CV

新论文 · v1arXiv:2611.12321

Strong Backdoor to Forests is FPT: Tight Linear-Time FPT for Essentially General SAT

Olesia Bilyk, Aidar Munduzbaev, Roohani Sharma, Mamnoon Siam

原文摘要

In a seminal work, Gaspers and Szeider [FOCS 2013] gave a fixed-parameter tractable (FPT) approximate algorithm for finding a strong backdoor of size at most $k$ to incidence treewidth at most $t$, for a given CNF-formula $φ$. In particular, their algorithm runs in $f(k,t) |φ|^3$ time, and finds a strong backdoor to treewidth at most $t$, of $φ$, of size at most $2^k$ whenever there exists one of size at most $k$. Determining whether the detection of strong backdoors to bounded incidence treewidth is FPT parameterized by $k+t$ was left open in their work and this has been repeatedly posed as an open question by Gaspers and Szeider, for example in [The Multivariate Algorithmic Revolution and Beyond 2012] and more recently in [Computer Science Reviews 2025], even for incidence forests and when the input is a $3$-CNF formula. We answer this question affirmatively. We show that strong backdoors to forests can be found in linear-FPT time on arbitrary non-tautological CNF formulas (not just on 3-CNF formulas). Given such a formula $φ$ and a budget $k$, our algorithm finds a strong backdoor to the class of forests, of size at most $k$, or correctly reports that none exists, in $2^{2^{O(k)}} |φ|$ time. Moreover, we show that our result is as tight as it can get. First, we show that finding strong backdoors to treewidth $t$ for any $t \geq 2$ is W[1]-hard, even on non-tautological 3-CNF formulas. Second, the running time of our algorithm is tight: it is linear in the input size and a better than double-exponential dependence on $k$ in the running time would imply a $2^{o(N/\log N)}$-time algorithm for solving 3-SAT on $N$ variables, which would beat even the very recently claimed sub-exponential algorithm for solving 3-SAT by OpenAI and Anthropic.

cs.DS · cs.CC

新论文 · v1arXiv:2611.12319

Mitigating SM-Level Load Imbalance in 3D Gaussian Splatting on GPUs

Junha Ryu, Hoi-Jun Yoo

原文摘要

3D Gaussian Splatting (3DGS) enables photorealistic, real-time rendering on commodity GPUs and is increasingly adopted in generative world models and autonomous driving simulators. However, existing optimizations rely on algorithmic changes that often require retraining, or on specialized accelerators that lack flexibility across evolving 3DGS variants. In this paper, we identify a fundamental inefficiency in GPU-based 3DGS rendering: severe SM-level load imbalance caused by uneven workloads across screen tiles. This imbalance creates a long execution tail, leaving most SMs idle while a few process computationally intensive tiles, particularly in large-scale urban scenes. To address this, we present a software-defined GPU scheduling approach that mitigates the execution tail. Our approach uses a persistent kernel to schedule heavy tiles first and selectively chunks outlier tiles across multiple CTAs. A lightweight per-frame policy determines when and how much to chunk using tile statistics already available in the rendering pipeline. Our approach requires neither retraining nor specialized hardware and can be applied orthogonally to existing optimizations across diverse 3DGS variants. Averaged per scene, it accelerates alpha blending by up to 2.93x on a large-scale urban scene, and by up to 5.6x on its most imbalanced frames, while retaining the original alpha blending formulation.

cs.DC · cs.CV · cs.GR · cs.LG

版本更新 · v7arXiv:2409.15955

A Historical Trajectory Assisted Optimization Method for Zeroth-Order Federated Learning

Yu Cai, Canxi Huang, Zike Li, Jing Gong, Xiaoyu He

原文摘要

Federated learning heavily relies on distributed gradient descent techniques. In the situation where gradient information is not available, the gradients need to be estimated from zeroth-order information, which typically involves computing finite-differences along isotropic random directions. This method suffers from high estimation errors, as the geometric features of the objective landscape may be overlooked during the isotropic sampling. In this work, we propose a non-isotropic sampling method to improve zeroth-order gradient estimation. The method uses historical solution trajectories to identify a promising subspace and constructs a non-isotropic Gaussian smoothing that balances exploitation in this subspace with global exploration. We implement this method in zeroth-order federated settings, and show that the convergence rate aligns with existing ones while introducing no significant overheads in communication or local computation. The effectiveness of our proposal is verified on several numerical experiments in comparison to several commonly-used zeroth-order federated optimization algorithms. The experiments cover both independent and identically distributed data and heterogeneous client data distributions.

cs.LG · cs.AI

新论文 · v1arXiv:2611.12317

Maximizing Detection Probability in UAV Search Missions using Random-Key Optimizers

Antonio Dantas, Elcio Shiguemori, Antonio Chaves

原文摘要

This paper focuses on the stochastic and real-time constraints of Unmanned Aerial Vehicle (UAV) path planning in Search and Rescue (SAR) missions. We introduce a configurable data-driven and intelligent routing architecture that combines a closed-loop probability update with the Random-Key Optimizers (RKO). Our problem is mathematically modeled as a dynamic probabilistic variant of the Open Vehicle Routing Problem (OVRP), enabling the solver to switch adaptively between two objectives, thereby balancing probability maximization and resource minimization. The framework degrades elegantly under noisy priors but not under biased ones: a systematically biased map performs about half as well as flying with no prior at all. Computational tests show that the proposed scheme is scalable and competitive with single-path scenarios in terms of solution performance and serves as a strong decision guide for intelligent planning in SAR operations in unstable environments

cs.NE · cs.RO

新论文 · v1arXiv:2611.12315

Beating Rytter's Bound: All-Pairs CFL Reachability in $O(n^3(\log\log n)^2/(\log n)^2)$ Time

Rupak Majumdar

原文摘要

Context-free reachability and 2NPDA recognition are fundamental problems in program analysis and language theory. Despite years of effort, the best algorithms for these problems run in time $O(n^3/\log n)$ on a word RAM model; they are based on an observation of Rytter in 1985 for 2NPDA which was adapted for CFL reachability by Chaudhuri in 2008. No better algorithm has been designed since. We give the first improvement to Rytter's algorithm. For both all-pairs context-free reachability and 2NPDA recognition, we show a deterministic algorithm running in $O(n^3(\log\log n)^2/(\log n)^2)$ time and $O(n^{2+ε})$ words of space for every fixed $0<ε<1$ on a word RAM. Our improvement is based on a new data structure that reports set differences using batched maintenance of exact intersection counts, allowing saturation to skip regions that contain no new reachability information.

cs.PL · cs.FL

新论文 · v1arXiv:2611.12314

A Modular Perspective for Modeling MARL Systems

Tiziano Maisonhaute, Jean-Christophe Soulié, Fabien Michel

原文摘要

The growing complexity of Multi-Agent Reinforcement Learning (MARL) has fragmented the literature, obscuring underlying architectural choices behind diverse implementations. This fragmentation makes it difficult to evaluate critical modeling dimensions in isolation, identify how components affect the resulting system dynamics, and compare, reuse, or combine contributions across the literature. This paper proposes a modular perspective for modeling, analyzing, and implementing MARL systems. We decompose them into eight functional modules: agents, environments, learning, reward modeling, training and execution modes, communication, modeling of other agents, and evaluation criteria. For each module, we clarify its role and review representative approaches. We instantiate this decomposition in MARLKIT, a framework whose modules are explicit and interchangeable. MARLKIT demonstrates how the proposed perspective supports transparent experimental assumptions and the controlled variation and combination of MARL mechanisms. Experiments illustrate its ability to prototype, compare, reuse and combine modules while making differences between configurations explicit. Overall, the paper provides a structured perspective on MARL modeling and implementation, offering a common language for making modeling choices explicit, supporting clearer descriptions of MARL approaches, and supporting more controlled experimentation through the systematic isolation and combination of MARL mechanisms.

cs.LG · cs.AI · cs.MA

新论文 · v1arXiv:2611.12313

Hidden Distances: How Likert-Scale Spacing Shapes Algorithmic Voting Advice

Thomas Broholt Knudsen, Christian Høst-Madsen, Vedran Sekara, Jonas L. Juul

原文摘要

Voting Advice Applications (VAAs) are algorithmic recommenders that match voters with political candidates on policy preferences. They are widely adopted across many multi-party democracies; in Denmark, 62\% of eligible voters used a VAA ahead of the 2022 general election, and 45\% of VAA users reported following its advice. VAAs typically ask voters and candidates to respond to policy statements on a Likert scale, from ``strongly disagree'' to ``strongly agree'', and recommend candidates whose responses are closest to the voter's. Computing these distances requires assigning numbers to response options, a design choice without an empirical basis, since it is unknown how people perceive the distances between options. Here we show that this seemingly technical choice substantially changes whom voters are matched with. We parameterize the distance between ``(dis)agree'' and ``strongly (dis)agree'' relative to the distance between ``neutral'' and ``(dis)agree'' as $α$, and quantify how it changes recommendations for a popular Danish VAA. We find that moving from equidistant options to doubling this distance can change $37.7\%$ of top candidate matches and $21.9\%$ of top party matches, although no answers change. Low $α$-values favor candidates with strong positions, with some parties receiving up to $ 19.6\%$ more recommendations, while high $α$-values favor moderates. Similarly, female candidates receive fewer recommendations at low $α$ and more at high $α$-values. Our findings demonstrate that undisclosed quantification choices in algorithmic recommenders can carry considerable electoral consequences, and they call for transparency and sensitivity analysis in VAA design. As Likert-based matching also underpins dating platforms and roommate allocation systems, these implications extend well beyond elections.

cs.CY · cs.IR · physics.soc-ph

新论文 · v1arXiv:2611.13044

Cyclically covering subspaces and additive perfect codes

Yangcheng Li, Pingzhi Yuan

原文摘要

Let $h_q(n)$ be the largest codimension of a subspace of $\mathbb{F}_q^n$ whose cyclic shifts cover the whole space. For $r>0$, we characterize the inequality $h_q(n)\ge r$ in terms of cyclic $\mathbb{F}_q$-linear codes over vector alphabets with covering radius one, no nonzero word of block weight one, and a scalar dual generated by the shifts of one word. For $k,m\ge2$, let $I_q(j)$ count the monic irreducible polynomials of degree $j$ over $\mathbb{F}_q$. If $k$ is prime or $m\ge2\sum_{j=1}^{k-1}I_q(j)+2$, we prove that a cyclic $\mathbb{F}_q$ linear perfect code of length $\frac{q^{km}-1}{q^k-1}$ over $\mathbb{F}_q^k$ exists if and only if $\gcd(m,q-1)=1$. When this condition holds, we also obtain \(h_q\!\left(\frac{q^{km}-1}{q^k-1}\right)=k(m-1).\) Restriction of scalars gives the same criterion for every $m\ge2$ when $q$ is odd, $q+1$ is a power of two, and $k=2p$ with $p$ prime. We also show that $h_q(q^k+1)=k$ exactly when $q$ is even, for every $k\ge1$.

cs.IT · math.CO · math.NT

版本更新 · v3arXiv:2606.24711

Almost Symmetric Linear Arc Monadic Datalog and Transitive Tournaments

Sebastian Meyer, Florian Starke

原文摘要

We introduce $n$-almost symmetric Datalog and study $n$-almost symmetric linear arc monadic Datalog. We characterize the finite relational structures whose constraint satisfaction problem is solved by this Datalog fragment as those that can be primitive positively constructed from the transitive tournament on $n+2$ vertices. We also give characterizations in terms of a certain homomorphism duality (which we call $n$-fixed unfolded caterpillar duality) and in universal-algebraic terms (the existence of $k$-absorptive operations and of operations forming an elevator chain of length $n+1$). This article generalizes the results from Bodirsky and Starke about symmetric linear arc monadic Datalog.

cs.LO · math.RA