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

+918新增论文
+729其中 AI 相关
+73已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-17 04:58 · 全站最近入库:2026-11-17 12:06各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 12:23 — 2026-11-17 12:23(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:2026-11-17 04:58最近发现新增版本:2026-11-17 12:06库内论文最新更新时间:2026-11-16 04:06

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。

24,672 已收录论文20,615 AI 相关7,189 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 24,672 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-17 04:57(北京时间)
新论文 · v1arXiv:2611.09274

FondueQA: A Benchmark for Evaluating Parametric Compensation in Multi-Hop QA

Laurin Schmid, Suman Navaratnarajah, Koel Dutta Chowdhury, Steffen Eger, Josif Grabocka, Christian Frey

原文摘要

Large Language Models (LLMs) show remarkable performance based on parametric knowledge, i.e., their ability to recall facts and associations internalized in a model's weights. However, studying this capability on established multi-hop benchmarks may be complicated by benchmark contamination, as many of these benchmarks have been publicly available long enough to plausibly appear in modern pretraining corpora. As a result, correct answers under missing evidence may reflect either general parametric knowledge or memorization of benchmark-specific instances. To study how models use internal knowledge when retrieval evidence is incomplete, we introduce FondueQA, in which every required multi-hop fact is uniquely localized to a designated evidence document. This enables controlled document-level evidence ablations to study parametric compensation under incomplete retrieval. Our empirical evaluation reveals that parametric compensation strongly depends on both entity popularity and the structural role of missing evidence. Generally, models compensate more successfully for facts involving popular entities. On FondueQA, we show that bridging evidence can be more useful than the answer-bearing document itself. Moreover, models may recall a missing fact in isolation but fail to use it under partial evidence, particularly when the context contains plausible competing entities, which can reduce Exact Match by up to 15 percentage points.

cs.LG · cs.AI · cs.IR

新论文 · v1arXiv:2611.09273

PHISHREV+: An ASP-Based Post-Hoc Defeasible Machine Learning Framework for Phishing Detection

Mainak Sen, Kumar Sanka Ray, Amlan Chakrabarti

原文摘要

Phishing website detection remains a critical cybersecurity challenge. Although machine learning classifiers achieve high accuracy on benchmark datasets, they suffer from a fundamental limitation: once trained, their decision boundaries are fixed and cannot incorporate new contextual evidence without retraining the model. This work presents \textbf{PHISHREV+}, a hybrid framework that instantiates the notion of \textit{post-hoc defeasible machine learning}. This framework does not replace the classifier. It treats the initial classifier predictions as defeasible beliefs and revises them through an Answer Set Programming based non-monotonic reasoning(NMR) layer. The framework operates in two phases. In the machine learning phase, four classifiers (SVM, KNN, DT and RF) are trained on the 87 feature benchmark dataset. In the post-hoc NMR phase, four defeasible rules derived from exploratory data analysis of the training set, and validated through Chi-square and Mann-Whitney U tests, formally revise initial predictions. The proposed framework achieves consistent false positive reduction across all our classifiers SVM (41$\rightarrow$39), KNN (47$\rightarrow$46), DT (62$\rightarrow$61), and RF (52$\rightarrow$51) while maintaining complete false negative parity with zero increase overhead. A comprehensive ablation studies across seven rule configurations confirms that the hierarchical combination of all four defeasible rules is necessary to achieve this optimal balance. Instance level explainability is provided through eXplainable ASP (XASP), which generates formal derivation graphs showing which defeasible rules fired and why the initial belief was retracted, a capability absent from all existing phishing detection approaches.

cs.AI · cs.LG

新论文 · v1arXiv:2611.10070

Frequency-consistent synthesis and selective transfer for medical image analysis

Zhuhui Wang, Jianwei Zuo, Xin Peng, Kai Zhong, Xuliang Deng, Jiajia Luo

原文摘要

Complementary imaging is not always available, and realistic synthesis does not necessarily improve downstream analysis. Here we introduce a training framework linking medical image synthesis to task learning through adaptive frequency consistency and selective feature transfer. Image-specific frequency constraints encourage consistency of structure and detail. Features are transferred only when a teacher using synthetic images achieves a lower task-error score than the student by a task-specific margin on a labelled training sample. Evaluations across five datasets show improved translation fidelity with three adversarial and diffusion-based translators trained without paired supervision, alongside gains in brain-tumour segmentation on tumour-containing slices and lesion centre-point detection. All 105 reported paired comparisons yielded point estimates favouring the proposed methods, including 36 external translation comparisons on post?treatment MRI without retraining. These findings support synthetic modalities as task-oriented complements to acquired scans when complementary imaging is unavailable.

eess.IV · cs.CV

新论文 · v1arXiv:2611.09270

EGT: Execution-Grounded Traversability through Learned Closed-Loop Trajectory Distributions

Chinmay Mundane, Amith Manoharan, Arun Kumar Singh

原文摘要

Rough terrain traversability is often estimated through point-wise roll, pitch, or force-angle margins along a planned path. However, these metrics are often inaccurate and overly conservative because they ignore how terrain disturbances and low-level controller corrections can affect the vehicle's motions. To overcome these limitations, we introduce Execution-Grounded Traversability (EGT), defined as the probability that a vehicle-controller pair can execute a candidate path while meeting trajectory-level tracking and progress requirements. We estimate EGT by predicting the distribution of closed-loop trajectories using a latent-space flow matching (FM) model conditioned on multi-resolution terrain features and 3D vehicle attitude and wheel-ground contact points prior. Across 650 simulated trials on unseen terrains, EGT reduces safe-path rejection to 2.2% (versus 11.4%-39.5% for pose-margin and force-angle baselines) and unsafe acceptance to 7.7%. Integrated into a receding-horizon sampling-based planner, EGT reduces navigation failure rates by 24-42 and 30-44 percentage points over [1] and [2], respectively, while cutting goal-reaching time by up to 20.5% and 45%. Finally, we demonstrate zero-shot transfer of our simulation-trained model to real-world outdoor experiments.

cs.RO

新论文 · v1arXiv:2611.09269

Thinking Twice: A Sequential Approach to Nudge Towards Reflective Judgment in GenAI-Assisted Decision Making

Hüseyin Hussein Keke, Daniel Eisenhardt, Christian Meske

原文摘要

Humans increasingly use generative AI (GenAI) for decision-making assistance, yet tend to engage in such situations using quick, intuitive (System 1) rather than deliberate, analytical assessment (System 2) as reflected in Dual Process Theory. Such engagement reduces the effectiveness of human-GenAI interactions and increases associated risks. Our research investigates how to design human-GenAI interactions that promote the transition from System 1 to System 2 thinking in decision-making. Based on the Three-Stage-Model, which suggests humans switch to System 2 when conflicts are detected, we conducted an experiment (n=130) testing sequential human-GenAI interaction as a cognitive forcing nudge during problem-solving tasks. This approach, where humans decide first before receiving AI assistance, enables detection of conflicting decisions. Compared to non-sequential settings (concurrent or no AI assistance), results show the sequential condition significantly enhanced both decision performance and GenAI prompt utilization, providing valuable insights for designing more reflective and thus effective human-GenAI interactions.

cs.HC

版本更新 · v2arXiv:2610.34590

Sparse Sum-of-Squares Layers for Certified Learning

Ege Gursoy, Nicolas Mansard

原文摘要

A central limitation of modern machine learning systems is the lack of formal certificates guaranteeing their behavior beyond empirical, sample-based evaluation. Sum-of-squares (SOS) methods provide such guarantees by certifying polynomial inequalities over continuous domains via semidefinite programming (SDP). While prior work has introduced SDP layers as differentiable components in neural networks, repeated learning calls can lose the computational benefit of the forward program's sparse representation. We propose Sparse SOS Layers, differentiable value layers whose backward passes reuse the local coordinates of the forward solve. Under a fixed template and learned objective coefficients, each layer avoids building dense certificates and reuses its sparse structure across training steps. Compared with existing methods, our approach achieves up to 2.7 times speedup in total warm-call time, with nearly 100 times lower memory usage (1.7 vs. 160 GiB) for relatively large problem sizes for the tested dense parameterization. Experiments cover sparse polynomial certification, pendulum control, combinatorial relaxations, robotics projection, oscillator chains, and pose graph synchronization. A design study achieves zero certified violations across unseen problem instances and sizes, while requiring roughly 7 times fewer optimization solves than estimating gradients by perturbing the objective coefficients and re-solving the problem (finite differences). These results show that sparse certificate values can be effectively integrated into learning pipelines when the backward pass respects the verifier's structure.

cs.LG · math.OC

版本更新 · v5arXiv:2506.14544

Infinite lexicographic products of positional objectives

Antonio Casares, Pierre Ohlmann, Michał Skrzypczak, Igor Walukiewicz

原文摘要

This paper contributes to the study of positional determinacy of infinite duration games played on potentially infinite graphs with neutral transitions. Recently, [Ohlmann, TheoretiCS 2023] established that positionality of prefix-independent objectives is preserved by finite lexicographic products. We propose two different notions of infinite lexicographic products indexed by arbitrary ordinals, and extend Ohlmann's result by proving that they also preserve positionality. In the context of one-player positionality, this extends positional determinacy results of [Grädel and Walukiewicz, Logical Methods in Computer Science 2006] to edge-labelled games and arbitrarily many priorities for both Max-Parity and Min-Parity. Moreover, we show that the Max-Parity objectives over countable ordinals are complete for the infinite levels of the difference hierarchy over $Σ^0_2$ and that Min-Parity is complete for the class $Σ^0_3$. We obtain therefore positional languages that are complete for all those levels, as well as new insights about closure under unions and neutral letters.

cs.GT

版本更新 · v2arXiv:2602.23903

SegMate: Asymmetric Attention-Based Lightweight Architecture for Efficient Multi-Organ Segmentation

Andrei-Alexandru Bunea, Dan-Matei Popovici, Radu Tudor Ionescu

原文摘要

State-of-the-art models for medical image segmentation achieve excellent accuracy, but require substantial computational resources, limiting deployment in typical resource-constrained clinical settings. We present SegMate, an efficient 2.5D framework that achieves state-of-the-art accuracy, while considerably reducing computational requirements. Our efficient design is the result of meticulously integrating asymmetric architectures, attention mechanisms, multi-scale feature fusion, slice-based positional conditioning, and multi-task optimization. We demonstrate the efficiency-accuracy trade-off of our framework across three modern backbones (EfficientNetV2-M, MambaOut-Tiny, FastViT-T12). We perform experiments on three datasets: TotalSegmentator, SegTHOR and AMOS22. Compared with the vanilla models, SegMate reduces computation (GFLOPs) by up to 2.5x and memory footprint (VRAM) by up to 2.1x, while generally registering performance gains of around 1%. On TotalSegmentator, we achieve a Dice score of 93.51% with only 295 MB peak GPU memory. Zero-shot cross-dataset evaluations on SegTHOR and AMOS22 demonstrate strong generalization, with Dice scores of up to 86.85% and 89.35%, respectively. SegMate variants in this study empower single GPU setups to process up to 10,000 volumes per hour with just 74 J per volume using batch inference, enabling population-scale CT processing on commodity hardware. We release our open-source code at https://github.com/andreibunea99/SegMate.

cs.CV · cs.LG

版本更新 · v2arXiv:2605.00722

From Points to Targets: Online Foreground Affinity and Background Learning for Infrared Small Target Detection

Qiancheng Zhou, Xiaodong Yue, Wenhua Zhang

原文摘要

Infrared small-target detection must identify a few faint target pixels in extensive background clutter while keeping false alarms low. Under single-point supervision, each target has only one labeled foreground pixel with unknown spatial extent during training, whereas the detector must recover complete targets from the infrared image without any point guidance at inference. Existing methods typically reconstruct regional pseudo-labels from local cues or intermediate predictions, which can introduce boundary noise around blurry target edges. Instead of turning uncertain boundaries into dense pseudo-masks, we propose Online Foreground Affinity and Background Learning (OABL), a single-stage framework that learns target structure directly from sparse points. First, for online foreground affinity learning, each annotated target point serves as a feature anchor, and local spatial proximity and intensity similarity weight the feature alignment between the point and surrounding pixels, guiding target-related representations without hard boundary labels. Second, for online background learning, we exclude the ambiguous neighborhood around each target point and select high-response false alarms outside this region as active negatives. Averaging the background loss over this active set keeps sparse target-like clutter influential as easy background pixels are suppressed. Jointly optimizing these objectives in a single stage updates the detector directly without generating or refreshing persistent pseudo-masks. Across three public datasets and the combined SIRST3 benchmark, OABL improves detection probability by 1.06--7.82 percentage points over matched PAL training at a false-alarm area rate of $2 \times 10^{-5}$ and avoids PAL's multi-stage full-pool label updates.

cs.CV

版本更新 · v2arXiv:2610.06238

Certification-Enhanced Generalization Bounds

Leo Elmecker-Plakolm, Matthew Wicker

原文摘要

We investigate the use of formal methods to provide tight and sound generalization bounds for learning algorithms. By casting the traditional notion of algorithmic stability as a specification to be verified, we demonstrate that recent advances in reachability analysis can yield provable bounds on the generalization of a given model and algorithm on a sample dataset. As sample-specific algorithmic stability is insufficient to bound the usual distributional notion of generalization, we develop a novel concentration inequality to connect the sample-specific results of formal certification algorithms to the required distributional analysis for bounding the expected generalization gap. The resulting framework enables the analysis of prior generalization bounds to extend far beyond their original restrictive assumptions. Our approach computes sound bounds on the expected generalization gap in a constant number of algorithm runs without making any analytical assumptions on the algorithm; to achieve non-vacuous bounds we only require that the certified reachable parameter set is bounded --- a condition that we do not assume but formally verify. In practice, we demonstrate that our framework provides formal generalization guarantees that are orders of magnitude tighter than alternative sound computational approaches at scales ranging from toy datasets to fine-tuning classification heads on top of modern large language models. While we implement certification-enhanced versions of several well-known stability results, future extensions of our approach will enable tighter bounds and enhanced practical adoption across the spectrum of modern generalization bounds.

cs.LG

新论文 · v1arXiv:2611.09267

Load Balancing with Item Fragmentation and More Bins than Items: Linear-Time and Exact

Ben Bals, Tomáš Flouri, Kassian Kobert, Solon P. Pissis, Leen Stougie

原文摘要

We study a fundamental load-balancing problem in which $N$ items of strictly positive integer sizes with total size $W$ must be assigned to $B$ bins, with items allowed to be divided into integer-size fragments across bins. Each bin must receive a load of either $\lfloor W/B \rfloor$ or $\lceil W/B \rceil$, ensuring that the loads of any two bins differ by at most one unit. Under this constraint, the objective is to minimize the maximum number of distinct item fragments placed into any single bin. This problem is NP-hard and there exists an $(\mathrm{OPT}+1)$-approximation algorithm that runs in $O(N \log N + B)$ time [Kobert et al., 2014]. The existing algorithm is employed by several widely used production codes for phylogenetic reconstruction. Here, we focus on the case $B \ge N$, that is, bins are at least as numerous as items. This setting arises pervasively in modern parallel and distributed systems, as well as in iterative algorithms that rebalance their workload at every step. In this context, bins are machines or machine cores, and items represent computational tasks (jobs). Our central contribution is a remarkably simple $O(N)$-time algorithm that computes an optimal assignment in this setting; this assignment is encoded using $O(N)$ space. In particular, we prove that an optimum always exists in which every bin receives at most two fragments and provide a characterization of when one fragment per bin suffices. Our result strictly improves the $(\mathrm{OPT}+1)$-approximation of Kobert et al. in the many-bins setting and, together with it, yields a strongly polynomial-time $(\mathrm{OPT}+1)$-approximation algorithm for the general setting, as it removes the dependency on the number $B$ of bins.

cs.DS · cs.DC

新论文 · v1arXiv:2611.09266

SUGARv2: Learning Diverse Visual Humanoid Loco-Manipulation Skills from Synthesized Interaction References

Tianshu Wu, Tianxiang Gui, Yue Chen, Tingxu Liu, Ziye Peng, Guangjie Yang, Xiangqi Kong, Ye Shi 等 10 位作者

原文摘要

Scaling up visual humanoid loco-manipulation skill acquisition requires reducing the human effort needed as tasks and spatial configurations expand, particularly in demonstration collection and task-specific training design. We present SUGARv2, a unified framework for learning diverse visual humanoid loco-manipulation skills through interaction reference synthesis and a shared training pipeline. To obtain diverse references at low cost, we adapt reusable task templates to different spatial configurations, synthesizing coordinated robot and object motions. To reduce task-specific reward design and training effort, we use reference-based imitation as a common learning objective across tasks. We first train privileged teachers to execute these references, then train visual policies through teacher distillation and reinforcement learning with the same reference-based mimic rewards, using diverse object instances and visual domain randomization to support visual generalization and sim-to-real transfer. Across five humanoid loco-manipulation tasks, SUGARv2 achieves a mean success rate of 91.0% in simulation. Deployment on a real humanoid robot further demonstrates successful sim-to-real transfer for whole-body manipulation. These results demonstrate the framework's potential for learning diverse visual humanoid loco-manipulation skills.

cs.RO

新论文 · v1arXiv:2611.09265

Reconciling European Electricity Data with Diffusion Priors Learned from Observations Alone

Matthias Pirlet, Adrien Bolland, Gilles Louppe, Damien Ernst

原文摘要

The ENTSO-E Transparency Platform publishes generation, load, and cross-border power flows for European bidding zones. The values carry undocumented errors and violate energy conservation, and data reconciliation consists in correcting them to satisfy that balance. In this work, we formulate data reconciliation as Bayesian inference. Classical methods implicitly take a uniform prior, which we replace with a diffusion model estimated from the observations alone by empirical-Bayes expectation-maximization. The resulting posterior is sampled with a guided process whose projection step makes every sample satisfy the balance exactly. On synthetic systems of six to thirty-five bidding zones, built from ENTSO-E resource-adequacy data, the diffusion prior gives the most accurate reconciliation, increasingly so as the system grows. Its credible intervals are calibrated or conservative, and it remains the most accurate under a misspecified noise covariance. Finally, when the generation of entire zones goes unreported, the classical methods fail while the learned prior recovers it from cross-zone structure.

eess.SY · cs.LG

新论文 · v1arXiv:2611.09264

Nudging Decision Models: Do Digital Nudges Steer Fast, Generation-Free AI Agents?

Sascha Kaltenpoth, Haya Halimeh, Kevin Bösch, Oliver Müller

原文摘要

LLM-based agents increasingly automate business and consumer tasks but are slow and expensive. Decision models, a new class that chooses among options without generating text, are far faster and less costly. Developers call them "System One models," referencing dual process theory. We ask whether such models can be steered by digital nudges online and whether, as the theory predicts, automatic nudges affect them more than reflective ones. We adapted an online shopping experiment, previously run with humans and LLM agents, to three decision models (Jev, Decision-1, d1). Across 600 runs per model, they chose a preselected default in 97.5-99.9% and a product with social influence information in 75-96% of choices, versus 47-49% in the control. All responded more strongly to the automatic nudge, the opposite of what has been reported for reasoning-capable LLM agents. We provide first evidence that non-generative decision models are susceptible to digital nudges in a System 1 pattern, implying agent-type-specific nudge effects.

cs.AI

新论文 · v1arXiv:2611.09263

Model-based learning for DoA estimation and array calibration via continuous sparse recovery

Baptiste Chatelier, José Miguel Mateos-Ramos, Vincent Corlay, Matthieu Crussière, Christian Häger, Henk Wymeersch, Nir Shlezinger, Luc Le Magoarou

原文摘要

Direction of arrival (DoA) estimation, a classical signal processing problem, has experienced renewed interest with the advent of integrated sensing and communication (ISAC). While decades of research have yielded highly accurate DoA estimators, hardware impairments have frequently been neglected, despite degrading both DoA estimation accuracy and downstream communication performance in ISAC systems. This work introduces a joint array calibration and DoA estimation method based on the simultaneous orthogonal matching pursuit (SOMP) algorithm, following the model-based machine learning paradigm. The proposed method enables the calibration of antenna arrays subject to severe gain-phase and antenna location impairments through projected gradient descent (PGD), with either supervised or unsupervised objectives. Additionally, DoA estimation is enhanced by extending SOMP to continuous dictionaries via PGD refinement steps. Simulation results demonstrate that the proposed method enables efficient hardware impairment compensation, even without labeled samples, while outperforming conventional sparse recovery and subspace-based DoA estimation baselines.

cs.AI · cs.LG

新论文 · v1arXiv:2611.09262

Path Isolation and Reachability in Surface-Embedded Graphs with Restricted Cycle and Cut Structure

Neelabjo Shubhashis Choudhury, Chetan Gupta, Raghunath Tewari

原文摘要

We study the reachability problem in directed surface-embedded graphs under two structural restrictions, using isolating weight assignments. First, we consider graphs whose underlying undirected embeddings contain at most polynomially many simple surface non-separating cycles. We develop a polynomially bounded, logspace-computable skew-symmetric edge-weight assignment with nonzero circulation around every simple cycle. This yields an unambiguous logspace (UL) upper bound for directed reachability. The construction also gives an SPL upper bound for bipartite perfect matching in the corresponding undirected graph class. Second, for $g$-genus directed graphs admitting a balanced hierarchical genus decomposition with $O(\log n)$ crossing edges at every partition, we obtain an unambiguous $O(\log g \cdot \log n)$-space bound for reachability. Our approach combines path-isolating weights for lower-genus subgraphs using polynomially bounded FKS hashing refinements at successive merging levels.

cs.CC

新论文 · v1arXiv:2611.09260

Navigating Complexity: A User-Centered Evaluation of Project Management Tools

Yasin Ghadimi Zaker, Hamid Reza Ghaeini

原文摘要

In the age of digital transformation, companies are increasingly relying on specialized software to manage the complexity of projects. However, when selecting tools, features and costs often take precedence over user experience (UX), leading to low adoption rates, user frustration, and project delays. This study empirically evaluates the user experience of leading project management tools (Jira, Trello, Monday.com, Asana, and Microsoft Project) across various project scales using a mixed methods approach. The System Usability Scale (SUS) was used as the primary quantitative instrument, with data collected from 141 experienced professionals via online questionnaires. The results reveal a significant trade-off between functionality and usability. Trello achieved the highest SUS score (77.5), indicating a superior user experience for small projects and agile teams, while Microsoft Project scored the lowest (51.2), suggesting significant usability challenges despite its robust features. Jira demonstrated a balanced profile, offering powerful features with manageable complexity. Statistical analyses confirmed that the choice of the optimal tool is highly context dependent, with team size and project complexity influencing UX outcomes. The findings underscore that UX is not a secondary feature but a critical success factor for software acceptance and project effectiveness. This study provides an evidence-based framework for aligning tool selection with the project context, offers practitioners actionable insights, and identifies design opportunities for software developers.

cs.SE · cs.HC

新论文 · v1arXiv:2611.09259

Forecasting cumulative intraoperative hypotension burden: patient-disjoint evaluation of quantile boosting and alert policies

Yunfan Zhao

原文摘要

Background: Binary hypotension forecasts do not describe the depth and duration of future low pressure. Burden forecasts may support graded early warning, but better forecast scores need not yield more useful alerts. Objective: To evaluate conditional quantiles of the next 15-minute mean arterial pressure (MAP) deficit below 65 mmHg and distinguish forecasting performance from episode-warning performance. Methods: Public VitalDB numeric arterial MAP was reduced to 10-second medians without forward filling. Subject-disjoint training, validation and test splits included 70,402, 14,270 and 15,575 labeled windows. We compared climatology, calibrated persistence, last-MAP-only boosting, and direct and residual quantile boosting, with and without additional MAP-history features. Patient-weighted pinball loss and subject-bootstrap intervals evaluated forecasting. Validation selected alert thresholds before a hash-recorded test evaluation. Results: In the test split, the prespecified residual-versus-persistence comparison at the 90th percentile yielded losses of 2.256 and 2.900 mmHg-min, respectively (difference -0.644; 95% interval -0.814 to -0.487). Direct prediction achieved 2.196, and direct prediction with additional MAP features achieved 2.193. Episode-warning results were sensitive to the alert rule and operating threshold. Conclusions: This retrospective benchmark separates burden-forecast skill from warning-policy performance. Findings support further study of direct burden estimation; they do not establish patient benefit, prospective reliability or transportability beyond the source hospital.

cs.AI

新论文 · v1arXiv:2611.09256

Zero-Query Transferable Pretend Benign Attacks with Amortized Online Generation for Cooperative Perception

Hongwei Lin, Xun Huang, Chenglu Wen, Cheng Wang

原文摘要

Cooperative perception enables an ego agent to acquire information from collaborators beyond its own sensors' reach. Yet, the most beneficial messages are often the hardest to verify from local observations. Pretend Benign (PB) exploits this asymmetry by targeting regions with weak local verifiability and applying multi-objective perturbations, making harmful feature changes appear to be benign assistance. However, PB is victim-dependent: selecting regions and optimizing perturbations require the victim model's architecture, parameters, and gradients, limiting transfer to unseen victims. A transferable attack must capture properties shared across cooperative detection models rather than those specific to one network. We address this by building a victim-agnostic attack from a heterogeneous ensemble of surrogate models and encoding its capabilities in a reusable dictionary to reduce per-message generation cost. Specifically, Transferable Pretend Benign (TrPB) transfers PB's region selection criterion and multi-objective perturbation strategy across heterogeneous surrogates to construct an offline attack. We further propose RT-TrPB, which encodes transferable regions and perturbation patterns into a region predictor and reusable perturbation dictionary, amortizing per-message attack generation. Experiments on widely used cooperative perception benchmarks show that RT-TrPB bypasses the consensus-based defenses ROBOSAC and FLD with success rates approaching 100% and generates each perturbation in under 56 ms. To counter PB-style attacks masquerading as benign collaboration, we also propose STTrust, which verifies received messages using spatial and temporal consistency and incorporates identity-level trust. STTrust detects over 90% of PB-style attacks and restores perception performance to near the attack-free level.

cs.AI

版本更新 · v2arXiv:2607.22133

Approximate Total Weighted Completion Time with Convex Controllable Processing Times

Klaus Heeger, Danny Hermelin, Dvir Shabtay

原文摘要

We study the single-machine scheduling problem with controllable processing times to minimize the total weighted completion time, focusing on the setting where a job's processing time is a convex function of its allocated continuous resource. The computational complexity of this problem represents a long-standing open question, as it is currently neither known to be polynomial-time solvable nor NP-hard. While we do not fully resolve this complexity question, we provide several insights into the problem's approximability. On the positive side, we present a polynomial-time $e \le 2.719$-approximation algorithm, alongside a quasi-polynomial approximation scheme for instances where the largest parameter value is polynomially bounded by the instance size. On the negative side, we demonstrate that simple sorting rules, which are optimal for certain special cases in the literature, cannot guarantee a constant-factor approximation for the general case.

cs.DS

新论文 · v1arXiv:2611.09254

TwinHash: Two-Sided Object Identity Management for Time- and Energy-Efficient Agentic Workflows

Sangbu Yun, Jung Gyu Min, Jin Hyun, Jeonghwan Ahn, Youngjoo Lee

原文摘要

Agentic artificial intelligence (AI) services interleave large language model (LLM) generation with external tool execution, and increasingly rely on search-based workflows that repeatedly revisit shared reasoning states and computations. These patterns create substantial redundancy across tool outputs, LLM responses, and key-value (KV) prefixes, yet existing serving systems primarily optimize shared prompt prefixes, while naive input-keyed caching is unsafe when identical requests produce different outputs. We present TwinHash, a unified object management architecture that assigns each object an input-side hash key to recognize repeated requests and an output-side content fingerprint to validate and locate stored state, complemented by type-specific reuse guards that preserve correctness and response diversity. A software object identity table maintains reusable objects across requests and trajectories, while a hardware object placement table tracks their residency across hierarchical memory tiers so that evicted state can be retrieved rather than recomputed. Across seven agent frameworks and five benchmark suites, reuse follows workflow structure more than benchmark identity. TwinHash serves up to 81% of tool outputs wherever deterministic tool reads recur, and up to 92% of LLM responses in search-based frameworks. Retrieving an evicted KV-prefix from DRAM reduces TTFT by up to 5.6x on Qwen3-32B, with greater gains projected for larger dense models. Under search-based frameworks, TwinHash reduces end-to-end wall-clock time by up to 87% and measured task energy by up to 81% over a prefix-cached baseline, while a per-key serving cap controls the quality-reuse trade-off in adaptive search. These results demonstrate that unified identity, safety, and placement management can convert structural redundancy in emerging agentic workflows into substantial serving-efficiency gains.

cs.AR

版本更新 · v2arXiv:2605.08885

Compact SO(3) Equivariant Atomistic Foundation Models via Structural Pruning

Chen Wang, Siyu Hu, Guangming Tan, Weile Jia

原文摘要

SO(3) equivariant graph neural networks have become the dominant paradigm for atomistic foundation models, achieving high accuracy and data efficiency by building rotational symmetry directly into the architecture. Yet the computational cost of their higher-order tensor operations creates a tough trade-off between model accuracy and inference efficiency. In this paper, we propose a structural pruning method for SO(3) equivariant atomistic foundation models to bridge this accuracy-efficiency gap. The pruning is applied along the channel and order dimensions, with each irreducible representation kept or removed as a complete block, thereby retaining SO(3) equivariance. Starting from a large checkpoint, the pruned model substantially reduces the inference cost while retaining higher accuracy than an independently trained small model. The pruned MACE-MP model outperforms the official from-scratch trained small model on 7 of 9 metrics on the Matbench Discovery leaderboard. In terms of efficiency, compressed MACE-MP and MACE-OFF models contain 1.5$\times$ to 4$\times$ fewer parameters and require 2.5$\times$ to 4$\times$ less pre-training compute than training a small model from scratch. For downstream applications, fine-tuning the pruned model reduces energy and force errors by 70.1% and 34.4% compared to training task-specific models from scratch across eight representative downstream datasets. We demonstrate that the method generalizes to other SO(3) equivariant architectures (SevenNet, eSCN) and can be combined with quantization and knowledge distillation for further gains.

cs.LG

新论文 · v1arXiv:2611.09252

Rethinking MoE Load Balancing as Feedback Control

Yikun Hou, Alp Yurtsever

原文摘要

Mixture-of-Experts (MoE) training is often not stationary: the data mixture changes at curriculum boundaries, when a model is continually pretrained into a new domain, or when the corpus is refreshed. Routing is learned against the current mixture, so each such change disrupts the per-expert load the router had converged to, and existing balancing methods have only been evaluated on stationary data. We rethink load balancing as a feedback control problem, in which the deviation of each expert's load from its fair share is the control error and the per-expert routing bias is the control input, and define a family of controllers, the PID-Balancer, from the proportional, integral, and derivative terms of classical PID control. Two widely used methods belong to this family: the auxiliary balancing loss behaves like a proportional controller, and the loss-free bias update is an integral controller acting on the sign of the error. Reading the router as a static map with a one-step delay, we show that the integral term is the only one that both removes persistent imbalance and averages out the step-to-step fluctuation of the measured load, whereas the proportional and derivative terms pass or amplify that fluctuation into the routing bias. We therefore adopt PID (I), the pure-integral member of the family with a single gain. Two settings are evaluated: (i) training an OLMoE backbone from scratch with 16 to 64 experts per layer, through a mid-run mixture switch, and (ii) continual pretraining of the released OLMoE-1B-7B on a new corpus. PID (I) holds balance before the shift and restores it more tightly afterwards than either the auxiliary loss or loss-free balancing, at comparable perplexity.

cs.LG

新论文 · v1arXiv:2611.09251

Green500: Adventure in Qualifying a Cluster

Nicolas Richart, Xavier Ouvrard, Julia Paolini, Manuel Cubero-Castan, Gilles Fourestey

原文摘要

Energy effciency has become a key metric for evaluating High Performance Computing (HPC) systems, as reflected by the Green500 ranking. However, energy effciency alone does not capture the full environmental impact of an HPC cluster. Using the Kuma cluster at EPFL, we report on two Green500 measurement campaigns at Level 2 and Level 3, and extend this analysis to a full carbon footprint assessment using the MITSI life-cycle based methodology. GPU power capping experiments show that energy effciency peaks at 450 W, achieving an 11% performance loss offset by a 20% reduction in energy consumption. When embodied emissions are accounted for, the optimal power cap for carbon effciency shifts to 500 W under Switzerland's low-carbon electrical grid, revealing a tension between minimizing usage and embodied contributions. We discuss the challenges of generalizing this approach into a broader carbon-based HPC ranking, and argue that moving beyond energy effciency is both necessary and feasible.

cs.DC

版本更新 · v2arXiv:2604.25508

Dyna-Style Safety Augmented Reinforcement Learning: Staying Safe in the Face of Uncertainty

Artur Eisele, Bernd Frauenknecht, Friedrich Solowjow, Sebastian Trimpe

原文摘要

Safety is a key problem in reinforcement learning, especially during exploration. While safety filters are promising to address this issue, they are ill-suited for high- dimensional systems with unknown dynamics. We propose Dyna-style Safety Augmented Reinforcement Learning (Dyna-SAuR), a novel algorithm that learns a control policy as well as a safety filter requiring minimal domain knowledge by leveraging a learned uncertainty-aware dynamics model. A novel filter learning formulation requires the filter to avoid failures and areas of high model uncertainty. As joint deployment of the control policy and filter allows to safely collect data and improve the dynamics model, certain areas grow and filter conservatism decreases over time. Dyna-SAuR reduces failures compared to established safe RL baselines by two orders of magnitude on goal-reaching CartPole and MuJoCo Walker.

cs.LG

新论文 · v1arXiv:2611.09248

Topology as a Design Variable: Joint Architecture-Sizing Optimization for SRAM

Can Wang, Junhao Ma, Yikai Wang, Shan Shen, Wei W. Xing

原文摘要

SRAM's power-performance-area-stability trade-off depends on bitcell topology, a discrete architectural choice that interacts non-separably with continuous transistor sizing. However, no open-source SRAM tool treats topology as an optimizable variable. OpenRAM generates SRAM layouts but performs no optimization, while OpenYield supports high-fidelity evaluation but restricts optimization to scalar sizing of a fixed 6T cell. OpenYieldV2 closes this gap through three integrated contributions. First, a fully parameterized compiler generates complete 6T and 10T SRAM macros with peripheral circuits and replica-bitline self-timing, enabling topology comparison under identical simulation conditions. Second, a few-shot TabPFN surrogate learns topology-dependent PPA responses with limited full-macro SPICE samples. Third, a coarse-to-refined multi-objective optimizer combines global exploration of discrete architectural choices with local refinement of continuous transistor sizes. Experiments across varying design conditions reveal a topology decision boundary that shifts with operating constraints rather than following a fixed design rule. Jointly optimizing across this boundary improves hypervolume by up to 17.3\% over the strongest single-topology baseline. OpenYieldV2 is open-source to support reproducible SRAM design research.

cs.LG

新论文 · v1arXiv:2611.09247

Practical Non-Stationary Graph Gaussian Processes

K. S. Sesh Kumar, Viacheslav Borovitskiy

原文摘要

Gaussian processes on graphs provide a principled framework for prediction and uncertainty estimation, but modelling heterogeneous networks often requires balancing flexibility against parameter complexity. Variability at a node may reflect useful signal that should propagate through the network, unreliable measurements whose influence should be suppressed, or a mixture of both. We introduce Variance-Coupled Gaussian Processes (VCGPs), which use a positive auxiliary signal to modulate graph interactions through a single learned coupling exponent. The exponent controls how strongly high-variability nodes propagate or attenuate information, while a cluster-wise extension accommodates different regimes within the same graph. Under stated structural assumptions, we characterize the unique stationary-rescaling point of the basic family, where correlations match those of a stationary graph kernel while node-dependent variances remain. Experiments on traffic, air-quality and weather datasets show competitive prediction and uncertainty estimation relative to stationary and per-node non-stationary baselines, with the largest gains on networks requiring multiple coupling regimes. Stationary correlations after variance rescaling remain sufficient on some data, and performance depends on the auxiliary signal and model selection.

cs.LG

版本更新 · v2arXiv:2510.18413

Adamas: Hadamard Sparse Attention for Efficient Long-Context Inference

Siyuan Yan, Guo-Qing Jiang, Yuchen Zhang, Xiaoxing Ma, Ran Zhu, Chun Cao, Jingwei Xu

原文摘要

Large language models (LLMs) now support context windows of hundreds of thousands to millions of tokens, enabling applications such as long-document summarization, large-scale code synthesis, multi-document question answering and persistent multi-turn dialogue. However, such extended contexts exacerbate the quadratic cost of self-attention, leading to severe latency in autoregressive decoding. Existing sparse attention methods reduce these costs by attending to only a subset of key-value (KV) tokens, but fixed or coarse-grained selection strategies can miss important tokens or retain substantial redundancy under constrained token budgets. We introduce \textbf{Adamas}, an accurate and efficient token-level sparse attention mechanism for long-context inference. Adamas applies the Hadamard transform, bucketization and 2-bit compression to produce compact representations, and uses lightweight distance-based estimation for efficient top-$k$ candidate selection. The selected positions are then used to gather the corresponding original KV states for sparse attention. Comprehensive evaluations show that Adamas maintains near-lossless performance within the effective context length of Llama-3.1-8B-Instruct. In efficiency evaluations, Adamas achieves up to $6.5\times$ self-attention speedup and $1.7\times$ end-to-end decoding speedup at a 32K context length. Adamas also maintains performance comparable to full attention on challenging long-form reasoning benchmarks, including AIME 2024 and AIME 2025.

cs.CL

新论文 · v1arXiv:2611.09244

Attaining Optimal Values under Sure Constraints

Takuto Yamauchi, Kenji Tei

原文摘要

A game may have, for each target below its value, a finite controller meeting that target, yet no finite controller attaining the value itself. We study finite stochastic games with a hard specification that must hold on every supported execution, including paths of probability zero. Max uses a pure finite controller; Min may use any pure public-history strategy. We distinguish three numerical questions: can a supplied target be met, can the unspecified optimum be attained, and what is one exact value? For explicit hard and Boolean soft Streett conditions, the strict and non-strict supplied-threshold problems are coNP-complete, attainment of the unsupplied supremum is $\mathrm P^{\mathrm{NP}}$-complete, and one exact reduced fraction is $\mathrm{FP}^{\mathrm{NP}}$-complete under polynomial metric reductions. The proofs preserve both the value and its finite attainability when fixing a single opponent, and encode adaptive queries without computing unknown subgame values. The same construction yields matching value-comparison and exact-output lower bounds for ordinary stochastic Streett games with unrestricted randomized history strategies. We also bound the memory needed for optimal finite implementations for arbitrary Muller hard conditions and rational rewards in $[0,1]$ determined by infinitely recurring states. One controller is sure from the entire original sure region and attains at every finitely attained start, with no attainment premise on the other states. For $n$ states in that region it uses $2^{O(n\log(n+1))}Q(1+\log R)$ modes, where $Q$ is the product of the least common denominators of full original chance rows sourced in that sure region and $R$ clears all reward values. Its joint dependence on $Q$ and $R$ is worst-case sharp at each fixed $n\ge6$ when $Q,R\ge2$. Optimal dependence on arena size and efficient general synthesis are not resolved here.

cs.GT · cs.LO

版本更新 · v2arXiv:2602.12300

Fast and General Automatic Differentiation for Finite-State Methods

Lucas Ondel Yang, Caio Corro, Nicolas Denier, Martin Kocour, Tina Raissi, Pablo Riera

原文摘要

We propose a new method, that we coined the ``morphism-trick'', to integrate custom implementations of vector-Jacobian products in automatic differentiation softwares, applicable to a wide range of semiring-based computations. Our approach leads to efficient and semiring-agnostic implementations of the backward pass of dynamic programming algorithms. For the particular case of finite-state methods, we introduce an algorithm that computes and differentiates the $\oplus$-sum of all paths' weight of a finite-state automaton. Results show that, with minimal effort from the user, our novel library allows computing the gradient of a function w.r.t. to the weights of a finite state automaton orders of magnitude faster than state-of-the-art automatic differentiation systems. Implementations are made available via an open-source library distributed under a permissive license.

cs.FL · cs.AI