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

+197新增论文
+151其中 AI 相关
+16已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-22 08:44 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 10:58 — 2026-11-22 10:58(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:2026-11-22 08:44最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 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。

29,158 已收录论文24,181 AI 相关8,992 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 23,345 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 08:42(北京时间)
新论文 · v1arXiv:2611.26300

A Tensor-Algebraic No-Go Theorem for High-Dimensional Photonic Greenberger--Horne--Zeilinger States Discovered with AlphaProof Nexus

Mario Krenn, Moritz Firsching, George Tsoukalas, Rishikesh Gajjala, Xuemei Gu, Swarat Chaudhuri

原文摘要

Photonic GHZ states generated with probabilistic pair sources can be described by edge-coloured, complex-weighted graphs. In this representation, conditioning on an event with one photon in every detector turns the output amplitudes into coherent sums over perfect matchings, and generating an \(N\)-photon \(D\)-dimensional GHZ state is equivalent to constructing a monochromatic quantum graph. Here, we prove that no complex-weighted monochromatic quantum graph exists for any even \(N\ge4\) when \(D\ge N\). The proof, discovered through AI-assisted formal proof search in Lean using AlphaProof Nexus, constructs a weighted sum \(\mathcal F\) of amplitudes whose coefficients factor vertex by vertex. Summing over the colours at one fixed vertex reduces the problem to an \((N-1)\times N\) matrix of effective edge weights. For the graph amplitudes \(ω\) and GHZ target \(Δ\), the row--column imbalance yields \(\mathcal F(ω)=0\) but \(\mathcal F(Δ)\neq0\), contradicting the required equality \(ω=Δ\). Finally, we give a physical interpretation of the AI-discovered mathematical proof.

quant-ph · cs.AI · math.CO

新论文 · v1arXiv:2611.26298

DailySafe: Benchmarking Dynamic Safety Awareness in Everyday Multi-Turn Multimodal Interactions

Xuankun Rong, Xinhao Deng, Wenzhang Jiang, Ziheng Peng, Siyuan Liang, Wenke Huang, Pablo Arbelaez, Mang Ye

原文摘要

As multimodal large language models (MLLMs) become increasingly integrated into everyday life, their ability to provide safe and reliable assistance in realistic daily activities remains insufficiently explored. Existing safety benchmarks primarily focus on isolated harmful requests or adversarial scenarios, overlooking the safety risks that may arise as ordinary tasks unfold. In practice, users pursue legitimate goals through multi-turn, multimodal interactions, where seemingly benign requests may become safety-critical when considered alongside earlier actions and visual observations. This calls for Dynamic Safety Awareness, the ability to track evolving task conditions, recognize implicit contextual risks, and provide safe and helpful assistance. To systematically evaluate this capability, we introduce DailySafe, a benchmark comprising 195 naturalistic multi-turn, multi-image interactions across 10 everyday domains and 42 task categories. Grounded in authentic user dialogue topics and documented safety knowledge, DailySafe captures realistic scenarios where safety-critical evidence is progressively revealed across conversational turns and visual observations. Using case-specific safety annotations, DailySafe assesses whether MLLMs can recognize and appropriately address evolving risks while supporting users' legitimate goals, bringing multimodal safety evaluation closer to real-world everyday AI assistance. DailySafe is publicly available at: https://github.com/XuankunRong/DailySafe.

cs.CR

新论文 · v1arXiv:2611.26297

Exact guarantees and faster algorithms for $k$-rollercoasters

Sungmin Kim, Florin Manea

原文摘要

For $k\ge3$, a $k$-rollercoaster is a sequence of distinct values whose maximal increasing and decreasing runs all have length at least $k$. We discover the maximum guaranteed length $f_k(n)$ of $k$-rollercoasters appearing as subsequences of $n$-point permutations. In particular, letting $q=k-1$, we prove that $f_k(n)= \lceil n/q\rceil$ for $n\ge2q^2$, $f_k(n)= 2q-\lfloor \sqrt{2q^2-n}\rfloor$ for $q^2<n<2q^2$ and $f_k(n)= 0$ otherwise. We prove that the guarantees are tight by constructing an $n$-point permutation whose longest $k$-rollercoaster has exactly $f_k(n)$ points. Our proof extends Seidenberg's argument [Journal of the London Mathematical Society, 1959] for proving the Erdős--Szekeres theorem by representing points in a subsequence with respect to the lengths of longest monotonic (increasing and decreasing) subsequences that reach each point. The combinatorial proof yields a deterministic comparison-based algorithm that finds a rollercoaster of length at least $f_k(n)$ in $O(n\log f_k(n))$ time and $O(n)$ space for $n>q^2$. Independently, we give an $O(nk\log k)$-time, $O(nk)$-space algorithm for a longest $k$-rollercoaster, improving the previous $O(nk^2)$ bound. We use the dynamic program of Gawrychowski et al. [STACS 2019, Algorithmica 2022], and process its weighted predecessor queries through monotone subsequences with finger-search trees. Both algorithms return such subsequences.

cs.DM · cs.DS

新论文 · v1arXiv:2611.26296

SKILL.PNG: Learning Agent Skills in Pixel Space

Maximilian Seeth, Chengzhi Martin Hu, Marie Kempkes, Paul Röttger, Leo Schwinn

原文摘要

AI agents are commonly specialized for new tasks and domains using skills, i.e. natural language instructions placed in their context. However, the discrete nature of textual skills prevents continuous optimization. Gradient-based approaches such as finetuning, on the other hand, are typically model-specific, preventing skill transfer across different agents. Since many agents today are built on vision-language models (VLMs), we can address these limitations by introducing Skill.png: a method for obtaining skill-like image inputs whose pixels are optimized with gradient descent through the vision encoder of a frozen VLM. Image skills are compatible with any VLM, and a single image can be optimized jointly for an ensemble of models. We show that Skill.png significantly outperforms state-of-the-art textual skills optimized using frontier LLMs in 9 of 16 settings (across 4 VLMs and 4 benchmarks) while requiring only 64 to 256 image tokens instead of roughly 900 to 2000 text tokens at inference time. Hybrid skills, i.e. text and image skills jointly optimized, further improve agent performance. Moreover, an image optimized with an ensemble of VLMs can successfully transfer across the models in the ensemble. Skill.png thus presents the first agent skill that can be optimized with gradient descent while retaining transfer benefits of text skills. Our code is available at: https://github.com/omseeth/skill.png

cs.LG · cs.CV

新论文 · v1arXiv:2611.26291

Who Moved My $Z$ Boson? Revealing Resonance Features Inside a Neural Network

Kevin Alberto Urquía Calderón, Midori Kato, Inar Timiryasov, Oleg Ruchayskiy

原文摘要

Methods used in mechanistic interpretability have revealed human-aligned concepts inside language and image models. In this paper, we search for physics concepts inside a neural a generative collider physics model trained on real LHC data (ShellFlow). We discover features inside ShellFlow that represent resonances, such as the $Z$, $J/ψ$, and $Υ$. The network was never told which muons come from a resonance, it was only trained to generate the kinematics of the final-state particles. We use these features to alter aspects of the $Z$ boson: we change its mass between $\sim80$ and $105$ GeV, and removing such a feature from the neural network produces a broader $Z$ peak. In both cases the rest of the invariant mass spectrum remains mostly unchanged. The feature was built from the gradients of the neural network, and its selectivity was built using pattern recognition methods. A generative particle physics model trained on unlabeled data can be modified internally to change a physical quantity.

hep-ph · cs.LG · hep-ex · physics.data-an

版本更新 · v2arXiv:2611.22476

CheckCo: Checkpoint-Coordinated Load Balancing for Skewed Event Streams at Scale

Muhammad Anis Uddin Nasir, Reza Sadraei

原文摘要

Event streams are rarely uniform: a few dominant keys can generate orders of magnitude more events than the rest, overloading the workers that receive them and capping throughput. We present CheckCo, a checkpoint-coordinated load-balancing algorithm built on a dynamic oracle that estimates per-key frequencies from the live stream, with no prior statistics. Workers count events per key locally; at each checkpoint barrier, the counts are merged into a partitioning function that divides each key into a number of splits roughly proportional to its estimated frequency and packs the splits onto workers, and this function routes the next checkpoint window. We derive approximation bounds on the resulting load imbalance from classical scheduling results and bound its total key fan-out. On a production pipeline processing over 100 billion events per day, the most loaded worker receives only 9.8% more events than the average over a day (imbalance ratio 1.10), against 8.03 for key-based routing in simulation; in simulation, CheckCo also needs less than half the fan-out of earlier partitioners that reach comparable balance. Shifts in the key distribution are reflected in routing from the next checkpoint on, and the load stays balanced through job restarts.

cs.DC

版本更新 · v3arXiv:2609.39632

Towards Better Exploration in Sequential Test-Time Scaling

Joseph Rance, Fabio Pizzati, Juil Sock, Woody Bayliss, Marc Górriz Blanch, Philip Torr, Adel Bibi

原文摘要

Test-time scaling improves language model reasoning by spending additional compute at inference. However, both classes of existing methods often fail to continue improving over long timescales. Parallel methods repeatedly sample independent answers from the model, scaling poorly on problems the model is unlikely to solve in a single attempt. In contrast, sequential methods build on previous answers to access new ideas, yet so far have not been shown to reach answers beyond those found by parallel scaling. First, we show that sequential scaling often stops improving because it becomes prematurely trapped in an attractor: a set of answers that prevents exploration of different answers once entered. Across 27 combinations of scaling methods, models, and benchmarks, we find that 53.8% of sequential scaling trajectories enter an attractor within four iterations. Second, we show that a simple model-mixing intervention helps escape attractors. This reduces the attractor hit rate by 21.2 percentage points on average, expands solution coverage beyond a compute-matched parallel baseline, and improves accuracy of recursive self-aggregation by at least 2.2 percentage points. Our results motivate refocusing long-horizon test-time scaling from parallel methods to sequential methods that improve previous answers.

cs.LG

新论文 · v1arXiv:2611.26282

What If Chain-of-Thought Is Not Enough?

Marc Jansen

原文摘要

Reasoning capabilities in large language models have evolved from prompting-based methods to internalized model behaviors. In this paper, we investigate whether the internal thinking model of an LLM can be deliberately changed and whether such a change is beneficial. Instead of relying on Chain-of-Thought, we train models to follow Question--Option--Criteria (QOC), a structured decision process that decomposes a task into explicit questions, competing options, and evaluation criteria. We present a three-generation development pipeline that ranges from a basic QOC decision core to richer answer synthesis and statistically enriched QOC reasoning. We then evaluate the resulting models with respect to both internal consistency and output quality. Across the reported experiments, QOC-based fine-tuning improves answer quality relative to non-fine-tuned base models and yields particularly strong gains once models are large enough to execute the underlying QOC computations reliably. The results suggest that the internal thinking model of an LLM is trainable and that structured alternatives to Chain-of-Thought can provide a promising path toward more reliable, interpretable, and task-adapted decision support.

cs.CL · cs.AI

新论文 · v1arXiv:2611.26276

I See You: Initial Multi-Robot LiDAR Registration with Mutual-Observation Checks

Jonathan Lichtenfeld, Oskar von Stryk

原文摘要

Compared to single-robot deployments, multi-robot teams can significantly improve search-and-rescue (SAR) mission success by covering large areas in parallel. To collaborate effectively, these robots must be registered in a common reference frame. Standard registration methods typically rely on external infrastructure or significant map overlap, but real deployments require infrastructure-free, stationary initial alignment for immediate operation. While global LiDAR point cloud registration addresses this, existing single-scan methods often fail silently in aliased or degenerate environments. Approaches scaling beyond two agents also remain rarely evaluated in real-world scenarios. We propose a centralized, deployment-ready framework for pre-mission multi-robot registration. Our system performs pairwise coarse-to-fine alignment and actively rejects impossible pose hypotheses via deterministic plausibility checks. We validate the framework on a real-world custom dataset of four synchronized robots in various environments with ground truth. The checks reject more than a third of the incorrect pairwise registrations while falsely rejecting less than 1% of the correct ones, and reduce the number of team registrations with a wrong robot pose by 38%. Dataset and code are publicly available.

cs.RO

版本更新 · v2arXiv:2611.17794

Federated Physics-Informed Thermal Field Prediction Across Unseen Geometries in Distributed Additive Manufacturing

Amirul Islam Saimon, Zhenyu James Kong

原文摘要

In additive manufacturing (AM), each change in part geometry requires a new thermal simulation, which makes design evaluation over many candidates costly. Geometry-aware models reduce this cost by predicting thermal fields on unseen parts with a single learned model, but they assume that diverse geometries are available centrally. This assumption is restrictive when each manufacturing site holds only a limited set of proprietary part designs that it cannot share. We propose Fed-PIGANO, a federated framework that trains physics-informed geometry-aware neural operator (PI-GANO) models at individual sites and aggregates their geometry encoders and prediction networks without sharing part geometries. We evaluate the framework on a 2D steady-state thermal benchmark for metal AM, with geometries from five polygonal families distributed across three sites under four scenarios that range from identical to strongly different family compositions. Over seven replications, Fed-PIGANO achieves mean relative L2 errors of 1.83% to 2.04% across all 12 scenario-site cases, compared with up to 20.46% for local-only training, and consistently yields lower PDE residuals. Its prediction accuracy is comparable to that of a centralized model trained on the pooled geometries of all sites. These results demonstrate that federated learning lets manufacturing sites benefit from each other's geometries without sharing them, enabling rapid thermal prediction on new part designs for tasks such as shape optimization, inverse design, and uncertainty quantification.

cs.LG

版本更新 · v2arXiv:2611.21472

Event-Triggered Visual Perception for Real-Time Harvest Outcome Estimation in Mechanical Blueberry Harvesting

Nicolas Miroslav Husár, Jelle Driessen, Petra Bosilj, Başak Sakçak

原文摘要

Mechanical blueberry harvesting requires a balance between removing ripe fruit and avoiding premature removal of unripe berries that could remain on the bush for a later harvest. However, operators generally lack real-time information about the maturity composition of the fruit being collected. This study develops an event-triggered machine-vision system that measures the maturity of harvested blueberries directly on the harvester. When a filled crate is moved by the machine, an RGB image is automatically captured and analysed using a three-class detector that identifies ripe, semi-ripe, and unripe berries. The system operates locally on the existing CPU-only industrial computer and therefore requires neither continuous image processing nor dedicated GPU hardware. During field testing, 79 crate images containing 48,634 visible blueberries in manually verified reference annotations were evaluated. The vision system estimated an overall ripe-fruit fraction of 90.22%, compared with 90.97% determined manually. Per-image ripe-fruit estimates showed a mean absolute error of 0.935 percentage points and a Pearson correlation of r=0.967. Maturity estimates remained similar between the two sides of the harvester for which the light conditions varied despite poorer absolute counting performance under direct sunlight. All field events were processed within the available 14 s per-side crate interval. The proposed approach provides a practical means of quantifying one component of harvest selectivity while the machine is operating. Such information could support operator decision-making and, when combined with measurements of fruit recovery and losses, contribute to future feedback-based control of mechanical harvesting.

cs.CV

新论文 · v1arXiv:2611.26266

Cooling Noisy Population Protocols -- Vanishing-Gain Averaging and Localisation under Persistent Errors

Leszek Gąsieniec, Łukasz Kuszner, Paul Spirakis, Grzegorz Stachowiak

原文摘要

We study noise-tolerant coordination in anonymous population protocols whose agents interact in uniformly random pairs, maintain real-valued labels, and have no global clock. Each agent cools its updates using a gain $γ_k=(k+1)^{-p}$ computed from its own local interaction counter. First, for pairwise averaging with independent communication errors drawn from a fixed centred finite-variance distribution, we prove convergence with probability 1 to a common finite random value for every $1/2<p\le1$, and derive convergence-rate exponents under the same assumptions. Second, for one-dimensional localisation with fixed non-degenerate Gaussian displacement errors, we show that the one-sided RightAlign rule rectifies centred noise and cannot stabilise; a signed update based on the relative-position discrepancy restores convergence to the true agents locations up to one finite random translation. Third, we analyse the setting in which both communication errors and displacement-measurement errors depend on the physical distance between the interacting devices. For additive independent Gaussian errors, the two sources combine into one centred effective error whose variance is the sum of the distance-dependent component variances. The signed updates protocol remains convergent for every fixed finite geometry, and the average combined variance determines the leading common-translation fluctuation. These results distinguish cooling-compatible signed corrections from one-sided updates that turn persistent noise into drift.

cs.DC

新论文 · v1arXiv:2611.26264

A Statistical Framework for Training Data Auditing of Large Language Models

Shengjie Niu, Yeheng Ge, Jian Huang

原文摘要

Training-data auditing asks whether data of interest were used to train a large language model (LLM), a question central to privacy auditing, copyright protection, and benchmark-contamination detection. These concerns are particularly relevant to the use of copyrighted books and scientific papers in pre-training, as well as synthetic text and medical question-answer records in fine-tuning. In practice, training membership signals may be concentrated in only a few passages of a long document, making it important to aggregate evidence within each document without diluting these localized signals. Beyond individual documents, auditing a target collection requires an overall assessment based on the document-level evidence. In this paper, we propose a unified statistical framework for document-level membership inference, target-collection global auditing, and suspicious-subset identification. We integrate complementary chunk-level membership evidence with Cauchy combination to construct document scores for document-level membership inference. The document scores and their calibrated p-values further enable an overall assessment of training-data collection use and the identification of suspicious documents through multiple testing. Under the stated exchangeability conditions, we establish finite-sample validity of document-level p-values, type-I error control for global auditing, and false discovery rate control for subset identification. Case studies on BookTection, Pile-arXiv, Cosmopedia, and HealthCareMagic demonstrate the effectiveness and reliability of the proposed framework in auditing pre-training and fine-tuning data.

stat.ML · cs.LG · stat.AP

新论文 · v1arXiv:2611.26262

Digitization of Analogue Gauges using Computer Vision

Erico Kayumba Mutonkole, Olasupo Ajayi, Omowunmi Isafiade

原文摘要

Analogue gauges remain prevalent in manufacturing industries for measuring physical quantities, yet manual monitoring by operators introduces human error and operational inefficiency. This research developed and evaluated an automated gauge reading system using computer vision and deep learning techniques. Three hybrid approaches were implemented and compared: OpenCV with Scikit-Image (traditional computer vision), OpenCV with ResNet18, and OpenCV with VGG19 (deep learning approaches). A comprehensive dataset of 1,848 pressure gauge images (0-10 BAR range) was curated through web scraping, synthetic generation, and augmentation techniques. The experimental results demonstrate that ResNet18 significantly outperforms the alternatives, achieving an accuracy of 97.3%, compared to VGG19's 64.4% and Scikit-Image's 63.8%. The study validates the effectiveness of residual learning architectures for industrial gauge digitization, providing a robust foundation for Industry 5.0 automation applications.

cs.CV · cs.AI

新论文 · v1arXiv:2611.26261

Similarity-based OSF Logic for Flexible SPARQL Query Answering

Gian Carlo Milanese, Gabriella Pasi

原文摘要

We present an updated version of fosf, a reasoner for fuzzy order-sorted feature (OSF) logic, with support for flexible SPARQL query answering over RDF knowledge graphs. Fuzzy OSF logic is a knowledge representation and reasoning language where feature symbols denote functions and sort symbols denote fuzzy sets. Sorts are organized in a fuzzy subsumption relation that extends to OSF terms, record-like structures representing classes of entities. The unification algorithm for these structures provides a calculus of fuzzy type subsumption. The latest release of fosf introduces support for similarity-based reasoning by extending the OSF language with a similarity relation among sorts, alongside a translation engine for compiling OSF terms into standard SPARQL. Queries expressed as OSF terms undergo fuzzy ontology-aware rewriting prior to translation. This process incorporates an OSF theory of sort definitions, feature domain and range declarations, and fuzzy subsumption and similarity relations through fuzzy OSF constraint normalization. This rewriting enables flexible query answering by returning approximate solutions, allowing queries that would otherwise be inconsistent with the underlying ontology to yield relevant results.

cs.AI · cs.DB · cs.LO

版本更新 · v2arXiv:2611.00172

From Fragmentation to Fusion: A Survey and Roadmap for Omnimodal Embeddings

Ziyin Zhang, Yuyu Guo, Ying Zhang, Siqiao Xue, Zihan Liao, Jin Qin, Wenjie Yang, Siyuan Yang 等 18 位作者

原文摘要

Embedding models underpin virtually every modern AI system, from search engines to recommendation systems. Despite shared mathematical foundations, research on embedding models remains fragmented by modality: the communities develop largely in isolation, seldom exchanging insights. We argue that this fragmentation obscures a deeper convergence. Driven by contrastive learning, Transformer architectures, and a granularity shift, embedding research across modalities is converging toward a common set of principles, even as modality-specific challenges remain underexplored. To reason across this convergence without conflating it, we propose a framework of three progressively harder capabilities: coverage, comparability, and compositionality. Three paths toward unification satisfy these in turn: transformation broadens coverage, alignment enables comparability, and joint embedding, the terminus we advocate, aims at compositionality. This position paper traces the resulting evolution, providing the first unified, cross-cutting treatment of omnimodal embedding research.

cs.CL · cs.AI

新论文 · v1arXiv:2611.26256

SkillBridge: Cost-Aware Diagnosis and Repair of Cross-OS Compatibility Defects in Agent Skills

Anjie Xu, Zixing Wang, Yifeng Cai, Leye Wang

原文摘要

LLM agents increasingly reuse executable capabilities through skills, but a skill that works on one OS may fail on another because OS assumptions are spread across guide text, scripts, metadata, install contracts, and local entrypoints. Diagnosing such failures by running every skill on every OS is expensive: many executions spend model tokens, runner time, and review effort before revealing whether the failure is truly OS-related. We present SkillBridge, a contract-based workflow with three stages: static analysis, dynamic validation, and repair. SkillBridge first screens 3,270 skill-target-OS cases, covering 1,090 skills across Linux, macOS, and Windows, to find OS-sensitive contract evidence. It then runs dynamic tasks and root-cause review on selected cases to confirm whether a failure is caused by an OS assumption, and repairs the contract field that caused the failure, such as guide text, package scripts, dependencies, or platform declarations. Repair raises the reviewer-judged target-task pass rate from 30.6% to 38.4%, a gain of 7.8 percentage points. A retrospective Linux/macOS budget analysis further shows the efficiency effect: SkillBridge reaches 38 confirmed OS issues with 185 dynamic validations, where uniform random selection would require about 865 validations in expectation.

cs.SE · cs.AI

新论文 · v1arXiv:2611.26255

STAGE: Spatio-Temporal Augmented Graph Expansion for Weakly Supervised Cross-Tweet Event Causality Discovery

Hieu Minh Duong, Todd Gary, Eugene Levin, Long Nguyen

原文摘要

Causal relations in disaster-related social media of- ten span independent posts, making cross-tweet causal discovery difficult to supervise and model at scale. We propose STAGE, a framework that separates scalable cross-tweet weak-supervision construction from spatio-temporal relational learning over event occurrences. Starting from local causal seeds, STAGE retrieves semantically related event occurrences across tweets and uses a causal scorer to construct weakly labeled cross-tweet pairs. These pairs supervise a multi-head Graph Attention Network over semantically enriched event representations and a spatio- temporal context graph. We evaluate STAGE on California Wildfire and Hurricane Harvey using human-gold cross-tweet test sets and 15 baselines. Compared with local-only supervision, the constructed cross-tweet supervision improves STAGE AUPRC by 0.340 on Wildfire and 0.107 on Hurricane. STAGE achieves in-domain AUROC of 0.885 on Wildfire and 0.710 on Hurricane. Cross-disaster experiments reveal asymmetric transfer, highlighting sensitivity to dataset-specific spatio-temporal shifts. These results demonstrate the value of scalable cross-tweet supervision combined with relational event modeling for causal learning across fragmented disaster reports.

cs.CL · cs.AI

新论文 · v1arXiv:2611.26254

Prism: Hierarchical Text Detection with Minimalist Design

Yuchen Su, Xuesheng Wang, Zhilong Ji, Jinfeng Bai, Shijian Lu, Zhineng Chen

原文摘要

Hierarchical text detection aims to localize words, text lines, and paragraphs while parsing their structural relationships. It provides essential structural cues for visual text understanding. To maximize accuracy, existing methods typically rely on complex multi-scale feature fusion necks and heavy-weight heads, resulting in bloated architectures and low inference efficiency. In this paper, we argue that a sufficiently pre-trained backbone can effectively replace these sophisticated external modules, while simple geometric inclusion suffices for hierarchical text structural parsing. Thus, we propose Prism, a minimalist framework for hierarchical text detection. Prism performs multi-granularity detection by attaching parallel lightweight heads to a single-scale backbone feature map, covering words, text lines, and paragraphs, and reconstructs the structural hierarchy via an efficient geometric inclusion algorithm. In addition, we systematically compare representative lightweight head archetypes and show that pixel-level regression offers the best accuracy-efficiency trade-off in this setting. Experiments on multiple public benchmarks show that our significantly simplified architecture achieves state-of-the-art (SOTA) performance with remarkable efficiency. Specifically, it runs $1.7\times$ faster than LRANet on CTW1500 while achieving higher accuracy, and surpasses the current SOTA method, OmniParser V2, by over 6 PQ points on the hierarchical HierText dataset. Code will be released soon.

cs.CV

版本更新 · v2arXiv:2603.23875

Self-Evolving Multi-Agent Framework for Efficient Decision Making in Real-Time Strategy Scenarios

Li Ma, Hao Peng, Yiming Wang, Jie Liu, Kongjing Gu, Kangli Zi, Na Han, Hui Lin

原文摘要

Large language models (LLMs) have demonstrated exceptional potential in complex reasoning,pioneering a new paradigm for autonomous agent decision making in dynamic settings. However, in Real-Time Strategy (RTS) scenarios, LLMs suffer from a critical speed-quality trade-off. Specifically expansive state spaces and time limits render inference delays prohibitive, while stochastic planning errors undermine logical consistency. To address these challenges, we present SEMA (Self-Evolving Multi-Agent), a novel framework designed for high-performance, low-latency decision-making in RTS environments. This collaborative multi-agent framework facilitates self-evolution by adaptively calibrating model bias through in-episode assessment and cross-episode analysis. We further incorporate dynamic observation pruning based on structural entropy to model game states topologically. By distilling high dimensional data into core semantic information, this approach significantly reduces inference time. We also develop a hybrid knowledge-memory mechanism that integrates micro-trajectories, macro-experience, and hierarchical domain knowledge, thereby enhancing both strategic adaptability and decision consistency. Experiments across multiple StarCraft II maps demonstrate that SEMA achieves superior win rates while reducing average decision latency by over 50%, validating its efficiency and robustness in complex RTS scenarios.

cs.MA

新论文 · v1arXiv:2611.26249

Beyond Covers and Titles: Evidence-First Ranking for Robust Cold-Start Recommendation

Fuyi Wang, Yuxin Cao, Yifan Liao, Renyang Liu, Lin Li, Wei Song

原文摘要

Short-video platforms rank new uploads before anyone has watched them, using content towers that read a video's cover, title and frames. Existing attacks on content-aware recommenders perturb pixels or features and ignore platform re-encoding, and existing defenses train against norm-bounded perturbations that neither match real edits nor preserve recommendation quality. We show with REAP, a realizable attack through {a simulated platform channel (H.264 transcoding, rescaling, cropping and JPEG)}, that packaging edits raise a cold video by 32.0 rank-percentile points in unrelated audiences. We then observe that cold-start ranking does not need the packaging at all: a tower that sees only the video body ranks cold items best. Building on this, we propose Evidence-First Ranking (EFR), which scores cold videos from their body, admits packaging only through a support-gated residual bounded by $γ$, and merges cold and warm rankings by rank percentile, yielding an exact certificate against any packaging edit. On MicroLens-100K, EFR cuts the attack gain by 81% and raises cold-start Recall@100 from 0.1133 to 0.170, while keeping the merged NDCG@10 within 4% of the undefended system.

cs.CV

新论文 · v1arXiv:2611.26248

TwinLab-Bench: Evaluating AI Scientists in Agentic Twins of Real Labs

Yang Wan, Linchao Zhu

原文摘要

AI agents are increasingly expected to act as AI scientists, which requires three increasingly open abilities: carrying out a given computational workflow correctly, choosing the next measurements from a given design space, and designing their own experiments. Existing benchmarks mainly evaluate the first two abilities, in a terminal or in a closed loop that selects from predefined candidates. Evaluating the third ability requires reliably executing an experiment that an agent designs, with readings grounded in a real laboratory. We introduce TwinLab-Bench, which evaluates AI scientists on self-designed experiments in 52 tasks from laboratories in the physical sciences, the life sciences, and engineering. The benchmark supports more than 100 experimental action types, and the agent's report is scored by comparison with a hidden answer taken from real laboratory records. Each task has its own TwinLab agent, an agent that serves as the environment and executes the experiments that the tested agent designs, reading the raw materials of the laboratory and calling calculators that are built from its records. Compared with a language model that sees only the task description, the TwinLab agent almost eliminates readings that deviate from the real records and inconsistent answers to a repeated request, and closed-book probes control for answers recalled from memory. We find that these tasks remain hard for frontier models: the strongest, Claude Fable 5.2, averages a score of only 45.0, and we conduct an empirical study of where it fails.

cs.AI · cs.CL · cs.LG

新论文 · v1arXiv:2611.26244

Invariance and Expressiveness: Modal Variations

Martin Otto

原文摘要

This contribution focuses on bisimulation invariance as the hallmark of modal model theory and of modal modelling. It exemplifies traditional as well as more recent ramifications \&\ extensions of classical results -- involving variant modes of bisimulation equivalence and matching modalities also beyond plain Kripke structures, and emphasising especially the technical challenges in finite model theory and other non-elementary settings. Main results to be discussed revolve about the theme of expressive completeness phenomena: beside expressive completeness under bisimulation invariance in relation to first-order background logics, in the style of van Benthem--Rosen characterisations, this also concerns maximality results under criteria form abstract model theory, in the style of Lindstroem theorems.

cs.LO · math.LO

版本更新 · v2arXiv:2611.23010

PhysScope: Agentic Multimodal Physics Reasoning with Grounded Visual Memory

Haoyang Liu, Kecheng Liang, Xinyu Li, Weixing Chen, Yang Liu

原文摘要

Vision-language models (VLMs) can correctly interpret physics diagrams yet apply constraints outside the states or conditions in which they hold, causing premise errors to propagate through subsequent calculations. We introduce PhysScope, an inference-time visual harness that supports self-correction of these scope mismatches without updating model weights. PhysScope enables the model to link physical scopes directly to its visual observations and explicitly constructs derived views to support reasoning. The harness imposes explicit constraints on state distinctions, conditions, and physical scopes during model reasoning, and checks agent-proposed revisions against sources and scopes. Accepted revisions invalidate registered dependents, thereby maintaining scope-aware working memory. On PhysAlign, PhysScope achieves higher solving scores than direct solving across all six evaluated VLMs. With Gemini-3.8-flash, it outperforms Canvas-CoT by 9.34 percentage points and substantially improves solving accuracy on the out-of-distribution (OOD) PhysUniBench benchmark. Ablation studies support explicit scope management and dependency maintenance as design principles for multimodal physics reasoning agents.

cs.AI

版本更新 · v2arXiv:2610.33131

Locally eventually onto cellular automata

Jan Kristian Haugland, Nadia S. Larsen, Tron Omland, Henrikke G. Rustad

原文摘要

We give a new checkable criterion to ensure that a one-dimensional cellular automaton on a finite alphabet is open and locally eventually onto. In this setting, openness is equivalent to being n-to-1 for some n and therefore implies surjectivity. Bipermutive cellular automata are known to be open and locally eventually onto, while open cellular automata that are neither bipermutive nor bijective appear to have received less attention. Building on Sutner's work with de Bruijn graphs, we describe a method for deciding openness and at the same time determining n. We then introduce the notion of block-regularity of local rules as a generalization of bipermutivity and prove that it implies openness. We further identify two conditions that, together with block-regularity, ensure that every nonempty cylinder set is mapped onto the whole configuration space after a finite number of iterations, and hence that the cellular automaton is open and locally eventually onto. The appendix provides the algorithms that check these finite criteria and then presents examples of open, locally eventually onto, non-bipermutive cellular automata for small diameters.

cs.FL · cs.DM · math.CO · math.DS · nlin.CG

版本更新 · v3arXiv:2608.29519

FuncRoom-Agent: Sequential Feed-Forward 3D Functional Indoor Scene Generation

Hao Feng, Zhi Zuo, MingJian Liang, Jingyu Hu, Xiaowei Hu, Liupengfei Wu, Dian Zhang, Guoxin Fang 等 9 位作者

原文摘要

We introduce Function-Room Generation, a new indoor 3D scene generation setting that creates rooms supporting explicit functional goals rather than merely visually plausible layouts. Existing agentic and executable methods improve controllability, but often depend on costly test-time generate--evaluate--revise loops, making functional room generation slow and computationally expensive. We address this challenge with three technical contributions. First, we design a recursive domain-specific language to effectively organize the hierarchical object compositions required by functional rooms, from room structure and major furniture to dense support-surface and nested small objects. It represents rooms as staged executable programs with explicit geometric and functional relations. Second, we propose a sequential feed-forward scene construction framework that distills recursive construction traces into a scene construction expert. At inference time, the expert writes executable DSL code stage by stage, and a deterministic executor directly instantiates each stage without teacher agents, online critics, or iterative repair. Third, we introduce ScenePRM, an execution-grounded process reward framework that improves the expert through reinforcement learning with functional, geometric, relational, and future-constructability feedback. We further establish a function-oriented benchmark and show state-of-the-art performance on both general indoor scene generation and function-room generation, achieving stronger functional completeness, relation correctness, geometric executability, and generation efficiency.

cs.CV

新论文 · v1arXiv:2611.26242

FastRoverVLA: Fast Vision-Language-Action Execution for Off-Road Autonomous Driving

Changtao Zhao, Yingxue Guan, Li Wang, Shijie Zhao, Yuhang Zhang, Shengkai Zhang, Qing Wang, Ziying Song

原文摘要

Off-road vision-language-action (VLA) models generate scene-conditioned plans, but frequent trajectory updates can repeatedly invoke expensive multimodal inference. Reusing a prediction reduces this demand while leaving its commands exposed to changes in vehicle motion. FastRoverVLA addresses this mismatch by decoupling visual plan generation from motion-conditioned execution. Its training-free interface maintains decoded plans between visual predictions. A speed-curvature action buffer is aligned with measured motion at each update, integrated into a local trajectory, and advanced by consuming the current action. The corrected remainder is written back to the buffer, preserving motion corrections across successive updates. A bounded refresh rule normalizes speed and curvature variations within a newly decoded plan and assigns a short or long reuse budget according to the resulting plan-roughness score. The interface requires neither backbone features nor an additional learned driving policy. Over a 3 s horizon, independent real-request evaluation achieves average displacement error (ADE) and final displacement error (FDE) of 0.328/0.596 m on ORAD-3D and 0.266/0.526 m on RELLIS-3D, reducing FDE by 18.0% and 36.7% at request rates of 6.0% and 4.8%, respectively. These runs retain lower errors across four backbones and both datasets and reduce Qwen3-VL request-processing cost by factors of 16.6 and 20.8 under serial replay, while mechanism and motion-only controls identify persistent state correction as the main source of the observed accuracy benefit. The source code and evaluation materials are publicly available at https://github.com/ADEPT-ORG/FastRoverVLA.

cs.RO · cs.AI

版本更新 · v2arXiv:2610.41373

Queryable Gaussian View Index: Text Retrieval and Selective Camera Localization

Tianyu Xiong, Rui Li, Jiaqi Yang

原文摘要

We present Queryable Gaussian View Index (QGVI) for querying existing Gaussian scene assets and their associated calibrated reference data. Text-view retrieval and selective RGB camera localization return poses in the asset's coordinate frame. QGVI-T turns Gaussian-rendered views into a language-searchable index of scene locations, binding structured captions to known camera poses and place identifiers. Semantic and lexical retrieval select views from distinct places without online rendering, VLM calls, or a scene-specific pose network. The image route, QGVI-I, filters LoGS-based geometric estimates using distinct inlier query keypoints. It omits photometric refinement and preserves accepted pose coordinates. On nine development scenes, QGVI-T achieves 58.3% Top-1 and 78.3% Top-5 joint relevance-and-validity success, compared with 26.1% and 34.6% for our CityLoC reimplementation with refinement. QGVI-I achieves 97.3% scene-mean pose success at 1 m/2 degrees, with pooled false-acceptance and false-rejection rates of 0.707% and 1.142%. A paired cached evaluation retains all 1,775 initializer poses correct at this threshold. Recorded median text query latency is 0.020 s. Matched controls show competitive BM25 retrieval and slightly lower false acceptance for thresholded full LoGS; grid augmentation suggests modest gains on novel-view-derived descriptions. We report model-judged semantic success separately from source-camera recovery, with source-verified or estimated scales for geometric evaluation.

cs.CV

版本更新 · v2arXiv:2606.16308

Physics-Informed Sensitivity Analysis for Enhanced Structural Health Assessment: Test-Case for a Mixed Steel-Concrete Bridge

Jacopo Bonari, Francesca Marsili, Max von Danwitz, Alexander Popp

原文摘要

Bridges are vital components of transportation systems, that serve as essential links ensuring the safe and efficient movement of people, goods, and emergency responders, especially during crises. With aging infrastructures, increasing traffic volumes and loads, and the intensifying impacts of extreme weather events due to climate change, the development of effective physics-informed structural health monitoring (SHM) frameworks has become critically important, more so when combined with sensitivity analysis (SA), which identifies the most influential structural parameters in the bridge's response. To support this, a high-fidelity, physics-based numerical model of a full-scale, two-span, mixed steel-concrete test bridge has been developed. This model serves as a virtual replica of a real structure located at the University of the Bundeswehr Munich. The numerical model is used as a complementary tool to improve prognostic capabilities and quantify uncertainty. A SA study is conducted to evaluate the structure's response under various mechanical conditions. Assessing these operational variations' effects on structural behavior forms part of an integrated, systematic evaluation framework aimed at combining SHM and SA.

cs.CE

新论文 · v1arXiv:2611.26239

Teaching Vision-Language-Action Models to Stop Safely

Zheyuan Liu, Chuhan Wang, Jinduo Guo, Yue Huang, Xiangchi Yuan, Ningshan Ma, Meng Jiang

原文摘要

Vision-language-action (VLA) models enable robots to perform diverse tasks from visual observations and language instructions. While prior work has explored task suppression and refusal, stopping prohibited behavior once execution is underway and controlling the resulting physical response remain challenging. Our evaluation reveals that policies which suppress a task from its initial state can still complete it when taking over partway through execution. Even when the task remains unfinished, the robot may drop a held object, making non-completion an incomplete measure of safety. To address these challenges, we introduce State-Aware Fallback Imitation (SAFI) for tasks where holding provides an appropriate alternative response. SAFI comprises two stages, (1) fallback target construction, which assigns stationary arm commands and consistent gripper targets throughout prohibited-task demonstrations, and (2) joint policy adaptation, which learns these targets alongside the original actions of retained tasks. This supervision teaches an explicit alternative response at intermediate execution states while maintaining the robot's other skills. Extensive experiments with OpenVLA-OFT across LIBERO and BadLIBERO tasks evaluate prohibited completion, physical incidents, and retained-task performance. On the evaluated LIBERO tasks, SAFI reduces aggregate target success after takeover to 1.3\%, with no recorded physical incidents or action saturation, while preserving high retained-task success.

cs.RO