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:2026-11-21 12:19 · 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 05:22 — 2026-11-22 05:22(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:2026-11-21 12:19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 21,490 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
新论文 · v1arXiv:2611.21702

Watermark Evidence under Open-Weight LLM Modification: Exact Bounds for Low-Rank Output Watermarks

Prashant Shekhar, Dumindu Samaraweera, Caroline Howard

原文摘要

Open-weight language models can continue generating after their released weights are modified, while a watermark verifier still scores outputs against the original base and marked models. We study how such modifications change the evidence available to an OpenStamp-style verifier. At each shared prefix, we represent the modification as a residual in the next-token logits. We derive an exact finite-vocabulary lower bound on the expected log-likelihood-ratio evidence under a residual-span constraint, along with a sharp span-only deviation bound. We also characterize the first-order evidence shift through a covariance term with an explicit second-order remainder, and determine the residual span needed to reach a target evidence level. For sequence-level detection, we derive an exact conditional exponential-moment bound and combine it with a supermartingale argument and a distribution-free order-statistic tolerance bound. This yields a high-confidence upper bound on miss probability after attack selection on calibration data and evaluation on independent certification continuations. In experiments with OpenStamp on Llama-2-7B and Mistral-7B-v0.3, INT8 quantization and 30% pruning retain test true-positive rates of 85.6-94.8%, while 500-step LoRA fine-tuning lowers them to 28.8% and 11.6%. The covariance prediction tracks the measured mean LoRA evidence drift on both models, with no remainder-bound violations across 160,000 test prefixes. Additionally, we observe zero false positives among 500 base-model continuations per model. Through these theoretical and empirical results, the current research provides a better understanding of watermark robustness to model-editing/tuning attacks.

cs.CR · cs.AI · cs.CL

版本更新 · v3arXiv:2608.14400

Ten simple rules for non-visual, reproducible and accessible bioinformatics

Jacqueline G. Kientsch, Stephan C. F. Neuhauss, Izaskun Mallona

原文摘要

Bioinformatics workflows rely heavily on visual representations. Quality-control plots, cell embeddings, heatmaps, genome-browser tracks, and interactive dashboards are not merely illustrations, but instruments for making analytical decisions. For blind and low-vision researchers who use screen readers, braille displays, or audio-based interfaces, these create a barrier: the evidence used to justify an analysis is often encoded in visual form, while the underlying decision remains undocumented. We argue that non-visual accessibility and computational reproducibility are closely aligned, as they both require analyses to be transparent and to record why decisions were made. We present ten simple rules for non-visual bioinformatics, covering plots as decision records, cautious use of AI-generated figure descriptions, accessible computing environments, text-first literate programming, structured data and metadata, compact object summaries, accessible publication formats, collaboration practices, shared community infrastructure, and accessibility as part of FAIR research. The intended audience is computational biologists and developers. Using single-cell RNA-seq as a running example, we show that the accessible equivalent of a plot is a structured decision record. That is, a plot companion that goes beyond storing the underlying data by also stating the purpose of the analysis and the resulting quantitative evidence and uncertainty. We argue that treating accessibility in this way makes bioinformatics more inclusive and also more transparent and auditable.

q-bio.GN · cs.HC

版本更新 · v2arXiv:2611.09387

A Bridge from Paste to Place: Physics-Guided One-Step Image Composition via Object-Scene Interaction

Hongzhen Li, Youwei Pan, Yingfang Zhu, Sen Zhu, Fengjie Zhu, Leilei Cao

原文摘要

Realistic image composition makes a pasted object appear naturally present in a scene while preserving the pasted layout and fine foreground and background details. Reference-based insertion methods preserve overall object identity but can alter pose and fine details, often at substantial computational cost. Foreground harmonization and shadow generation address individual aspects of this task, but neither alone ensures natural integration. An efficient, unified solution remains an open challenge, and large-scale, high-quality datasets and benchmarks for this task are lacking. To address these challenges, we introduce Paste2Place, an end-to-end, physics-guided flow-based model that learns a direct latent bridge from pasted inputs to realistic composites, guided by image-space corrections analytically derived from predicted physical components of object and scene appearance changes. To support training and evaluation, we introduce P2P-Data with 86K manually reviewed synthetic and real-scene training pairs, including dense physical annotations from our Blender rendering and validation pipeline for the synthetic subset. P2P-Bench combines paired compositions and manually pasted inputs from collected images into 1.5K examples for evaluating composition under user-chosen placements. Extensive qualitative and quantitative experiments demonstrate that Paste2Place achieves substantial advantages in image composition quality and inference speed across diverse scenarios.

cs.CV

版本更新 · v2arXiv:2602.05846

Optimal scaling laws in learning hierarchical multi-index models

Leonardo Defilippis, Florent Krzakala, Bruno Loureiro, Antoine Maillard

原文摘要

In this work, we provide a sharp theory of scaling laws for two-layer neural networks trained on a class of hierarchical multi-index targets, in a genuinely representation-limited regime. We derive exact information-theoretic scaling laws for subspace recovery and prediction error, revealing how the hierarchical features of the target are sequentially learned through a cascade of phase transitions. We further show that these optimal rates are achieved by a simple, target-agnostic spectral estimator, which can be interpreted as the small learning-rate limit of gradient descent on the first-layer weights. Once an adapted representation is identified, the readout can be learned statistically optimally, using an efficient procedure. As a consequence, we provide a unified and rigorous explanation of scaling laws, plateau phenomena, and spectral structure in shallow neural networks trained on such hierarchical targets.

stat.ML · cs.LG

版本更新 · v2arXiv:2611.14783

A Multi-Prover Interactive Protocol for Certification of Resolution Refutations

Philipp Czerner, Adrian Krauss, Josia Pietsch, Javier Esparza

原文摘要

A resolution refutation of a SAT-formula $\varphi$ is an independently checkable certificate proving that $\varphi$ is unsatisfiable. However, the refutations of $\varphi$ can be exponentially larger than $\varphi$. So, a verifier needs worst-case exponential time in the size of $\varphi$ to check their correctness. We present ResCertify, an interactive probabilistic protocol in which the verifier interacts with multiple independent, untrusted provers (MIP) to check the refutation with very low probability of error. The verifier runs in linear time in the size of $\varphi$. The provers require time $\mathcal{O}(n \cdot |Φ|)$, where $Φ$ is the resolution refutation and $n$ is the number of variables of $\varphi$. If they can be trusted to act as a multilinear oracle on certain queries, a single prover suffices, and the runtime can be improved to $\mathcal{O}(|Φ|)$. Finally, while the focus of our work is theoretical, we also report on a proof-of-concept implementation of ResCertify.

cs.LO

新论文 · v1arXiv:2611.21275

Optimal Ordering-Free Two-Dimensional Insdel Reed-Solomon Codes via Cross-Ratios

Runqing Qiu, Shixin Zhu, Yang Li, San Ling

原文摘要

Insertion-deletion (insdel) codes correct synchronization errors. By the half-Singleton bound, an ${[n,2]}_q$ code has minimum insdel distance at most $2n-4$. The smallest field size of two-dimensional Reed--Solomon (RS) codes attaining this bound is $Θ(n^3)$. Unlike the minimum Hamming distance, the minimum insdel distance of an RS code depends on the ordering of its evaluation points. An evaluation set is called ordering-free if every ordering of its points gives an RS code attaining the half-Singleton bound. In this paper, we first show that for $n\ge6$ every ${[n,2]}_q$ code attaining the half-Singleton bound is an RS code, and hence $q\ge\binom{n}{3}+2$. Secondly, we show that an ordering-free evaluation set with $n\ge6$ points in $\mathbb{F}_q$ satisfies $n<q^{1/3}+2$, and that it has at most $r+1$ points if $q=r^3$ for a prime power $r\ge3$. Finally, by using cross-ratios, we construct an ordering-free evaluation set with $r+1$ points in $\mathbb{F}_{r^3}$ for every prime power $r$. Hence, the bound $r+1$ is attained for $r\ge3$. Moreover, the constructed set is even robust against permutations combined with insdel errors.

cs.IT

版本更新 · v2arXiv:2404.00551

Gaussian-Channel Regularity and Distribution Learning with Flow Matching

Yuan Gao, Jian Huang, Yuling Jiao, Shurong Zheng

原文摘要

We study distribution learning by flow matching with linear interpolation from a Gaussian source under Gaussian-channel regularity, a condition on the target distribution. For an integer $r\geq2$, we establish spatial regularity of order $r$ for the population velocity, together with temporal Lipschitz continuity on the full interval and local time analyticity before the terminal time. We use these properties to construct a finite multiscale ReLU sieve with a spatial Lipschitz bound independent of the truncation radius. For an exact minimizer of the empirical flow matching risk over this sieve, we obtain an upper bound on the expected Wasserstein-$2$ error of order $n^{-r/(d+2r)}$, up to a logarithmic factor, where $n$ is the sample size and $d$ is the dimension. The bound includes Euler discretization up to time one, without early stopping. The conditions hold at $r=2$ for targets with strongly convex $C^2$ potentials and two-sided Hessian bounds. They also hold at every fixed order $r\geq2$ for distributions obtained by convolving a law of bounded support with a nondegenerate isotropic Gaussian. For sufficiently large fixed constants defining the target class, we prove a minimax lower bound of order $\max\{n^{-1/2},n^{-(r+1)/(d+2r)}\}$.

stat.ML · cs.LG

新论文 · v1arXiv:2611.21274

SURMA: Efficient Fine-Grained Communication Offload for SuperPOD

Haoran Shang, Weifeng Zhang, Mengzhu Li, Huizheng Wang, Sihan Guan, Xinyang Huang, Bowen Liu, Ran Shu 等 17 位作者

原文摘要

GPU SuperPODs underpin large language model (LLM) serving, but growing bandwidth and round-trip times make inter-GPU communication consume increasing compute resources. SM-driven remote memory access occupies shared memory or registers for in-flight data and competes for SM-to-NoC bandwidth. Dedicated engines can free these resources, but must handle fine-grained transfers, down to a 576\,B KV-cache entry. NVIDIA's CopyEngine uses less than 1\% of NVLink bandwidth at 7\,KB granularity. We present SURMA, an on-die Scale-Up Remote Memory Access engine. Adapting RDMA requires overcoming slow doorbell submission, excessive per-application connection state, head-of-line blocking of completion notifications on shared connections, and costly ordering for multipath transfers. SURMA uses a credit-based shared send queue to reduce submission latency from 1.2\,$μ$s to 400\,ns; fused write-with-atomic semantics to share connections while independently notifying each transaction; and Network Per Path Ordering to ensure data arrives before the completion flag without Sender or Receiver Ordering. We implement SURMA in RTL on a two-FPGA prototype and evaluate it with two 8-GPU NVLink servers. At 512\,B granularity, SURMA saturates attainable bandwidth with a single SM, whereas NVLink needs over 14\% of the SMs. SURMA occupies under 0.5\% of GPU area and accelerates inference on four models by 1.05--1.26$\times$ over NVLink.

cs.AR

新论文 · v1arXiv:2611.21273

CAE-Bench: Benchmarking AI Agents for Reusable CAE Solver Development

Zhiyu Zhou, Tianyou Liu, Xinping Yang, Yiyao Liu, Jiayi Dong, Yihan Lin, Haokai Ye, Yifan Lu 等 11 位作者

原文摘要

We developed CAE-Bench, a benchmark to evaluate AI agents on Computer-Aided Engineering (CAE) solver development. A CAE solver is more than a PDE solver; it must be able to generalize across various inputs, such as different boundary conditions, geometries, and material properties. CAE-Bench evaluates the generalizability of AI-developed CAE solvers by providing the same task, such as a heat transfer problem, multiple cases, with each case specifying an input. The AI agent develops a solver for a fixed task using only a few public cases, and the resulting solver is then tested on held-out cases, i.e., cases it has never seen before. We evaluate 12 models across a range of reasoning settings on 80 computational tasks. Our experiments show that even if a solver developed by an AI agent performs well on the public cases, it may even get 0 score on held-out cases. For tasks such as fluid dynamics problems, even the solver developed by GPT-6 Astra performs poorly on held-out cases. A data format and an SDK for task registration are provided, so the researcher can use the benchmark on their own infrastructure. We hope that CAE-Bench will help the community to develop AI agents that can develop reusable CAE solvers that generalize to various inputs.

cs.AI

新论文 · v1arXiv:2611.21701

Hybrid Quantum Selection of Learning Rates in Language-Model Training: Termination Criteria and an Interaction-Guided Schedule Oracle

Wei-Che Hung

原文摘要

Learning-rate choices strongly affect language-model fine-tuning, but the best joint profile across layer groups is generally unknown. This paper studies quantum minimum finding for layer-group learning-rate selection within a hybrid classical-quantum training framework. It combines Durr-Hoyer minimum finding with BBHT search and compares fixed-budget and confidence-based stopping policies using a lookup oracle built from measured profile scores at fixed training checkpoints. The paper then introduces an Interaction-Guided Schedule Oracle that scores and marks joint schedules in superposition without a precomputed score table. Classical one-step loss measurements supply the main, pairwise and three-way interaction effects between layer groups. The circuit adds the effects for each schedule, compares the resulting score with the current baseline score, and marks improving schedules for amplitude amplification. Measured candidates are checked classically before acceptance. Uniform-rate training supplies the initial baseline; using schedules from classical adaptive methods as baselines for joint refinement is left for future work. In closed-loop fine-tuning of a 1.5-billion-parameter language model, each selected schedule drives the next 200 classical training steps. Benchmark accuracies lie within the range observed across five uniform-rate seeds. The results give a working example of how quantum superposition can support adaptive learning-rate selection during training; the remaining quantum limitations are discussed in the paper.

cs.LG

新论文 · v1arXiv:2611.21270

SCOPE: A Physical Execution Latency-Guided Quantum Circuit Compilation Framework

Bolin Zhang, Zhiyuan Zhang, Yongguang Lv, Ruiqing He, Hengliang Guo, Jiandong Shang, Qiang Chen

原文摘要

Quantum computing requires compilers to translate algorithms represented in the quantum circuit model into unitary operations supported by physical devices. Limited coherence time makes physical execution latency an important compilation objective. Gate fusion can shorten pulses, but gate count and depth do not capture fused targets' control demands. Evaluating every candidate with quantum optimal control (QOC) would embed pulse optimization in structural search. We present Schmidt-guided Compilation for Optimized Pulse Execution (SCOPE), driven by an operator Schmidt time surrogate. The target's angular distance from product operators measures the required nonlocal change; dividing it by a coupling-limited evolution-rate bound gives a lower bound on exact implementation time. Trace-angle and waveform constraints complete block scores for critical-path evaluation during genetic search. Local QOC determines final pulse durations. Under a numerical nearest-neighbor control model, all 104 results across 13 instances from four application families have shorter QOC critical-path durations than an adapted efficient pulse generation framework with advanced synthesis for quantum circuits (EPOC). Using eight-run instance means, the equally weighted reduction is 42.50\%, with a geometric mean speedup of 2.00. In a shared six-qubit quantum Fourier transform (QFT) ablation, time-surrogate guidance reduces mean QOC duration by 22.21\% relative to gate-count guidance and 21.01\% relative to depth guidance, validating the surrogate's joint use in fitness evaluation and mutation-region selection.

quant-ph · cs.AR · cs.ET

新论文 · v1arXiv:2611.21268

In-Context Estimation and Prediction for Parametric ODEs

Abdullah Ahmed, Yun Yang

原文摘要

Transformers have demonstrated the ability to perform in-context learning, that is, to adapt to new tasks from a few examples without updating their parameters. Existing theory has largely focused on emulating gradient-based algorithms for convex statistical problems or establishing general function approximation guarantees without exploiting the underlying statistical structure. We study in-context parameter estimation and trajectory prediction for parametric ordinary differential equations (ODEs), where estimation is generally nonconvex. Under suitable identifiability and regularity conditions, we construct a transformer that estimates unknown system parameters from noisy trajectory observations through a two-stage approximate maximum likelihood procedure: a coarse search provides an initialization within a locally strongly convex region, followed by gradient descent with local linear contraction. For prediction, we compose this estimator with a neural approximation of the ODE solution map. We further show that, through parameter sharing, a single transformer can perform both parameter estimation and trajectory prediction simultaneously. For these constructions, we establish nonasymptotic guarantees and finite-pretraining oracle inequalities that separate errors due to finite pretraining data, finite context length, and finite-sized transformer approximation. Numerical experiments on linear and nonlinear ODEs further show that pretrained transformers can benefit from longer inference contexts without updating their weights.

cs.LG · cs.AI · math.NA · math.ST · stat.ML

新论文 · v1arXiv:2611.21267

Conformal Expert Pools: Training-Free Probabilistic Time-Series Forecasting Beyond Seasonality

Valery Manokhin

原文摘要

Conformal Seasonal Pools (CSP) showed that a forecaster with no training at all, built only from past values at the same point in the season and from past forecast errors, significantly outperformed DeepNPTS, Amazon's learned non-parametric forecaster. We propose Conformal Expert Pools (CEP), a training-free successor. CEP replaces the single seasonal-naive forecast by a pool of simple forecasters, builds its predictive distribution from their past forecast errors, and adapts both the pool and the errors to the series being forecast. No model is trained and no parameter is learned across series. On the CSP benchmark of 232 datasets and 24,502 forecast windows, CEP is better than CSP on 78% of datasets by CRPS, on 84% by MSIS and on 83% by Winkler score; on a typical dataset its CRPS is 14% lower and its MSIS 23% lower (both p < 1e-22, paired Wilcoxon test), and coverage of 95% intervals rises from 90.1% to 92.2%. CEP has a lower CRPS than DeepNPTS on 88% of datasets, than NPTS on 89% and than SeasonalNPTS on 83%. The improvement persists on dataset families outside the development set and on 36 additional fev-bench files. We also test the published claims that Laplace, an online ensemble forecaster, "beats (almost) everything" and "beats" CSP. On 228 datasets at multi-step horizons the claims do not hold: CSP outperforms Laplace on 60% of datasets by CRPS and on 64% by interval score, and Laplace ranks sixth of seven methods, with the widest intervals of all (69% wider than CEP's). Its point forecast is biased low and on 54% of datasets is less accurate than seasonal naive, and from a cold start it takes about 7,700 times longer than CSP. CEP is better than Laplace on 82% of datasets by CRPS and on 80% by MSIS, with intervals about 40% narrower, and runs 271 times faster.

cs.LG · cs.AI

版本更新 · v2arXiv:2605.06211

Contrastive Identification and Generation in the Limit

Xiaoyu Li, Andi Han, Jiaojiao Jiang, Junbin Gao

原文摘要

In identification in the limit (Gold, 1967), a learner reads positive examples and must eventually name the target hypothesis; in generation in the limit (Kleinberg and Mullainathan, 2024), it must eventually produce new positive examples. We study a weaker, relational signal: each observation is an unordered pair $\{x,y\}$ with $h(x)\neq h(y)$, such as a cannot-link constraint or a dissimilar-pair label, and the learner never learns which point is positive. All our results come from one object: a pair is valid for every member of a finite family exactly when its points lie in antipodal cells of the family's membership map. (1) For every corruption budget $k$, known or unknown, we characterize exactly the identifiable classes. Incomparable hypotheses must cover the domain and share more than $2k$ points, and Angluin's tell-tale sets must survive the loss of $2k$ points. Every unbounded budget makes any two hypotheses confusable. (2) A contrastive closure dimension characterizes uniform generation. On finite classes, generation fails exactly when a family that shares a presentation has a finite common support; on countable classes this finite condition no longer suffices. (3) On clean data the four learning criteria form a strict diamond. (4) Under corruption the order changes: some classes are identifiable from contrastive pairs under every finite budget by one algorithm, but not from positive examples with one corrupted example.

cs.LG · cs.AI · cs.CL · cs.DS

新论文 · v1arXiv:2611.21262

Strategic Repayment and Latent Fragility in Financial Networks: Why Banks Withhold Payable Liquidity

Hicham El Kaissi

原文摘要

A network in which every bank pays in full can nevertheless admit a self-fulfilling settlement freeze under the same balance-sheet fundamentals. Thus, observing full repayment does not establish the uniqueness or robustness of the payment equilibrium. We derive this result from a precautionary-liquidity choice: banks may delay otherwise feasible payments to insure an interim funding need, trading a positive settlement-discipline cost against the marginal value of retained cash. The optimal reserve is a critical quantile of future liquidity requirements, and the repayment rule nests Eisenberg-Noe maximal feasible clearing exactly. Counterparty underpayment both reduces current cash and raises desired reserves. We characterise network amplification and the conditions for coexistence, including a homogeneous two-bank GPD frontier in which interbank exposure and maximum funding pass-through enter through one dimensionless index. A two-date settlement accounting rule distinguishes payment timing from ultimate default. The main result concerns equilibrium coexistence; the conditional best-response adjustment diagnostic does not assign selection probabilities.

q-fin.RM · cs.GT · econ.TH · q-fin.MF

新论文 · v1arXiv:2611.21260

Leveraging Binary Hashing for Scalable Index Assignment in Semantic Communications

Leonardo Roque, Kuangyun Zhu, Louis-Adrien Dufrène, Quentin Lampin, Grégoire Lefebvre, Mohamad Assaad

原文摘要

Transmitting semantically structured embedding vectors over digital channels is costly in bit rate, while conven- tional vector quantization approaches face limitations in scalabil- ity, encoding complexity, and index assignment. This paper inves- tigates binary hashing techniques from the information retrieval literature as semantic indexing strategies for general-purpose networks. We study random Locality-Sensitive Hashing (LSH) along with Principal Component Analysis (PCA)-, Canonical Correlation Analysis (CCA)-, and ITQ (Iterative Quantization)- based variants in a semantic communication pipeline over a Binary Symmetric Channel. Embeddings are compressed into binary codes, reconstructed through Hamming retrieval from a shared table, and evaluated on downstream classification. Ex- periments on the Massive Text Embedding Benchmark (MTEB) and the Banking77 dataset show that data-dependent hashing improves upon random LSH, while ITQ refinement increases robustness to channel noise. Among the evaluated methods, CCA- ITQ achieves the best classification accuracy across the tested channel conditions. These results indicate that binary hashing is an efficient and scalable alternative to quantization-based embedding compression for semantic communications.

eess.SP · cs.IR

版本更新 · v3arXiv:2610.35254

Style over Substance? Linguistic Bias in LLM-based Peer Review

Sai Suresh Macharla Vasu, Sumedh Santosh Joshi, Philipp Christmann, Ivaxi Sheth, Ruta Binkyte, Koel Dutta Chowdhury, Raouf Kerkouche, Hui-Po Wang 等 9 位作者

原文摘要

The number of paper submissions to major AI conferences has increased dramatically in recent years, substantially increasing the peer-review workload of researchers. At the same time, large language models (LLMs) are increasingly used to support peer review, both by individual reviewers and by conference organizations. While LLM capabilities have improved considerably, their evaluations may be influenced by linguistic characteristics that are unrelated to scientific content. In this work, we introduce a controlled experimental framework for studying such effects by systematically perturbing the linguistic style of research papers. Specifically, we rewrite papers to exhibit (i) linguistic features associated with native or non-native English writing, and (ii) high- or low-confidence linguistic features. To construct these interventions, we derive fine-grained rewriting instructions grounded in the linguistic literature and apply them using LLMs. Crucially, our interventions are designed to preserve the underlying scientific content. We then evaluate the resulting papers using different LLM reviewers. Our experiments expose a critical vulnerability in LLM-based peer review: reviewers systematically reward confident rhetoric independent of scientific content, raising serious concerns about the robustness of their assessments.

cs.CL

版本更新 · v4arXiv:2409.16238

Linear-time Rule Mining Under Formal Guarantees

Jonathan Feldstein, Dominic Phillips, Efthymia Tsamoura

原文摘要

Probabilistic logical models are a core component of neurosymbolic AI and are important in their own right for tasks that require high explainability. Unlike neural networks, logical theories that underlie the model are often handcrafted using domain expertise, making their development costly and prone to errors. While there are algorithms that learn logical theories from data, they are generally prohibitively expensive, limiting their applicability in real-world settings. Here, we introduce precision and recall for logical rules and define their composition as rule utility -- a measure of the predictive power of logical theories that can be computed in linear time in the data size. We then present SPECTRUM, a linear-time framework for learning logical theories from relational data, that mines recurrent patterns in the data, and subsequently uses our utility measure to evaluate and rank the rules derived from these patterns. Finally, we prove theoretical guarantees on the utility of the learnt logical theory. As a result, we demonstrate across various tasks that SPECTRUM scales to databases with orders of magnitude more relations and entities, often learning more accurate logical theories on CPUs in < 1% of the runtime of state-of-the-art neural network approaches on GPUs.

cs.AI

版本更新 · v2arXiv:2609.31071

Externalized CPDAG Summaries Improve LLM Causal Deduction

Wentao Sun, João Paulo Nogueira, Dominique Verchere, Mathieu Acher, Alonso Silva

原文摘要

Observational data rarely identify a single causal structure. Such structures are typically modeled as directed acyclic graphs (DAGs) whose arrows point from direct causes to their effects, and observed correlations and conditional independencies usually leave a whole family of DAGs that fit the data equally well. A causal claim follows from the data only if it holds in every one of them. Classical causal discovery methods such as the Peter--Clark (PC) algorithm summarize this family as a completed partially directed acyclic graph (CPDAG): an edge is directed when every compatible graph orients it the same way, and undirected when the data leave its direction open. On the Corr2Cause benchmark, large language models (LLMs) that reason in free text often lose track of this family and decide from a few local edges. We propose \emph{Structured Thinking}, a two-turn method in which the model first summarizes the CPDAG in a constrained schema and then checks the claim against that summary. Without fine-tuning or an external solver, it raises Qwen3.5-27B from $77.5$ to $86.5$ F$_1$ (mean of three seeds) over a baseline that receives explicit PC-algorithm instructions, whereas a second turn of free-text analysis does worse than that baseline. The gain holds on test splits with renamed variables or paraphrased hypotheses and on other models. Given only the graph and the claim, the model's answer flips when the graph is replaced by a valid CPDAG under which the claim has the opposite truth value. Moreover, replacing the model's graphs with reference CPDAGs on a fixed subset shows that most remaining errors arise in building the graph rather than in reading it. Making causal structure explicit can help LLMs reason more reliably, provided the intermediate representation is itself trustworthy.

cs.AI

新论文 · v1arXiv:2611.21251

The Price of Choosing Examples: Context Overfitting in Adaptive In-Context Learning

Xiaoyu Li, Jiangxuan Long

原文摘要

In-context learning is usually analyzed as if the examples in the prompt were sampled before the learner is chosen. In deployed systems they are not: examples are retrieved, filtered, re-ranked, edited, and repeatedly tested after seeing the query and the data store. We formalize this gap by treating prompt construction as adaptive data analysis through a conditional stochastic-kernel calculus. Our main quantity is the context capacity, the mutual information or approximate max-information between the data store and the final prompt transcript. For any frozen in-context learner and any adaptive context pipeline with capacity $κ$, we prove a finite-sample context generalization bound of order $\sqrt{κ/k}$, where $k$ is the number of selected examples whose losses form the reported score. We prove a matching lower bound, whose constant is exact when $\log k\llκ\ll k$, and derive two PAC-Bayesian retrieval rules: a first-order Gibbs rule that charges data-dependent candidate gates their prior mass, and a self-normalized second-order rule. On Banking77 with 64 retrieval recipes and two model families, the certificates hold in all 24,000 resampled selection events, and from 64 (Qwen2.5-7B) or 128 (GPT-4.1-mini) reused validation queries the Gibbs rule certifies a risk below the zero-shot error in over 99% of validation draws. Finally, we instantiate the theory for Bayesian linear in-context regression, including an order-statistics analysis of query-aligned top-$k$ Gaussian retrieval. The results separate context quality from context certification: longer or more relevant contexts improve risk only when the procedure used to choose them is stable enough for selected-context evidence to transfer.

cs.LG · cs.CL · stat.ML

新论文 · v1arXiv:2611.21250

Stream of Belief: Eliciting Collective Intelligence through Latent Belief Dynamics

Yu Yao, Jiayi Dong, Yilun Du

原文摘要

In this work, we view multi-agent reasoning as a process of seeking a collective equilibrium of implicit belief dynamics and introduce Stream of Belief (SoB), where agents maintain continuous latent beliefs and iteratively refine them through communication and reflection. Our method seeks a collective belief state of a multi-agent system where further communication induces no meaningful information propagation. Through extensive experiments, we demonstrate the generalization of SoB across tasks and model families. More Broadly, our results suggest a new perspective on scaling multi-agent reasoning from belief dynamics.

cs.AI · cs.CL · cs.MA

新论文 · v1arXiv:2611.21249

Heteroscedastic Gaussian Process Q-learning for Sample Efficient Experimentation

Maximilian Bloor, Max Mowbray, Calvin Tsay, Ehecatl Antonio del Rio Chanona

原文摘要

Self-driving laboratories must learn to control a process from tens to hundreds of expensive experiments, too few for deep reinforcement learning (RL). We learn the Q-function directly with a Gaussian process (GP), which avoids learning the dynamics, and show that the GP posterior supplies the learning rate of Q-learning. If each Bellman target is treated as a noisy measurement of the Q-function, the learning rate that minimises the mean squared error is the Kalman gain, and applying it to every observed transition is equivalent to GP regression. Heteroscedastic Gaussian Process Q-learning (HGPQ) sets the noise variance of each target with a heteroscedastic GP, which learns how unreliable the targets are across the states and inputs. Targets from noisy operating conditions, or from regions where the value function has large gradients, then move the estimate less than targets from low-noise regions, so HGPQ learns quickly where the data are reliable without being misled where they are not. For kernel value iteration with per-target variances that are assigned when a target is collected, we prove a high-probability bound on the error of the value estimate, uniform over the explored region. Pooled over five simulated benchmarks, which include a chemical reactor and a bioprocess, HGPQ approaches the best return found by any method in fewer episodes than GP, kernel and deep RL baselines.

cs.LG · eess.SY

版本更新 · v6arXiv:2405.15647

A Logic of Knowledge and Justifications, with an Application to Computational Trust

Francesco A. Genco

原文摘要

We present a logical framework that enables us to define a formal theory of computational trust in which this notion is analysed in terms of epistemic attitudes towards the possible objects of trust and in relation to existing evidence in favour of the trustworthiness of these objects. The framework is based on a quantified epistemic and justification logic featuring a non-standard handling of identities. Thus, the theory is able to account for the hyperintensional nature of computational trust. We present a proof system and a frame semantics for the logic, we prove soundness and completeness results and we introduce the syntactical machinery required to define a theory of trust.

cs.LO

新论文 · v1arXiv:2611.21241

Anytime-Valid PAC-Bayes Certificates for Adaptive Test-Time Scaling

Xiaoyu Li, Jiangxuan Long

原文摘要

Test-time scaling systems often choose how much to sample, which prompt to use, and which verifier or aggregation rule to trust after repeatedly inspecting a calibration set. Standard validation error bars are not valid after this adaptive selection. We model a test-time scaling recipe as a randomized predictor with a random cost and prove a time-uniform PAC-Bayes certificate that holds simultaneously over all calibration times, all posterior mixtures over recipes, and all data-dependent stopping rules. Thus the same event covers the recipe search that precedes deployment, not merely the fixed recipe finally reported. For a finite grid of budgets and verifiers, the penalty is the familiar $\log M/n$, which in the worst case no certificate valid after selection can avoid, while non-uniform priors and localized posterior mixtures can give sharper certificates for structured searches. We specialize the result to self-consistency and show a complementary margin law: plurality voting improves exponentially in the sample budget only on examples where the correct answer is the generator's unique mode; otherwise more compute can provably amplify errors. The same margin analysis yields an oracle water-filling law for compute allocation. A synthetic audit quantifies the optimism caused by adaptive budget selection, and a 192-example GSM8K audit using gpt-4.1-mini generations illustrates risk-cost reporting for a real inference pipeline. At scale, with two models on GSM8K and MATH-500, selected-best error bars fall below the out-of-split GSM8K risk in up to 22.5% of random splits at a nominal 5% while the certificate never does, and on the full GSM8K test split it tightens to 0.109 (held-out risk 0.039). The results give a lightweight, distribution-free way to report risk and compute claims for adaptive inference systems.

cs.LG · cs.CL · stat.ML

新论文 · v1arXiv:2611.21240

How Developer Personality Shapes the Use of AI Coding Assistants

Annemarie Wittig, Alina Mailach, Norbert Siegmund

原文摘要

Developers differ in personality traits that shape how they approach software development tasks, yet AI coding assistants either behave uniformly or offer personalization features whose fit with individual developers must be found through trial and error. This is because it remains unclear how personality shapes developers' experiences with AI assistants, and thus which traits personalization should account for. In other words, we provide tools with no underlying theory on what works when and why. We take a first step towards such a theory with a systematic scoping review on how users' personality relates to their perception of LLM-based tools. We identified twelve studies through general search engines, major Software Engineering (SE) venues, AI tooling, and snowballing. They all reported associations between personality and perceptions, particularly perceived usefulness, yet none addressed this in a SE context. Building on these findings, we conducted an exploratory two-wave survey with 29 and 11 developers, collecting first empirical evidence of how developers' personality (measured using the Big Five Model) relates to the perception of AI coding assistants. Higher Extraversion was associated with more positive private-use experiences in both waves, while Agreeableness was associated with negative professional experiences in the first wave and positive ones in the second. These results provide first indications that the personality effects found in the literature extend to developers. Although further studies with bigger samples are needed to build a theory, our work takes the first step towards an empirical grounded theory of developer personality and AI personalization traits.

cs.AI · cs.SE

版本更新 · v2arXiv:2607.06873

Mining Workflow Graphs for Black-Box Boundary Testing of Conversational LLM Agents

Liting Lin, Boxi Yu, Yuzhong Zhang, Lionel Briand, David-Paul Niland, Emir Muñoz

原文摘要

Failures of conversational LLM agents can have real-world consequences, for example when an agent completes a transaction without the user's confirmation. An important class of such failures occurs at workflow boundaries, such as identity checks and confirmation steps, which a test can reach only after several turns of conversation. We present AgentEval, a black-box testing framework that discovers and tests these boundaries. AgentEval interacts with an agent to mine a conversational workflow graph, a model of its behavior whose nodes are the agent's activities and whose edges are the user actions observed between them. It generates tests at each node of this graph, replaying the conversational path to that node before applying a perturbation. AgentEval then runs each test, and a separate LLM judge decides whether it passes or fails using only the conversation turns. We benchmark AgentEval against a privileged, white-box auditor with access to the agent's underlying source code, which AgentEval never sees. On four $τ^3$-bench agents, the boundary tests of AgentEval cover 38.8-46.0 distinct boundaries per agent on average over five repetitions. In ablation studies, generating tests without targeting the graph's nodes lowers the distinct-boundary count by 2.0-7.0 in every agent and raises the duplicate rate in most agents.

cs.SE

版本更新 · v3arXiv:2602.13238

Securing SIM-Assisted Wireless Networks via Quantum Reinforcement Learning

Le-Hung Hoang, Quang-Trung Luu, Dinh Thai Hoang, Diep N. Nguyen, Van-Dinh Nguyen

原文摘要

Stacked intelligent metasurfaces (SIMs) have recently emerged as a powerful wave-domain technology that enables multi-stage manipulation of electromagnetic signals through multilayer programmable architectures. While SIMs offer unprecedented degrees of freedom for enhancing physical-layer security, their extremely large number of meta-atoms leads to a high-dimensional and strongly coupled optimization space, making conventional design approaches inefficient and difficult to scale. Moreover, existing deep reinforcement learning (DRL) techniques suffer from slow convergence and performance degradation in dynamic wireless environments with imperfect knowledge of passive eavesdroppers. To address these challenges, we propose a hybrid quantum proximal policy optimization (QPPO) framework for SIM-assisted secure communications that jointly optimizes transmit power allocation and SIM phase shifts to maximize the average secrecy rate under power and quality-of-service constraints. Specifically, a parameterized quantum circuit is embedded into the actor network, forming a hybrid classical-quantum policy architecture that enhances policy representation capability and exploration efficiency in high-dimensional continuous action spaces. Extensive simulations demonstrate that the proposed Q-PPO scheme consistently outperforms DRL baselines, achieving approximately 15% higher secrecy rates and 30% faster convergence under imperfect eavesdropper channel state information. These results establish Q-PPO as a powerful optimization paradigm for SIM-enabled secure wireless networks.

cs.NI · cs.LG

新论文 · v1arXiv:2611.21232

A Generative AI-Driven Architecture for Whole-Home Intelligent Services: Edge Models, Memory Management, and Household Applications

Mo Zhou

原文摘要

Generative artificial intelligence is entering the home. Cloud-based assistants face governance limitations in data transmission, continuous availability, and the reliability of physical actions, which are especially salient in households where devices remain online, data accumulate over time, and commands trigger real-world actions. Using the home local server as a unifying organizing axis, this article develops a design-oriented review framework. Sources from arXiv, CNKI, ACL Anthology, and official documentation were searched through November 2026 and coded into five evidence categories: reviews, system prototypes, benchmarks, HCI and eldercare studies, and official documentation. System designs were mapped onto shared architectural modules, identifying nine recurrent responsibilities of the home local server. Generative models support perceptual interpretation, intent understanding, and candidate planning, while deterministic validation, knowledge-graph constraints, and authorization leases confine candidate actions to an inspectable space. Home control, emotional companionship, and intelligent guarding can be compared within a common framework: they share state and memory but differ in latency, false positive and negative rates, proactivity, and permissions. Existing benchmarks rely on virtual environments and cannot substitute for real-deployment evaluation. Local deployment is not inherently safer, and technical continuity alone does not establish the social or medical effects of companionship and guarding. The article proposes a five-dimensional evaluation framework covering architectural capability, system resources, privacy, safety and reliability, and human experience, together with six design principles and a future research agenda for local-first intelligent home systems.

cs.CL · cs.AI

版本更新 · v3arXiv:2603.11750

Trustworthy Calibration or Vulnerability? Unveiling the Over-Calibration Paradox and Attack Surface in Rashomon Sets

Mustafa Cavus

原文摘要

Post-hoc calibration is standard practice for aligning classifier confidence scores with empirical frequencies in high-stakes decision systems. However, its downstream effects on decision stability across competing, equally accurate models remain largely unexamined. In this paper, we formalize the over-calibration paradox within the framework of predictive multiplicity, reflecting the Rashomon effect where competing models with near-identical loss assign conflicting predictions to the same individual. Evaluating nine credit risk portfolios, we examine the impact of Platt Scaling, Isotonic Regression, and Beta Calibration on individual prediction agreement and expected calibration error. We identify two distinct operating regimes. In systematically miscalibrated models, post-hoc calibration consistently aligns probability estimates and reduces prediction disagreement. Conversely, when baseline models are already well-calibrated, post-hoc calibration, particularly non-parametric estimators constrained by finite sample sizes, overfits to hold-out noise. This distortion shifts decision thresholds near the classification boundary, paradoxically increasing both expected calibration error and predictive multiplicity. From an auditing and security standpoint, this paradox exposes a practical vulnerability to soft adversarial manipulation, whereby an interested party or automated model search can exploit calibration choices to steer specific individual outcomes while preserving aggregate performance and passing black-box evaluations.

cs.LG

版本更新 · v3arXiv:2610.00518

One-Step Generative Modeling via Training Dynamics Action

Zhangyong Liang, Ying Huang, Haibin Ling

原文摘要

Recent one-step generators learn to move outputs toward data by fitting sample movements. However, the optimizer updates shared parameters rather than sample positions, so the movements can differ from those prescribed. To address this issue, we propose Training Dynamics Action (TDAC), which uses the cost of fitting movements jointly to choose transport plans. For a linearized generator, local generator action is the minimum sum of parameter-update cost and a feature-fitting penalty over shared parameter increments. We derive a closed-form action and minimize a regularized version while retaining a prescribed fraction of the reference plan's predicted distributional improvement. We estimate the covariance of feature responses using random parameter directions and evaluate action with a low-rank approximation. The plan defines fixed regression targets. An execution-gap bound relates local generator action to first-order progress of the actual update. Planning occurs during training; inference requires one generator evaluation. On ImageNet 256 x 256, TDAC achieves Frechet Inception Distance (FID) below 1.1 without distillation. Furthermore, TDAC reduces optimizer-time action while maintaining distributional accuracy and full mode coverage. At comparable FID, TDAC requires approximately 100 times fewer generator evaluations than multi-step diffusion models. The code for our work will be released soon.

cs.LG