跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 19:37 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 20:07 — 2026-11-09 20:07（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：2026-11-09 19:37最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 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。

18,172 已收录论文15,506 AI 相关4,527 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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 13,660 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 19:35（北京时间）
新论文 · v1arXiv:2611.07973

Tight Asymptotic Bounds on the Maximum Number of Linear Regions of Piecewise-Linear Kolmogorov--Arnold networks

Ye Su, Yong Liu

原文摘要

Schoots et al.~\citep{schoots2025relating} (AISTATS 2025) established a generally loose upper bound on the number of linear regions of continuous piecewise-linear (CPWL) Kolmogorov--Arnold networks (KANs), without providing a lower bound. We consider a $T$-layer network with width vector $\mathbf n=(n_0,\ldots,n_T)$, input dimension $n_0=d$, output width $n_T=1$, and at most $k\geq2$ affine segments per edge. Our matching upper and lower bounds determine the tight growth order $Θ_{\mathbf n}(k^{\sum_{\ell=1}^{T}ρ_{\ell-1}})$ in $k$, where $ρ_{\ell-1}:=\min_{0\leq s\leq\ell-1}n_s$. When every hidden width is at least $d$, the tight order simplifies to $Θ_{\mathbf n}(k^{dT})$. The upper bound of \citep{schoots2025relating} is $k^{\sum_{\ell=1}^{T}n_{\ell-1}n_\ell}$. Our upper bound improves it by a factor of $Θ_{\mathbf n}\!\left(k^{\sum_{\ell=1}^{T}n_{\ell-1}n_\ell-\sum_{\ell=1}^{T}ρ_{\ell-1}} \right)$, with strict asymptotic improvement whenever a hidden layer has width greater than one. We further compare CPWL KANs with rectified linear unit (ReLU) networks using dense parameterizations with at most $Λ$ parameters per model and the same fixed nonlinear depth $T$. Counting trainable knot locations and optimizing the widths and $k$, we prove that the maximum region count of CPWL KANs divided by that of ReLU networks is $Θ_{d,T}(Λ^{d\lfloor T/2\rfloor})$ as $Λ\to\infty$, yielding a polynomial advantage for KANs when $T\geq2$. These tight bounds characterize the attainable geometric complexity of CPWL KANs, providing a foundation for understanding their expressive power and guiding architectural design.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07972

A Little Derandomization Goes a Long Way: Unconditional Circuit Lower Bounds using Low-Degree PIT

Nikolai Chukhin, Karthik Gajulapalli, Alexander Golovnev, Ivan Mihajlin

原文摘要

We prove unconditionally that either NE contains a language requiring Boolean circuits of size at least $2^n/(2n)$, or $VP^0_{\mathbb{Z}}\ne VNP^0_{\mathbb{Z}}$, a constant-free version of Valiant's conjecture over the integers. The Boolean alternative implies that $NP\not\subseteq SIZE[n^k]$ for every constant $k\ge1$. Our proof gives a fine-grained variant of the connection between Polynomial Identity Testing (PIT) and circuit lower bounds established by Kabanets and Impagliazzo (2004). We show that the specific identity tests required by this argument can be performed over the integers without a derandomization assumption. Over a fixed finite field $\mathbb{F}$, we first give a deterministic $O(st^{d-1})$-time algorithm for PIT on size-$s$ circuits computing degree-$d$ polynomials in $t$ variables. We further show that, for any fixed $d\ge2$ and $\varepsilon>0$, improving this running time by a factor of $t^{\varepsilon}$, even nondeterministically, implies either the same Boolean lower bound or an arithmetic circuit lower bound of $t^{1+\varepsilon/2}$ for a polynomial family from $VNP_{\mathbb{F}}$. If nondeterministic PIT instead runs in time $s^{o(d)}t^{(1-\varepsilon)d}$ for infinitely many degrees $d$, then the arithmetic lower bound strengthens to $VP_{\mathbb{F}}\ne VNP_{\mathbb{F}}$. Over the integers, we give a deterministic PIT algorithm for syntactically set-multilinear circuits running in time $s^{O(1)}t^{5d/6}$, which yields the unconditional result above. Combining the Kabanets-Impagliazzo argument with range avoidance, we show that an NP algorithm for PIT over $\mathbb{Z}$ gives a purely arithmetic win-win: either $VP_{\mathbb{Z}}\ne VNP_{\mathbb{Z}}$, or constant-degree polynomials of maximum circuit complexity can be constructed in FNP.

cs.CC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.41697

TSBPO: Tree-Structured Branching for Policy Optimization in Interactive Language Agents

Rui Yu, Chong Mu, Jinchuan Zhang

原文摘要

Terminal feedback in multi-turn agent training leaves both rollout allocation and local credit underdetermined. Dynamics-Predictive Sampling (DPS) [9] provides a task-level predictive sampling reference, but interactive agents also need to choose which visited states merit further continuations. We introduce TSBPO with two method components. A lightweight, fine-grained Root/Branch budget allocator distributes factual rollouts across tasks and additional suffixes across replayable states using likelihood-fitted estimates of terminal-outcome contrast. On the resulting physical rollout trees, a tree-aware step-level credit assignment algorithm compares immediate sibling segments and assigns their local outcome contrasts to the turns they contain. Exact task/observation groups provide a complementary step term. The allocator selects what to sample; observed outcomes determine the subsequent credit. With a Qwen2.5-1.5B actor, fixed checkpoints attain 97.79% seen and 96.64% unseen stochastic success on ALFWorld, and an 81.07% per-episode success rate over six stochastic episodes for each of the 500 WebShop test goals. At the WebShop update-100 checkpoint, removing the observation-group step term yields 75.93% under the same evaluation. These results describe the evaluated training configurations on two interactive benchmarks.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.04992

ContractLens: Latent Security Knowledge for Malicious Smart Contract Detection

Shuyi Miao, Xinyi Huang, Wangjie Qiu, Fei Shen, Jinchun He, Zhiming Zheng, Tat-Seng Chua

原文摘要

Detecting malicious smart contracts is essential to safeguarding the Web3.0 ecosystem. However, existing auditing methods based on large language models (LLMs) largely rely on prompt engineering or attack-specific fine-tuning, while the internal representations that support malicious logic detection remain poorly characterized. To address this gap, we propose ContractLens, a framework that localizes and uses latent security knowledge in pretrained LLMs for interpretable malicious smart contract detection. Specifically, we first use layerwise linear probes to identify candidate layers that distinguish malicious from benign contracts, then select critical layers based on their sensitivity to malicious logic removal and stability under behaviour-preserving surface modifications. Next, within these critical layers, we combine activation contrast, malicious-logic specificity, and probe weights into a tri-factor importance score and adaptively select malicious contract-discriminative units (MCDUs) using the knee point of the ranked score curve. Finally, we concatenate the selected units' activations into a compact representation and train a lightweight classifier for detection, keeping the pretrained model frozen throughout. Neuron masking experiments show that masking MCDUs causes larger drops in detection performance than masking randomly selected neurons or neurons matched in activation magnitude. ContractLens achieves higher average detection accuracy than the evaluated methods on all three pretrained models. Further evaluations demonstrate generalization to unseen malicious intents and show that, with the identified MCDUs fixed, a classifier trained on few labelled samples can still achieve strong detection performance.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07964

Time-Indexed Skill Success Models for Latency-Aware Skill Selection and Timing in Dynamic Manipulation

Mohsen Omidi, Maria Chiara Leva, Brian Vaughan

原文摘要

Robots that manipulate moving objects act on observations that are outdated when the chosen skill starts, and the best skill can change within a few hundred milliseconds. Skill competence models, however, predict success for a launch at the moment of observation. We propose time-indexed skill success models, which predict whole-task success when a skill is launched after a given delay. Trained on rollouts branched at a grid of launch delays, they let a receding-horizon planner select both the skill and its launch time under fixed or random latency. In a MuJoCo study in which a UR5e captures a sliding puck with three skills, the planner exceeded a static competence model by 2.8 to 6.2 percentage points at 100 to 300 ms of latency, including when that model was evaluated on point or sampled forecasts of the launch state. Across five complete runs (three training seeds and two distribution shifts), all 80 paired 95% intervals against four baselines excluded zero. On delayed launches, the time-indexed model was calibrated (expected calibration error 0.009 against 0.239), and pausing the world during latency overstated success by up to 23 points. On a real UR5e that captures a rolling ball after 0.2 s of injected latency, a static model trained in a hardware-matched simulator predicted 99% success on a prespecified subset of 35 delayed launches that it rated at least 0.8. Of these, 63% succeeded (95% interval 46 to 77%), and the time-indexed model predicted 56%. In this single-skill, predictable regime, a matched physics-based forecast was also well calibrated.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07962

TCSExam: Evaluating Frontier LLMs on the Full Range of TCS Research

Yifan Luo, Zhengying Liu, Yang Yuan, Zhilin Yang, Andrew Chi-Chih Yao

原文摘要

Can large language models (LLMs) advance theoretical computer science and resolve its long-standing open conjectures? To study progress toward this goal, we introduce TCSExam, a unified framework and benchmark covering the full range of TCS research. It evaluates theorem proving, solver engineering, and constructions alongside direct attempts to resolve open conjectures, capturing both concrete research accomplishments and progress toward long-standing research goals. TCSExam-Full contains 100 expert-reviewed tasks, with submissions checked by the Lean kernel or an executable task checker. TCSExam-Lite selects 20 tasks, five per track, reducing the number of task attempts by 80% at the same per-attempt budget. We evaluate eight agents on Full and nine on Lite. The TCSExam Index combines all four tracks: GPT-6 Astra leads Full (71.9), and Opus 5.5 leads Lite (72.3). Full and Lite rankings are strongly aligned across eight shared agents (Spearman's $ρ=0.93$), supporting Lite as a compact, discriminative benchmark. The evaluations yield improved solver outputs and mathematical constructions, together with independently verified special cases and bounds from open-conjecture attempts. TCSExam provides an extensible framework with task sources, Docker build recipes, and evaluation tools for reproducible use.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07961

Bri3D: Bridging the Object-Scene Gap in Single-Image 3D Generation via Scene-Anchor

Hongye Hou, Shuai Zhang, Hongjie Li, Zhuoxiao Li, Haiping Wang, Yuan Liu, Wufan Zhao

原文摘要

Generating compositional 3D scenes from a single image requires recovering detailed object geometry and coherent spatial arrangements. Existing object-to-scene methods, including SAM3D and MIDI, extend object generation through image-context reasoning or inter-instance modeling. Coordinating objects remains challenging with limited scene-level supervision. Directly extending object-centric generators to entire scenes can degrade geometry and fail to preserve instance scale, orientation, and pose. We propose Bri3D, a framework bridging scene-level structural reasoning and object-level generative priors through instance-aware voxel scene anchors. Bri3D predicts a color-coded scene scaffold encoding coarse object geometry and spatial arrangements. Each instance is extracted as a scene anchor and refined into a pose-preserving, prior-compatible voxel support, enabling a frozen object generator to synthesize detailed textured geometry in the anchor-defined spatial reference. This coarse-to-fine design separates scene organization from object-scale detail synthesis, focusing scene-level training on spatial organization and anchor refinement while reusing pretrained object priors. Experiments demonstrate improvements in scene layout, object geometry, visual quality, and generalization. Bri3D predicts scene layouts efficiently; full scene generation is faster than SceneGen and SAM3D.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07959

CoRD: Coupled Rollouts Fill the Blind Spot of On-Policy Distillation

Guhan Chen, Bohan Li, Jun Rao, Hejin Wang, Songtao Tian, Yexin Xie, Xiaojun Meng, Peng Yuan 等 11 位作者

原文摘要

On-policy distillation trains a student on its own rollouts, so states the teacher would reach but the student does not are seldom supervised. We introduce CoRD (coupled-rollout distillation), which keeps the on-policy loss and moves only the distribution of training states toward the teacher, drawing rollouts from a geometric interpolation of student and teacher through the maximal coupling of speculative decoding. The coupling keeps the student's token wherever the two distributions agree and otherwise substitutes a token from the part of the target the student underweights, so interventions are as rare as any exact sampler allows and recede as the student learns. Across six base students from two model families (Qwen3 and Qwen3.5, 0.6B to 4B), CoRD raises average pass@1 over on-policy distillation by 0.9 to 2.0 points and pass@8 by 1.2 to 3.4 points on five public math benchmarks at equal steps and data. On frozen teacher-reached states, a 4B student trained with CoRD reaches in 16 steps a gap closure that on-policy distillation does not reach in 80, and substitution rules intervening at least as often in other directions fall short of CoRD.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07955

Rotation Is Token-Blind: A Structural Criterion for Post-Training Quantization of Feed-Forward Geometry Transformers

Huanfei He, Bohao Zhang, Jiaxin Zhang, Wei Sui, John See, Zeyd Boukhers, Cong Yang

原文摘要

Feed-forward 3D models use Transformers to predict camera poses, depth, and structure in one pass, avoiding iterative multi-view optimization. Long sequences and deep attention incur high compute and memory costs, motivating Post-Training Quantization (PTQ) for deployment. Existing PTQ methods mainly suppress channel-wise outliers by smoothing or orthogonal rotation. Geometry Transformers introduce a different challenge: heterogeneous token types share one activation quantization grid. A few special tokens may exert high leverage over global outputs and be updated by only a subset of blocks. Token-blind transforms, which apply the same transformation to every token, reduce overall quantization error but cannot remove differentiated degradation across token types. We propose QMapAnything, a structure-aware PTQ framework. We cast floating-point-preserving rotation and smoothing as a token-blind reparameterization group, and prove that they yield common-mode gains while leaving relative token SNR unchanged. We introduce a statistic $Γ$ that combines a special token's quantization disadvantage and output leverage to predict whether differentiated bias correction is needed beyond rotation. Experiments on geometric benchmarks show that W4A8 closely matches full-precision performance. Under W8A8, peak memory falls by $2.2$--$3.1\times$ versus FP32, with up to $3.1\times$ speedup on real hardware. These results provide a principled and efficient approach to deploying feed-forward 3D reconstruction models in resource-constrained edges.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:1803.06878

Parameterized Complexity of Fair Vertex Evaluation Problems

Dušan Knop, Tomáš Masařík, Tomáš Toufar

原文摘要

Graph modification problems form a unifying framework for many classical graph problems, where the goal is to remove a minimum number of vertices so that the resulting graph satisfies a desired property $π$. In this work, we replace the classical objective of minimizing the solution size with the fair objective [Lin&Sahni: Fair edge deletion problems. IEEE Trans. Comput. 89], which minimizes the maximum number of deleted neighbors incident to any vertex. This fairness criterion aims to distribute deletions evenly across the graph and leads to new algorithmic and complexity challenges. We study fair deletion and evaluation problems in the logical setting, where the target property~$π$ is defined by a formula in a logic $\mathsf{L}$. In particular, we consider the Fair $\mathsf{L}$ Vertex Evaluation problem, which asks whether there exists a vertex set $W$ of bounded fair cost such that a given formula $\varphi(X)$ holds in the input graph $G$. Our main result is an FPT algorithm for the Fair MSO$_1$ Vertex Evaluation problem with one free variable, parameterized by the twin cover number of the input graph and the quantifier length of the formula. We further show that extending this result to formulas with $\ell$ free variables is unlikely: the $\ell$-Fair FO Vertex Evaluation problem is W[1]-hard for parameter $\ell$ even on graphs of twin cover one. As a concrete case study, we investigate the Fair Vertex Cover}\ problem, one of the simplest fairness-aware graph problems. We prove that it is W[1]-hard when parameterized by the combined treedepth and feedback vertex set, but admits an FPT algorithm for the parameter modular width.

cs.CC · cs.DS · cs.LO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.14414

CytoBERT: A Foundation Model for Cytometry Data

Syed Abdul Haseeb Qadri, Bjarne C. Hiller, Felix Blanke, Vanja Sophie Cangalovic, Kutalmış Coşkun, Amin Mirzaei, Tom Siegl, Sebastian Bader 等 10 位作者

原文摘要

Cytometry measures the complex characteristics of single cells (e.g., counts and protein expression of immune cells) and is widely used across immunological research and clinical settings. However, cytometry data is highly heterogeneous and unstandardized due to experimental protocols and the choice of measured features. While machine learning methods hold the potential to gain deeper insights into cell biology, these challenges make them difficult to apply and transfer across studies. Recent advances in foundation models can alleviate these issues, but corresponding approaches are still scarce in this field. To address this, we provide CytoBERT, a publicly available, open-source, open-weight foundation model for single-cell cytometry data with variable marker panels. CytoBERT is pretrained in a self-supervised manner on a large-scale cytometry corpus (15 human datasets with heterogeneous marker panels and more than 50 million cells) curated through marker standardization, enabling it to learn transferable inter-marker relationships within cells. Fine-tuning CytoBERT for sample-level classification demonstrates that transfer learning across heterogeneous cytometry datasets is feasible, providing a starting point for scalable, generalizable cytometry analysis. Code is available at GitHub.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.23183

Dequantization Barriers for Guided Stoquastic Hamiltonians

Yassine Hamoudi, Yvan Le Borgne, Shrinidhi Teganahally Sridhara

原文摘要

We construct a probability distribution, induced by the Perron--Frobenius eigenvector of an exponentially large graph, that cannot be efficiently sampled by any classical algorithm, even when given the best-possible warm-start distribution. In the quantum setting, this problem can be viewed as preparing the ground state of a stoquastic Hamiltonian given a guiding state as input, and is known to be efficiently solvable on a quantum computer. We further show that even estimating the ground-state energy of that Hamiltonian remains classically hard. Our results suggest that no efficient classical algorithm can solve a broad class of stoquastic ground-state problems. Our graph is constructed from a class of high-degree, high-girth spectral expanders (such as the LPS Ramanujan graphs) to which self-similar trees are attached. This builds on and extends prior work of Gilyén, Hastings, and Vazirani (Quantum 2021, STOC 2021), which ruled out dequantization for a specific stoquastic adiabatic path algorithm. We strengthen their result by ruling out any classical algorithm for guided ground-state preparation or energy estimation, while also providing a derandomized construction.

quant-ph · cs.CC · cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07953

A Behavioural Framework for Predicting and Understanding Loss of Control in Frontier Artificial Intelligence Systems

Yao Huang, Yichi Zhang, Yifan Wang, Yitong Sun, Haoyu Dong, Jifan Ma, Jinzhe Tu, Xiaojian Li 等 11 位作者

原文摘要

Frontier artificial intelligence (AI) systems are increasingly operating over longer horizons with diminishing human oversight, raising the risk of loss of control: systems acting beyond effective human control with potentially irreversible consequences. Because such failures may become observable only after containment is difficult, they must be assessed prospectively. We introduce a behavioural framework that decomposes loss-of-control risk into three factors: misaligned motive, harm-enabling capability, and monitoring evasion. We operationalise these factors through 13 measurable aspects and 29 evaluation tasks, whose scores are combined into a single loss-of-control (LoC) score. Across 13 frontier models, the LoC score shows strong prospective validity, correlating with failure rates in contained long-horizon risk scenarios (Pearson r = 0.84). Risk varies systematically across models and cannot be explained by capability alone. We further show that the framework can guide targeted mitigations: fine-tuning and monitoring directed at diagnosed vulnerabilities reduce failure rates while largely preserving general performance. These results provide a practical basis for predicting, understanding, and mitigating loss-of-control risk before it materialises.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08556

The Containment Polytope of a Triangle and a Convex Polygon

Yoonsung Choi, Sunghee Choi

原文摘要

The containment polytope $\mathcal{C}$ for a triangle $P$ and a convex $n$-gon $Q$ is a four-dimensional polytope representing the similarity transforms (translation, rotation, scaling) that place $P$ inside $Q$. While it is known that the complexity of $\mathcal{C}$ and its silhouette $Λ$, which represents all the largest placements of $P$ inside $Q$ for all orientations, can be quadratic in $n$, we show that the silhouette can be partitioned into a linear number of planar convex chains and steps in $O(n \log n)$ time. Based on the linear number of convex chains and steps, we can compute the complexity of silhouette $Λ$ in $O(n \log n)$ time and query the largest placement of $P$ inside $Q$ for a given orientation in $O(\log n)$ time. We explain geometrically how the triangle $P$ rotates while continuously scaling and translating to be maximal inside $Q$, leading to a parameterized algorithm for containment problems.

cs.CG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07951

Requirements Nobody Wrote Down: Emergence in a Public-Sector ML Pipeline

Ronivaldo Ferreira, Vinicius Costa Girard, Cleidson de Souza, Igor Steinmacher, Carla Aguiar, Filipe Roseiro Cogo, Gustavo Pinto

原文摘要

Governments increasingly use machine learning (ML) to handle data volumes beyond their analytical capacity, yet little is known about how requirements arise and evolve as an ML experiment moves toward operational use. Requirements Engineering (RE) for ML often assumes that requirements can be elicited upfront; in the public sector, however, demands arrive vague, stakeholders speak different professional languages, and what counts as a ``good'' result is unknown in advance. We report a 15-month case study of a thematic classification pipeline for Brazil's national digital participation platform, which holds over 60,000 citizen proposals, triangulating 43 project artifacts with interviews of six project participants. Institutional demands arrived as broad goals, endorsed but not sponsored, and only 40\% of the 95 reconstructed requirements and criteria were ever formalized. The pipeline's key requirements emerged largely from experiments, model outputs, and integration work, shaped by technical decisions and institutional constraints; the central one, the classification categories, was settled by a government taxonomy chosen for its institutional legitimacy. Acceptance relied on technical metrics, domain judgment, and political assessment, without shared thresholds or validation of usefulness in practice. In public-sector ML, technical and institutional artifacts thus act as elicitation instruments, and experimentation and integration belong to the requirements process.

cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07950

Leakage- and Label-Aware Benchmarking of Class-Imbalance Strategies for Multimodal Chest X-Ray and EHR Classification

Dang-Khoa Bui, Quang-Huy Tran, Minh-Khoi Nguyen-Bui, Duc-Tuan Ngo, Thanh-Trong Tran, Tuan-Khoi Nguyen, Hoang-Anh Ngo

原文摘要

Benchmarks of class-imbalance strategies for multimodal chest X-ray (CXR) and electronic health record (EHR) prediction are often evaluated on record-level splits of cohorts in which one patient contributes several radiographs. We audit such a benchmark on 29,083 MIMIC-CXR radiographs of 10,479 patients with eight diagnosis targets. First, the record-split benchmark was misleading: a lookup table that copies the label of a development-set radiograph with the same EHR vector nearly matched the best model, and on unseen patients every model fell to the level of predicting every case positive. Second, tracing the labels back to MIMIC-IV explained why: each patient's labels are keyword matches on the diagnosis codes of a single admission, copied, with one EHR vector per patient, to all of the patient's radiographs, so about a third of the radiographs carry labels that differ from the codes of their own admission. Third, under patient-separated evaluation with admission-aligned and rule-refined labels, the initial conclusions do not hold: in the evaluated configurations no imbalance strategy raised the observed mean macro F2 over no augmentation by more than 0.01, tuned tree ensembles showed no consistent advantage over tuned logistic regression, and the released EHR variables stayed at the level of the all-positive baseline, whereas the diagnostic history available at imaging time and image embeddings exceeded it, including, with rule-refined labels, a CheXpert-trained encoder that never saw these radiographs; RAD-DINO had seen 96.6% of them during self-supervised pretraining. Adding either encoder to the diagnostic history gave no statistically significant F2 gain; exploratory AUROC gains were significant with RAD-DINO but not with DenseNet. We provide reusable diagnostics, a leakage-aware protocol and a checklist.

cs.LG · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07949

Beyond the Keyword: A Human-Annotated Benchmark for Arabic Anxiety-Related Discourse

Shimaa Ibrahim, Mabrouka Bessghaier, Md. Rafiul Biswas, Insaf Elouard, Wajdi Zaghouani

原文摘要

Keyword retrieval returns expressions of personal anxiety together with many other uses of anxiety-related language. We present a benchmark of 1,000 Arabic Twitter/X posts retrieved with the keyword qalaq ("anxiety/worry") and annotated for six discourse functions. Two native Arabic-speaking annotators labeled every post independently, reaching 51.1% raw agreement (Cohen's $κ= 0.378$). We then reviewed all 489 disagreements and all 511 agreements under the same guidelines. The review changed 120 of the agreed labels (23.5%), which shows that agreements need auditing as well as disagreements. The final labels form a consensus reference; on a random sample of 200 posts, an additional annotator agreed with it on 60.5% of posts ($κ= 0.517$). Against this reference, Fanar-C-2-27B reaches 79.8% accuracy and macro-F1 0.784 ($κ= 0.749$). Its errors concentrate in the residual category (41.1% of errors; precision 0.905, recall 0.447), whose definition is internally inconsistent in the executed prompt, so the low recall cannot be attributed to the model alone. Sociopolitical Anxiety (27.1%) outnumbers Personal Emotional Expression (22.0%); these are assignment proportions in the sample, not estimates of prevalence or retrieval precision. We release the guidelines, a residual-subtype scheme, a fixed data split, label provenance, and evaluation code.

cs.CL · cs.SI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07948

Circe: Training-Free LLM Self-Evaluation via Component Interaction Consistency

Shuyi Miao, Zheng Li, Xu Xie, Linrui Xu, Fei Shen, Xiaoyu Du, Tat-Seng Chua

原文摘要

As large language models (LLMs) are increasingly deployed in real-world applications, evaluating the correctness of their responses is crucial for reliable use. However, such evaluation is challenging because reference answers are rarely available in practice. Existing reference-free methods mainly rely on output signals, which may assign high scores to incorrect responses and thus do not necessarily reflect correctness. This motivates exploring the model's internal computation for complementary correctness signals. Recent studies exploit internal states, but they mainly analyze hidden-state trajectories across layers, which record only the combined updates of attention and feed-forward networks (FFNs) and overlook how these components interact. We therefore propose Circe, a training-free self-evaluation method that assesses a response using both internal and external signals, without reference answers or repeated sampling. For internal signals, we first introduce component interaction consistency (CIC), which measures the directional alignment between attention updates in earlier layers and attention-induced FFN output changes in later layers. We further incorporate representation geometry (RG) to characterize normalized displacement and angular changes along layerwise hidden-state trajectories. For the external signal, we convert the mean negative log-likelihood of generated tokens into a bounded likelihood confidence (LC) score. Finally, we fuse CIC, RG, and LC into a unified correctness score. Experiments on five LLMs and six benchmarks across four domains show that our method distinguishes correct from incorrect responses more effectively than existing baselines, and generalizes to multilingual, multimodal, and open-world settings.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07947

ChemE-as-Code: An Open-Source Platform for Agentic AI in Chemical Engineering

Artur M. Schweidtmann

原文摘要

ChemE-as-Code provides an open-source environment in which AI agents built on large language models (LLMs) can carry out chemical engineering work and engineers can check it. Its calculation tools range from catalysis through process simulation to plant layout, HAZOP and life cycle assessment, and skills tell a general-purpose agent how to use them. Engineering files are linked, machine-readable and versioned in Git; calculations run outside the LLM, each value records its origin, and automated checks report inconsistencies and out-of-date results by file and line. In an illustrative ammonia case, agents developed a written task into a preliminary basic-engineering package (simulation files, P&IDs, layout, HAZOP, datasheets, relief) for USD 224 of API cost in the design sessions. Planted faults and engineering changes show that the checks find what their rules cover and miss the rest, so they guide human review rather than replace it. No independent engineer has reviewed the design.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07945

tok: a textual concrete syntax of BPMN and DMN for humans and AI agents

Marek Deja

原文摘要

tok is a plain-text notation for Business Process Model and Notation (BPMN) 2.0.2 process models and Decision Model and Notation (DMN) 1.5 decisions. One engine checks a tok document against both standards, compiles the document to XML with an automatic diagram, and serves language-model applications through the Model Context Protocol. The paper classifies the notation as an alternative concrete syntax of the BPMN and DMN metamodels and reports one study. A tok model takes 2.2 times fewer tokens than the smallest BPMN XML of 893 files exported by 37 tools and 7.7 times fewer than the files as exported. The checker signals 98.2% of 1,411 injected faults, against 85.8% for the XML Schema with bpmnlint. Four language models new to tok write valid tok from a one-page reference for 85.7 to 100% of 87 process descriptions from two datasets and valid BPMN XML for every description, and the strongest model writes tok with 25% and 19% fewer tokens than BPMN XML. As agents with a lean skill and one checker tool, the models write valid tok for 97.6 to 100% of the descriptions, the strongest model spends 21% and 14% fewer tokens on tok than on BPMN XML, and a skill which sends the model to read the reference through a tool costs 1.7 to 2.8 times the tokens of the lean skill. Of 47 event logs simulated from public models, 44 fit their source models, and tok imports every model discovered from the logs.

cs.CY · cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.19969

Your Neighbors Know: Leveraging Local Neighborhoods for Backdoor Detection in Decentralized Learning

Sayan Biswas, Antoine Boutet, Davide Frey, Romaric Gaudel, Rachid Guerraoui, Maxime Jacovella, Anne-Marie Kermarrec, Dimitri Lerévérend 等 10 位作者

原文摘要

Decentralized learning (DL) is an emerging machine learning paradigm where nodes collaboratively train models without a central server. However, the collaborative nature of DL makes it vulnerable to backdoor attacks, where a model is taught to behave normally on standard inputs while executing hidden, malicious actions when encountering data with specific triggers. Backdoor attacks in DL remain understudied and existing defenses often overlook DL constraints. We introduce Argus, a novel backdoor detection framework native to DL that requires neither a central coordinator nor prior knowledge of the trigger. In Argus, honest nodes locally analyze received model updates to identify potential backdoor triggers. Nodes then collectively share their triggers with their neighbors and use a structural similarity metric to separate true backdoors from false alarms induced by data heterogeneity. A key insight is that false positive triggers exhibit inconsistencies across participants while true positive ones show consistent patterns. Model updates that fail this collaborative test are rejected, and persistently malicious senders are eventually evicted. We provide the first theoretical convergence guarantees for a DL-specific backdoor detection mechanism, showing that filtering out suspicious model updates with high probability preserves a convergence rate comparable to standard DL. We implement and evaluate Argus on three standard datasets and against three state-of-the-art baselines. Across settings, Argus reduces attack success rates by up to 90 points compared to no defense, while preserving model utility within 5 percentage points of an omniscient oracle. Furthermore, the effectiveness of Argus compared to baselines improves as data heterogeneity increases.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07941

IDPrior: Decoupling Identity Generation from Facial Image Synthesis

Fadi Boutros, Meriç Demirörs, Darian Tomašević, Vitomir Štruc, Naser Damer

原文摘要

Large-scale identity-labeled face datasets are essential for training modern face recognition models, yet collecting and annotating such data is costly and raises privacy and ethical concerns. Existing synthetic face generation methods typically derive identities from predefined class labels, unconditional image generation, or predefined latent sampling strategies, without explicitly modeling the underlying distribution of facial identities. In this paper, we propose IDPrior, a two-stage framework that decouples identity generation from image synthesis. We first learn a diffusion prior in the embedding space of a pretrained face recognition model to model the distribution of facial identities and generate novel identity embeddings. These embeddings are then used to condition a pretrained identity-conditioned diffusion model (DM), enabling the synthesis of multiple images of the same identity. This modular design provides a scalable approach to identity generation while remaining compatible with existing and future identity-conditioned DMs. Experiments indicate that IDPrior generates diverse and well-separated identities while maintaining a closer correspondence to the distribution of authentic identities. Face recognition models trained on datasets generated using IDPrior-generated identities achieve competitive or improved performance compared with existing synthetic-data-based methods across multiple face verification benchmarks. Code and generated datasets are publicly available at https://github.com/fdbtrs/IDperturb.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07940

CardioLM: A multilingual suite of small language models for the cardiology domain

Manuela-Daniela Danu, Miguel Rodríguez-Ortega, Alberto Becerra-Tome, Pablo Arancibia, Fernando Gallego-Donoso, Lorenzo Pratesi, Xi Bai, Andrei-Damian Dinescu 等 40 位作者

原文摘要

Background: Cardiovascular care generates large volumes of clinical free-text documentation in local languages. However, clinical natural language processing (NLP) resources remain concentrated in English, and no existing benchmark is cardiology-specific, multilingual, and broad in entity coverage. Methods: We present two contributions. The first is CardioCCC, a corpus of 508 cardiology case reports originally published in Spanish and extended to Czech, Dutch, English, Italian, Romanian, and Swedish through machine translation, annotation projection, and clinician review, with annotations covering diseases, symptoms, procedures, and medications. The second is CardioLM, comprising CardioBERTa, a set of language-specific encoders obtained by continued pretraining on cardiology and biomedical corpora, and CardioNER, a set of named entity recognition (NER) models fine-tuned on CardioCCC. Results: Cardiology-specific pretraining reduced pseudo-perplexity by up to a factor of eight, yet changed strict span-level F1 by at most 0.04, with benefits concentrated in languages whose backbones lacked biomedical coverage. The jointly trained multilingual XLM-RoBERTa-large models achieved the best strict F1 in nearly every language and entity type, exceeding the strongest monolingual system by up to 0.13 F1. A large share of residual errors concerned boundary detection: relaxed matching recovered 0.10-0.23 F1 for disease, procedure, and symptom, but only 0.01-0.07 for medication. Clinicians rated CardioNER well above a rule- and dictionary-based baseline, with the mean rating across entity types rising from 26% to 73%. Conclusions: Specialty-specific pretraining is not the decisive factor for downstream entity recognition, whereas multilingual joint training yields the strongest results in nearly all settings and a simpler deployment path for multi-country clinical information extraction.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07939

WAM-Sim0.1: World Anchored Memory Meets Online RL for Consistent and Realistic Driving Simulation

Jiahao Cui, Jiaye Li, Wenhao Zhang, Yaoyi Li, Shan Luan, Quanhui Tang, Jianhua Han, Lin Cheng 等 10 位作者

原文摘要

Autoregressive driving world models systematically suffer from structural drift, identity drift, and quality decay over long rollout horizons due to transient conditioning signals that lack persistent state. We present WAM-Sim, a driving world model anchored by a persistent hierarchical memory and optimized via online flow-matching RL. WAM-Sim structures persistent context across three temporal and semantic scales: pose-aligned structural tokens encoding persistent road topology, read-only scene tokens supplying geolocated background appearance, and write-once instance tokens preserving individual traffic participant identities across occlusions and chunk boundaries. To restore visual sharpness and physical plausibility degraded by multi-scale conditioning, we introduce an online post-training framework that optimizes self-generated rollouts via flow-matching RL guided by hierarchy-aligned visual rewards and a vision-language model physical judge. The invariant memory empirically confines policy optimization within the anchored context, helping suppress semantic collapse and reward hacking, while online RL systematically enforces physical commonsense and fine-grained visual fidelity. On the nuScenes benchmark, WAM-Sim achieves a superior generation fidelity (FID=3.47, FVD=25.72) and strong downstream perception performance (24.16 mAP, 71.23 road mIoU). On minute-scale rollouts of self-collected data, WAM-Sim substantially mitigates structural and identity drift, preserving high scene similarity and subject identity coherence across extended horizons. Project page: https://fudan-generative-vision.github.io/WAM-Sim.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.03761

AgentSelect: Benchmark for Narrative Query-to-Agent Recommendation

Yunxiao Shi, Wujiang Xu, Tingwei Chen, Haoning Shang, Ling Yang, Yunfeng Wan, Zhuo Cao, Xing Zi 等 10 位作者

原文摘要

LLM agents are rapidly becoming the practical interface for task automation, yet the ecosystem lacks a principled way to choose among an exploding space of deployable configurations. Existing LLM leaderboards and tool/agent benchmarks evaluate components in isolation and remain fragmented across tasks, metrics, and candidate pools, leaving a critical research gap: there is little query-conditioned supervision for learning to recommend end-to-end agent configurations that couple a backbone model with a toolkit. We address this gap with AgentSelect, a benchmark that reframes agent selection as narrative query-to-agent recommendation over capability profiles and systematically converts heterogeneous evaluation artifacts into unified, positive-only interaction data. AgentSelectcomprises 111,179 queries, 107,721 deployable agents, and 251,103 interaction records aggregated from 40+ sources, spanning LLM-only, toolkit-only, and compositional agents. Our analyses reveal a regime shift from dense head reuse to long-tail, near one-off supervision, where popularity-based CF/GNN methods become fragile and content-aware capability matching is essential. We further show that Part~III synthesized compositional interactions are learnable, induce capability-sensitive behavior under controlled counterfactual edits, and improve coverage over realistic compositions; models trained on AgentSelect also transfer to a public agent marketplace (MuleRun), yielding consistent gains on an unseen catalog. Overall, AgentSelect provides the first unified data and evaluation infrastructure for agent recommendation, which establishes a reproducible foundation to study and accelerate the emerging agent ecosystem.

cs.AI · cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07937

Joint Modeling of Conditional Mean and Variability in Multilevel Functional Data: Application to Postprandial Glucose Trajectories in the AEGIS Study

Yang Xiao, Francisco Gude, Marcos Matabuena

原文摘要

Functional data analysis provides a framework for studying time-varying associations between covariates and high-frequency biological signals. In digital health, participants often contribute repeated functional trajectories, yet existing multilevel regression methods largely focus on the conditional mean, overlooking variability and its role in biological heterogeneity. We propose a heteroskedastic functional mixed-effects regression framework that jointly models the conditional mean and variance of repeated trajectories, with participant-specific random effects in both components. We also develop a participant-level bootstrap to quantify uncertainty in estimated functional parameters. We apply the method to postprandial glucose trajectories from the AEGIS study. Premeal glucose, carbohydrate intake, and meal type show distinct time-dependent associations with glucose variability, whereas HbA1c is more strongly associated with the conditional mean than with variability. Substantial between-participant differences in residual variability remain even after accounting for observed covariates. These findings show that modeling conditional variability alongside the mean provides insights into glucose regulation and individual heterogeneity that mean-focused analyses may miss. More broadly, the proposed framework enables joint characterization of average responses, variability, and participant-specific heterogeneity in repeated biological signals.

stat.ML · cs.LG · stat.AP · stat.ME

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2506.08911

Implementing Keyword Spotting on the MCXN947 Microcontroller with Integrated NPU

Petar Jakuš, Hrvoje Džapo

原文摘要

This paper presents a keyword spotting (KWS) system implemented on the NXP MCXN947 microcontroller with an integrated Neural Processing Unit (NPU), enabling real-time voice interaction on resource-constrained devices. The system combines MFCC feature extraction with a CNN classifier, optimized using Quantization Aware Training to reduce model size with minimal accuracy drop. Experimental results demonstrate a 59x speedup in inference time when leveraging the NPU compared to CPU-only execution, achieving 97.06% accuracy with a model size of 30.58 KB, demonstrating the feasibility of efficient, low-power voice interfaces on embedded platforms.

cs.HC · cs.AR · cs.LG · cs.PF · cs.SD

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.05730

The Male Abstraction Bias in Internet Culture and Large Language Models

Douglas Guilbeault, Bhargav Srinivasa Desikan

原文摘要

Conceptual abstraction and gender are two equally central aspects of the human mind, yet they have traditionally been studied in isolation from one another, as though they were fundamentally separate. Here, we find gender and abstraction are systematically linked throughout the space of concepts spanning single (N = 40,000) and multi-word expressions (N = 67,000): across billions of words and millions of images on the internet --- and across numerous measurement techniques, including human and AI classifications --- more abstract concepts are more associated with men, a pattern we show replicates in languages around the world. This male abstraction bias not only holds across semantic domains, but it also maps onto grammatical structure: verbs and adverbs are more abstract and more male-coded, revealing a system-wide trace of stereotypes accentuating agentic qualities in men. Furthermore, we show this bias readily emerges in the free associations humans and AIs produce in controlled online tasks, indicating its psychological internalization and its algorithmic reproduction. These findings identify a latent structure in conceptual space that unifies a range of stereotypes: for example, framings of women as more embodied, emotional, and warm, versus men as more cognitive, rational, and competent; as well as erroneous views of men as better at mathematics, science, and engineering. More broadly, by analyzing an unprecedentedly large, multimodal sample of online data, we provide culture-wide evidence of gender as a core organizing principle shaping conceptual space far beyond the characterization of people and social roles.

cs.CY · cs.CL · cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07935

Towards Scalable Diagnostic-Driven Whole-Slide Image Retrieval for Pathology Archives

Jingsong Liu, Youssef Wally Han Li, Weiwei Zhou, Jing Dai, Elisabeth Wetzer, Peter J. Schüffler

原文摘要

The growing adoption of digital pathology has rapidly expanded collections of hematoxylin-and-eosin whole-slide images, yet efficient navigation through these archives remains challenging, as metadata is often inconsistent or unavailable. Content-based image retrieval addresses this challenge by identifying similar cases directly from visual representations instead of manual annotations or metadata. Existing retrieval systems have demonstrated promising performance but largely rely on handcrafted indexing pipelines and predefined sampling strategies, constraining scalability and generalization. Here, we present CLEAR-WSI (Constant-Length Embedding for Automatic Retrieval of Whole-Slide Images) as a scalable, diagnostic-driven slide-retrieval framework, validated on both public and clinical data. Using a fixed-length slide embedding, CLEAR-WSI refines retrieved candidates with either a predicted diagnostic label or the ground-truth label, depending on the retrieval setting. Newly processed cases are subsequently added to the expanding memory bank, allowing the retrieval archive to grow over time. On a comprehensive benchmark consisting of two public and one private clinical datasets representing four retrieval tasks, CLEAR-WSI improves Precision@5 over the strongest evaluated baseline, with gains on CAMELYON16 (3.10), BRACS-1 (2.75), BRACS-2 (1.95), and X-HER2 (3.75). Additional ablation and latency studies further examine the contribution of each component and highlight its potential for scalable deployment.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07934

The Blindfolded Controller: Decision Model-Guided Training for Reinforcement Learning

Muhammad Ibrahim Khan, Aniket Dixit, Faizan Ahmed, James Brusey

原文摘要

Reinforcement learning (RL) provides a framework for continuous improvement through interaction with an environment. However, RL agents struggle against tasks that offer exploration challenges and sparse rewards, because learning efficient policies from scratch is slow and sample-inefficient. In contrast, decision models (DMs), given a description of the environment and task, can perform well in sparse-reward tasks, but, as they do not learn from reward, they are not able to improve towards the optimal solution. In this paper, we present Decision Model-Guided Training (DMGT), a technique that uses a DM with a description of the environment and task to initialise an RL policy, combining the DM's ability to act without training with RL's ability to improve from reward. Instead of exploring from scratch, the agent reaches the goal and receives reward from its first episodes, and RL then improves its policy beyond what the DM achieves. We demonstrate through experiments on seven tasks that our approach outperforms RL in all seven and DM in five. In addition, we provide comprehensive guidelines, derived from ablation studies, for describing an environment and task to a DM.

cs.LG

查看论文
arXiv ↗PDF ↗