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

+0新增论文
+0其中 AI 相关
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-08 04:03 · 全站最近入库：2026-11-07 17:43各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 04:52 — 2026-11-08 04:52（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：2026-11-08 04:03最近发现新增版本：2026-11-07 17:43库内论文最新更新时间：2026-11-06 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。

17,100 已收录论文14,661 AI 相关4,056 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 17,100 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 04:02（北京时间）
新论文 · v1arXiv:2611.04714

Hybrid acoustic and pretrained embedding feature fusion for unmanned aerial vehicle detection using stacking ensemble learning under a leakage-aware evaluation protocol

Zahid Iqbal

原文摘要

Small multirotor drones produce a characteristic acoustic signature, and microphones offer a low-cost way to detect them. High accuracies have been reported on public drone audio benchmarks, often with random clip-level splits of datasets built from a few long recordings and pieces of existing sound collections, so pieces of one source can appear in both training and test data. We study the binary task of the public DroneAudioDataset (11,704 one-second clips). Its 1,332 drone clips come from 257 five-second chunks of 7 recordings, and 96.4% of its non-drone clips are pieces of the 2,000 clips of the ESC-50 sound dataset. A grouped, source-disjoint protocol (five folds, three repeats) is compared with a random split. Each clip is described by 57 hand-crafted acoustic descriptors, reduced by a hybrid minimum-redundancy maximum-relevance and ReliefF selection or by NSGA-II multi-objective search, and by a 1024-dimensional embedding from the pretrained YAMNet network. Random Forest and XGBoost learners on both views form a stacking ensemble. Under the grouped protocol, the two-view stack reached a mean accuracy of 95.29% (SD 1.62 points over 15 test folds), a specificity of 98.29% and an area under the ROC curve of 0.990, and it correctly classified 98.78% of unseen ESC-50 source clips as non-drone. The random split overstated accuracy by 1.89 to 3.22 points for the four models. Adding YAMNet embeddings to the hand-crafted view raised accuracy by 1.11 points (higher in 12 of 15 folds). Hybrid selection matched the accuracy of all 44 baseline descriptors with 16 to 18 features, and NSGA-II retained 4 to 6 features at lower accuracy. The stack took 51.0 ms per clip on one CPU thread. Source-disjoint evaluation is needed for a fair benchmark on this dataset, and fusing hand-crafted descriptors with pretrained embeddings gives a small but consistent gain at modest computational cost.

cs.SD · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.02957

Cyber-JEV: Matched Contrastive Fine-Tuning of Language Models for Fast Source-Code Vulnerability Triage

Zhuyi Zhao, Shengjie Yuan, Shengyu Wang, Kang Wei, Wang Yang, Wenchao Xu, Fushuo Huo

原文摘要

Single-pass scoring models such as Jev give each code function a vulnerability probability, so that security teams can rank many functions for review without generating written explanations. Training an open-weight model for this task is limited by data. Benchmarks with both vulnerable and non-vulnerable labels keep few vulnerable functions once examples related to the test data are removed, while larger public vulnerability records mostly contain vulnerable functions only. Mixing the two lets the data source predict the label, and training on the labeled data alone leaves a model that often scores a fixed function above its vulnerable original. We present Cyber-JEV, a fine-tuning method that uses fix commits to turn these records into comparison groups. Each group holds a vulnerable function, its patched version and up to two unchanged functions from the same file, so the model sees the change that removed a recorded defect. One shared model learns two tasks: classifying functions from the labeled reference data, and ranking the vulnerable function above the other members of its group. At test time the input is one function and the output is a vulnerability score. On a test benchmark of 7,270 functions, an ensemble of five fine-tuned Qwen3.5-4B models reaches an area under the receiver operating characteristic curve of 0.814, compared with 0.743 for Jev 1.13. With the 4,031 alerts of Jev as the review budget, it misses 16 of 322 vulnerable functions instead of 39. Compared with training on the reference data alone, it ranks the vulnerable version above the patched version 14.8 to 29.2 percentage points more often on three sets of real fixes. Such scores can order the changed functions of a pull request or a release for review under a fixed budget.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04712

VISAGE: Vertex-based Intrinsic Surface Appearance GEneration via Dual-Stream Diffusion for Arbitrary 3D Heads

Jeremias Krauß, Pragati Jaiswal, René Schuster, Didier Stricker

原文摘要

Recovering identity-faithful, physically based surface appearance for 3D human heads from sparse images remains challenging. Existing methods often rely on UV-based pipelines, introducing seam artefacts, or operate in image space, limiting surface consistency. We present VISAGE, Vertex-based Intrinsic Surface Appearance GEneration, a surface-based conditional diffusion framework that synthesises per-vertex albedo and roughness directly on arbitrary mesh topologies, without requiring consistent UV parameterisation at training time. VISAGE combines global spectral processing with local geodesic K-Nearest-Neighbour refinement, enforcing structural coherence while restoring detail beyond the truncated spectral basis. Multi-view RGB images condition the network via visibility-aware cross-attention, enabling occlusion-robust synthesis across the full head surface. Region-specific modules specialise in semantically demanding and distinct areas (eyes, mouth, skin and hair), while a tangent-space output projection recovers fine iris detail. We further introduce a scalable procedural augmentation pipeline that enriches raw geometry scans with physically plausible albedo, roughness and normal maps for training. The predicted attributes render directly as a single RGBA vertex-colour channel. VISAGE reduces FID by 42.7% on NPHM and 22.5% and 4.4% on zero-shot FaceVerse and i3DMM, respectively, relative to the strongest baseline, with a 7.2M-parameter core network.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04711

Cycle WAM: Coupling Action and Video through Cycle Consistency

Qinglin Yang, Jiepeng Wang, Yuxing Huang, Haibin Huang, Kai Xu, Chi Zhang, Ruizhen Hu, Xuelong Li

原文摘要

Recent advances in video modeling have driven substantial progress in world action models (WAMs). Existing approaches exploit pretrained video priors by decoding actions from latent representations or inferring them from generated videos. The underlying link is causal: robot actions produce changes in the scene, and video observations of these changes provide evidence for inferring the actions that produced them. However, existing training formulations do not by themselves ensure that actions and their predicted visual consequences are consistent, potentially limiting the use of pretrained capabilities. We treat video and action as paired modalities linked by this causal relationship and learn their correspondence through a unified training framework designed to better exploit pretrained video priors. Cycle WAM first augments video-action co-training with bidirectional conversion to reinforce cross-modal correspondence and recover forward and inverse dynamics. It then introduces a differentiable cycle-reconstruction objective to further couple the two mappings. The resulting model supports both forward and inverse dynamics, with the potential to improve performance through more effective use of pretrained video priors. Cycle WAM achieves state-of-the-art performance among comparable methods on LIBERO-Pro and substantially improves DreamZero on DROID. Comparisons with UWM characterize its inverse-dynamics performance and show sharper visual detail in the displayed forward-dynamics predictions.

cs.CV · cs.AI · cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.26746

4-Block Integer Programming is in FPT

Martin Koutecký, Alexandra Lassota, Koen Ligthart

原文摘要

Integer programming is a fundamental and important NP-hard problem. This motivated extensive efforts in studying several tractable subclasses. One of the most important, unresolved complexity questions is the parameterized complexity of 4-block IPs, a natural class characterized by having a diagonal matrix with small blocks after deleting few rows and columns. Over the years, significant progress has been made in improving algorithms for 4-block IPs, but the question whether such IPs can be solved in FPT time, parameterized by the block dimensions and largest matrix coefficient, has remained open. This question is repeatedly highlighted, most recently by Koutecký [IPEC 2025] and by Eisenbrand and Rothvoss [SODA 2026]. We resolve this question in the positive by providing an FPT time algorithm. Our algorithm can optimize non-linear, separable convex objective functions, and can be extended to broader classes of constraint matrices (such as tree-fold or multi-stage) and allows appending few ``global'' columns to it, and it allows coefficients unbounded by the parameters in those columns. It is known that tractability cannot be extended further in any of those directions. The key structural property that we establish is that a function $f\colon\mathbb Z^n\to\mathbb R$ that is integer midpoint convex, i.e., $f(x)\le\tfrac12f(x-p)+\tfrac12f(x+p)$ for all $x,p\in\mathbb Z^n$, can be extended to a convex function on the set $2d\mathbb Z^n\cap L$ if $L$ is a linear subspace of dimension $d$. This closes the gap in a recent work by Ligthart [arXiv 2606.30330, 2026], which allows us to extend the previous algorithm that solves 4-block integer programs with a single global variable to incorporate any parameterized number of global variables. As an example, we apply our algorithm to solve an open problem posed by Boehmer and Koana [ACM Trans. Algorithms, 2024] in Max-Min Fair Matching.

cs.CC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04710

DenseTwins: Dense Modality Decoupling for Multimodal Self-Supervision

Carlo Sgaravatti, Daniele Kopyshevskiy, Davide Secco, Giacomo Boracchi

原文摘要

Multimodal perception is central to many computer vision applications, including robotics and autonomous driving, where different sensing modalities provide complementary cues. Self-supervised learning offers a scalable solution for exploiting large amounts of unlabeled multimodal data. However, existing methods either neglect modality-specific information by enforcing feature-space alignment between modalities or learn only global representations without preserving spatial structure. We propose DenseTwins, a multimodal self-supervised framework that learns dense representations by explicitly decoupling the dense feature space into shared and modality-specific components. The proposed approach combines dense cross-modal correspondences with redundancy-reduction objectives, enabling the model to capture both shared semantics and modality-specific cues within a structured dense embedding space. DenseTwins jointly optimizes an intra-modal objective across augmented views and a cross-modal objective that aligns shared features while decorrelating modality-specific information. We evaluate DenseTwins across multiple multimodal benchmarks and sensing setups, achieving state-of-the-art or competitive performance across multimodal self-supervised baselines. Code available at: https://github.com/CarloSgaravatti/DenseTwins.

cs.CV · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.11285

Max Independent Set Remains NP-hard when Excluding a Planar Induced Minor (and More)

Édouard Bonnet, Yeonsu Chang

原文摘要

We show that Max Independent Set (MIS) remains NP-hard in graphs excluding the $5 \times 5$ grid as an induced minor. This negatively answers a question of Dallard--Milanič--Štorgel that has attracted sustained attention, and refutes a conjecture by Gartland and Lokshtanov. Unless $N$-variable 3-SAT can be solved in time $2^{\mathcal O(N^{1-\varepsilon})}$ for some $\varepsilon > 0$, MIS requires $2^{Ω(n^{1/2-o(1)})}$ time on $n$-vertex graphs in this class. This complements a $2^{\widetilde{O}(n^{2/3})}$-time algorithm on any $H$-induced-minor-free class by Korhonen and Lokshtanov. Exploiting a connection between low twin-width or reduced parameters on one hand and planar-induced-minor-freeness on the other, we further show that 3-Coloring, Feedback Vertex Set and Dominating Set are NP-complete on weakly sparse graphs of reduced component max-leaf (hence twin-width) at most 3, even when a witnessing contraction sequence is given. Classes of bounded reduced component max-leaf (by any constant) and of twin-width at most 3 are known to exclude a fixed planar graph as an induced minor. The 3-Coloring and Feedback Vertex Set results refute more cases of the Gartland--Lokshtanov conjecture, even when the inputs are weakly sparse. The complexity of MIS in weakly sparse graphs excluding a planar induced minor remains open.

cs.CC · cs.DM · cs.DS · math.CO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04709

Learning from Unlabeled Photographs for General Oral Image Analysis

Zhong-Shi Zhang, Zi-Li Yu, Xiao Xiao, Huan Liu, Gui-Song Xia, Cui Huang, Meng-Xun Li

原文摘要

Oral photographs contain rich clinical information and hold significant potential for artificial intelligence applications; however, most models are trained for individual tasks and rely on costly expert annotations. We hypothesized that self-supervised training on unlabeled oral photographs could produce transferable visual representations for heterogeneous vision tasks. To test this hypothesis, we developed DOVE (Dental Optical Visual Encoder) by domain-adaptive self-supervised pretraining on approximately 530,000 unlabeled oral photographs collected from publicly accessible sources. DOVE was benchmarked against 3 established baselines across 5 classification datasets and 4 segmentation datasets, covering both frozen backbone evaluation and end-to-end finetuning. DOVE achieved the strongest overall performance, ranking best in few-shot transfer and label efficiency on most benchmarks. Under the 20-shot frozen-backbone protocol, DOVE outperformed the second best DINOv3 by 4.37 percentage points in mean macro-F1 across classification datasets and by 4.49 percentage points in mean macro-Dice across segmentation tasks. Under end-to-end finetuning, DOVE achieved at least 80% of the strongest full-data baseline's performance across most evaluation datasets using only 10% of the labeled training data. Qualitative retrieval and feature analyses further indicated better organization of image-level and spatial representations. These findings support DOVE as a generalizable and label-efficient backbone for oral vision research.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04708

CLARA: A Cognitively-Driven Clarification Framework for Grounding Ambiguous Requests

Dimitrios Bekris, Marios Glytsos, Panagiotis P. Filntisis, Niki Efthymiou, George Retsinas, Petros Maragos

原文摘要

Robotics and AI systems are increasingly deploying large vision-language models (LVLMs) to follow high-level instructions, from routine household chores to more complex organizational tasks. Yet, broad directives like "clean the room" or "organize the desk" frequently omit crucial details about user preferences and specific arrangement of objects that influence the desired outcome. Without any further guidance, such models tend to overestimate their grasp of ambiguous instructions and frequently assume they have sufficient understanding despite missing important details. In this paper, we propose CLARA (Conversational cLArification for Robotic Arrangement), a cognitively-driven clarification framework that proactively elicits key information from users, in a similar fashion as humans' clarification seeking behavior. Through targeted questioning, CLARA refines ambiguous requests into structured, detailed instructions describing precisely how objects should be organized or rearranged, according to the user's preferences. These clarifications then guide a diffusion-based image generation pipeline, producing realistic visual renderings of the final, desired scene. This final rendering also serves as a visual confirmation of the system's understanding from the user. Experimental results and user studies demonstrate that CLARA leads to more accurate and consistent outcomes compared to another State-of-the-Art LVLM system, highlighting the importance of interactive clarification for bridging the gap between vague directives and fully grounded task specifications.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04707

Methodological Assessment of Instrumented Indentation for Spatially Resolved Mesoscale Stiffness and Creep in Short Fiber-Reinforced Injection-Molded PBT Components

Eduard Klatt, Natalie Rauter

原文摘要

Instrumented indentation enables assessment of local mechanical properties in heterogeneous polymer systems, but specimen preparation and the selected indentation protocol significantly influence the quantitative interpretation of the measured response. This study develops and evaluates an experimental methodology for spatially resolved mesoscale characterization of both unreinforced and short fiber-reinforced composites. An unreinforced material system is used as a reference material to systematically examine the effects of indentation spacing, surface preparation, maximum indentation load, temporal loading parameters, and unloading evaluation. Indentation loads of 500, 1000, and 1750 mN are investigated in complementary experimental campaigns. The apparent indentation modulus exhibits moderate sensitivity to indentation load and loading time within the studied ranges. In contrast, indentation depth and the creep-related depth increment display greater sensitivity to the applied load history. Surface polishing minimizes topographical disturbances and enables reliable identification of residual indentation profiles and pile-up. Based on these methodological findings, a final load-hold-unload protocol with an indentation load of 1750 mN, a loading time of 6 s, a holding period of 300 s, and an unloading time of 4 s is applied to both unreinforced material and short fiber-reinforced composites. The mean apparent indentation modulus increases from 2.91 GPa for unreinforced material to 6.65 GPa for short fiber-reinforced composites, while the mean depth of indentation creep decreases from 2.36 to 1.91 microns. The coefficient of variation also increases for both quantities, indicating that short-fiber reinforcement enhances mean local stiffness and introduces pronounced spatial heterogeneity in both stiffness-related and time-dependent mesoscale indentation responses.

cs.CE · cond-mat.mtrl-sci

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.03183

Auto-Research Agent on MSA Organization to Improve Protein-Protein Complex Structure Prediction

Zilu Zhang, Jing Bao, Lifeng Qiao, Sheng Xu, Qiantai Feng, Siqi Sun, Yang Yang

原文摘要

Protein-complex structure prediction with AlphaFold 3 depends on MSA content, depth, and cross-chain pairing. Current pipelines apply uniform recipes, typically maximizing depth and pairing by species, yet even whether cross-chain pairing helps AF3 remains contested. We show that the value of both depth and pairing is strongly target-dependent, so no single recipe is optimal across interfaces. We introduce an autonomous agent that treats a frozen AF3 as a black-box experimental instrument. For each target, the agent formulates biological hypotheses, analyzes and reorganizes the MSA, and iteratively refines sequence selection and pairing using predictor label-free signals alone. On 1{,}015 protein--protein interfaces from three benchmarks released after AF3's training cutoff, the agent improves overall interface DockQ over AF3's default pipeline and fixed MSA recipes on every benchmark, while using on average 60\% fewer MSA sequences than the default. Gains are largest for inter-species heteromers, where species-based pairing is unreliable: mean DockQ increases from 0.465 to 0.612 on FoldBench and from 0.482 to 0.562 on HD439. The improvements arise from both sequence construction and pairing policy, including deliberate non-pairing. These results recast MSA design as a target-specific problem and show that an autonomous agent can adapt it at test time through biological reasoning and self-directed, confidence-guided experimentation.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2604.12452

Latent-Condensed Transformer for Efficient Long Context Modeling

Zeng You, Yaofo Chen, Qiuwu Chen, Ying Sun, Shuhai Zhang, Yingjian Li, Yaowei Wang, Mingkui Tan

原文摘要

Large language models (LLMs) face significant challenges in processing long contexts due to the linear growth of the key-value (KV) cache and quadratic complexity of self-attention. Existing approaches address these bottlenecks separately: Multi-head Latent Attention (MLA) reduces the KV cache by projecting tokens into a low-dimensional latent space, while sparse attention reduces computation. However, sparse methods cannot operate natively on MLA's compressed latent structure, missing opportunities for joint optimization. In this paper, we propose Latent-Condensed Attention (LCA), which directly condenses context within MLA's latent space, where the representation is disentangled into semantic latent vectors and positional keys. LCA separately aggregates semantic vectors via query-aware pooling and preserves positional keys via anchor selection. This approach jointly reduces both computational cost and KV cache without adding parameters. Beyond MLA, LCA's design is architecture-agnostic and readily extends to other attention mechanisms such as GQA. Theoretically, we prove a length-independent error bound. Experiments show LCA achieves up to 2.5$\times$ prefilling speedup and 90% KV cache reduction at 128K context while maintaining competitive performance.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2509.19930

How deep is your network? Deep vs. shallow learning of transfer operators

Mohammad Tabish, Benedict Leimkuhler, Stefan Klus

原文摘要

We introduce RaNNDy, a randomized neural network framework for learning transfer operators and their spectral decompositions. By fixing the weights of the hidden layers and training only the output layer, RaNNDy achieves significant reductions in computational costs -- often by two orders of magnitude -- with similar accuracy compared to state-of-the-art deep learning methods. The method is less sensitive to hyperparameter tuning and provides a closed-form solution for the output layer weights that directly represent eigenfunctions of the learned operator. Moreover, it is possible to estimate uncertainties associated with the computed spectral properties via ensemble learning. We demonstrate the efficacy of the proposed approach using diverse benchmark problems, including stochastic dynamical systems and protein folding processes, highlighting the strengths but also weaknesses of RaNNDy.

cs.LG · math.DS · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04701

Proving the Wrong Program: Miscompilations as a Threat to zkVM Guarantees

Hui Xuan Tan, Stefanos Chaliasos, Alastair F. Donaldson

原文摘要

A zero-knowledge virtual machine (zkVM) lets an untrusted prover convince a verifier that a program, typically Rust compiled to RISC-V, ran correctly. The proof covers the compiled binary, so a miscompilation can make a correct zkVM produce a valid proof of a computation that differs from the developer's source. We present the first empirical study of miscompilation as a threat to zkVM guarantees, on the production zkVMs SP1 and Jolt. We assemble 88 known rustc and LLVM miscompilations with Rust reproducers, using an LLM agent to recover Rust triggers for 60 of 124 LLVM bugs reported only as LLVM IR. Many of the bugs carry over to zkVMs: 48 of the 88 make a guest commit a wrong output on SP1 and 46 on Jolt, including the same 15 rustc bugs on both. Most bugs that do not reproduce never reach the faulty code on the zkVM's target, e.g. because they need an instruction-set extension. Existing guest programs are rarely affected by accident. Across 13 guests of 10 popular SP1 projects, the buggy and the fixed compiler produce byte-identical binaries in 447 of the 552 guest-bug pairs that build, and the other 105 have the same code or agree on every input we ran. An attacker who contributes code to a guest, however, can trigger these bugs on purpose. For about $40 per project, an LLM agent found patches that look like ordinary optimisations, preserve the behaviour of the guest's source, and expose a known bug in 12 of 366 project-bug pairs, across 11 of 20 projects. In four cases the guest commits a wrong output, including an Ethereum client that rejects a valid block, and in the other eight it fails on a valid input. Reviewing or formally verifying the zkVM or the guest's source cannot catch such a patch, because both are correct. zkVM projects should treat their compiler as part of their trusted base and track the known bugs of their toolchain.

cs.PL · cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04700

One-shot Distributed Learning via Weighted Averaging with Server-side Information

Pavle Tepavčević, Dušan Jakovetić, Miloš Savić

原文摘要

Distributed learning has drawn considerable attention due to its capability of learning from distributed data without aggregating raw observations. However, frequent exchange of model updates can become the main bottleneck of communication. Therefore, one-shot approaches where each worker fits a local model and sends it to the server to aggregate emerge. It is known that averaging can achieve the so-called pooled-data mean squared error (MSE) order of a hypothetical node that has access to data from the server and all the workers, and performs empirical risk minimization (ERM) on it. However, when the number of workers increases too fast compared to the local sample size, nonzero local estimation bias prevents averaging from achieving this order. In this paper, we study whether independent server data can overcome this limitation. We consider $m$ workers with $n$ observations each and a server with $p$ observations, all i.i.d., giving $N=mn+p$ observations in total. Under certain regularity conditions, a pooled-data ERM achieves MSE of order $\mathcal O(N^{-1})$. We analyze deterministic nonnegative averaging of convex-loss M-estimators, with equal worker weights and the server's own estimator included. Under our assumptions, including nonzero local bias of order $n^{-α}$, $α\geq1$, sample-size weighted averaging achieves the pooled-data MSE order whenever $m=\mathcal O(n^{2α-1})$. Above this worker scale, it does so if and only if $p=Ω(nm\cdot m/n^{2α-1})$. Hence, server-only estimation, whose MSE is of order $\mathcal{O}(p^{-1})$, can achieve pooled-data order while sample-size weighting fails. Analytical examples and synthetic experiments illustrate when averaging matches the pooled-data MSE order, complemented by CIFAR-10 experiments comparing aggregation strategies with linear and nonlinear classifiers.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04699

Glauber Dynamics for Sampling Colorings: Rapid Mixing above $(1+1/\mathrm{e})Δ$ via Hidden Hard-Core Models

Xiongxin Yang

原文摘要

We show that for every $γ>0$ and every sufficiently large $Δ$, the Glauber dynamics for proper $q$-colorings of any $n$-vertex graph of maximum degree $Δ$ has spectral gap $Ω_γ(1/n)$, and hence mixing time $O_γ(n^2\log q)$, whenever $q\ge(1+1/\mathrm{e}+γ)Δ$. Our proof establishes a Bochner-type inequality by exploiting the spectral gaps of hard-core models hidden in the color classes. The constant $1+1/\mathrm{e}\approx1.368$ comes from the uniqueness threshold $\approx\mathrm{e}/Δ$ of the hard-core model on the infinite $Δ$-regular tree.

cs.DS · cs.DM · math.CO · math.PR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04697

When Ground Truth Is Not Ground Truth: Automatic Labeling for Hallucination Detection

Rounak Sen, Divya Kumari, Deeksha Varshney

原文摘要

Hallucinations in Large Language Models (LLMs) remain a major challenge, as they can produce misleading, factually incorrect, or unverifiable information, thereby undermining their trustworthiness and reliability. However, reliable ground-truth labels remain a key challenge in evaluating hallucination detectors. Recent studies often construct labels automatically by comparing model generations with reference answers using similarity metrics such as BLEURT. This implicitly treats BLEURT similarity as a proxy for hallucination, despite its English-centric supervision, unbounded score range, and design as a similarity metric rather than a factuality measure, making threshold-based ground-truth construction potentially unreliable. Through comprehensive experiments using 15 automatic supervision judges, seven hallucination detection baselines, two generator models, two QA datasets, and five languages, we demonstrate that detector performance varies substantially with the choice of supervision judge. Human validation reveals substantial differences in labeling reliability, with QGen-9B achieving the lowest overall misclassification rate (12.86%), while BLEURT and BLEURT-n exhibit rates of 47.23% and 47.32%, respectively. Our findings highlight the limitations of automatic similarity-based labeling and the need for more reliable judging methods that better capture semantic and factual correctness.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04695

Surrogate Models for Stochastic Al-Cu Phase-Field Solidification

Simon Savukoski, Tatu Pinomaa

原文摘要

Phase-field models resolve microstructural evolution during rapid alloy solidification, but their computational cost limits long trajectories, stochastic ensembles, and studies across process conditions. We present a variance-preserving denoising diffusion bridge model (VP-DDBM) for state-conditioned prediction of two-dimensional Al-Cu solidification. Given the current phase, concentration, and prescribed temperature fields, the model predicts the subsequent state and is applied autoregressively. Across two held-out thermal gradients, VP-DDBM produces lower long-horizon errors than deterministic U-Net and SI-ConvNeXt baselines in domain-mean phase, domain-mean Cu concentration, and leading-tip position. It also retains fine dendritic structure over long rollouts, whereas the deterministic U-Net progressively smooths the morphology. VP-DDBM predicts the phase and concentration evolution approximately $73\times$ faster than the phase-field solver, showing potential for faster process-condition screening and ensemble-based microstructure studies.

cs.LG · cond-mat.mtrl-sci

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04693

Rate-Distortion-Perception Tradeoff for Vector Gaussian Sources with Limited Common Randomness: Exact Characterization and Approximate Universality

Wentao Wang, Shuo Shao, Ruibin Li, Jingjing Qian, Jun Chen, Bin Xia

原文摘要

The distortion-rate-common randomness-perception (DRCP) theory characterizes how limited common randomness (CR) improves reconstruction fidelity under perceptual constraints, thereby providing an information-theoretic foundation for generative compression. In this paper, we characterize the DRCP tradeoff for vector Gaussian sources with limited CR under the squared-error distortion measure and the squared Wasserstein-2 perception measure. Specifically, we first establish a generalized reverse waterfilling characterization of globally optimal allocations. Second, we derive an analytical upper bound on the DRCP function through sequential greedy allocation of rate and CR. For fixed rate and CR budgets, the resulting representation is independent of the perception threshold. Finally, we establish its approximate universality through uniform performance guarantees: the achievable distortion exceeds the optimal distortion by at most $2ρ^*\approx0.2897$ times the total source variance, whereas the optimal-to-greedy distortion ratio is at least $η^*\approx0.7517$.

cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04692

Just Between Us? Exploring a Wearable-Mediated Channel for Discreet Human-Agent Interaction in a Shared Game Setting

Atikkhan Faridkhan Nilgar, Manuel Dietrich, Kristof Van Laerhoven

原文摘要

In shared settings, social robots may need to exchange information with an individual while limiting co-present others' access to or interpretation of that information. Publicly observable speech and gestures may not adequately support such exchanges. We investigate a wearable-mediated channel for discreet interaction that combines in-ear audio messages with deliberate rightward head tilts as responses. To examine its feasibility and participants' experiences, we studied 20 pairs (40 participants) playing a card game with a screen-based conversational agent representing a social robot, controlled by a researcher in a Wizard-of-Oz setup. Each pair played with and without the channel. One participant wore the device (the wearer), while the other (the non-wearer) was informed about the channel after gameplay. The channel conveyed information that could help the wearer or robot character select an opponent they could defeat. The information exchange and subsequent opponent selection occurred as intended in 39 of 40 channel-mediated turns. Wearers reported low perceived pressure/tension in both conditions, with no statistically significant difference between conditions, and favorable usability immediately after use. Retrospective interviews, however, revealed varied accounts of noticing the interaction among non-wearers and contrasting perceptions of teamwork and unfairness. These findings support the feasibility of wearable-mediated exchanges within this game and identify awareness and fairness as considerations for future designs.

cs.HC · cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.14795

JediKG: Return of the Schema

Ivan Diliso, Roberto Barile, Nicola Fanizzi, Claudia d'Amato

原文摘要

Benchmark datasets for Knowledge Graph Refinement typically contain only ground facts, discarding the schema available in the source knowledge graph. This limits the evaluation of Neural-Symbolic methods that leverage expressive schemas. We present JEDIKG the first resource that systematically addresses these gaps through two components: JDEX a general configurable tool for extracting complete, portable, modular dataset from any RDF/OWL knowledge graph; and JDSET, a curated suite of eleven datasets with varying expressivity, volume, and domain. JDEX preserves full schema expressivity, employs standard OWL reasoning to detect and correct inconsistencies and materialize implicit knowledge, applies schema modularization, and provides utilities for integration with mainstream machine learning libraries such as PyTorch and PyKEEN. We validated the completeness and portability of the datasets across several dimensions and preliminarily proved the utility of JEDIKG in experimental workflows combining data-driven methods with schema-driven reasoning.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2604.02846

Adaptive Local Frequency Filtering for Fourier-Encoded Implicit Neural Representations

Ligen Shi, Jun Qiu, Zengyu Pang, Yuhang Zheng, Lina Wu, Di He, Chang Liu

原文摘要

Implicit neural representations (INRs) commonly employ Fourier features to alleviate spectral bias and represent high-frequency signals. Fourier encodings, however, use the same frequency representation across spatial locations despite the spatially varying frequency content of natural signals. We propose Adaptive Frequency Implicit Neural Representation (AFINR), a spatially adaptive frequency-conditioning framework for Fourier encoded INRs. A sampling compatible Fourier dictionary first defines the explicit frequency support, and a learnable spatial control field then modulates the admitted Fourier components before decoding. The control field is parameterized in the discrete cosine transform (DCT) domain to provide a compact and continuously queryable spatial representation. AFINR can be combined with different coordinate decoders, including ReLU, SIREN, CAFE, and CAFE+. Experiments on Kodak and DIV2K show consistent average improvements across these decoder families. In particular, AFINR-CAFE+ improves CAFE+ by 3.95 dB on Kodak and 3.50 dB on DIV2K. Ablation studies characterize the effects of adaptive-field parameterization, DCT coefficient retention, and frequency-response parameters, while learned spatial responses show position-dependent use of the admitted Fourier components.

cs.CV · eess.IV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2507.16271

Beyond Isolated Dots: Benchmarking Structured Table Construction as Deep Knowledge Extraction

Tianyun Zhong, Guozhao Mo, Yanjiang Liu, Yihan Chen, Lingdi Kong, Xuanang Chen, Yaojie Lu, Hongyu Lin 等 12 位作者

原文摘要

Large language models (LLMs) are increasingly expected to extract and synthesize structured information from complex real-world documents, yet they typically produce unstructured, hard-to-verify paragraph-style outputs. We introduce AOE (Arranged and Organized Extraction), a bilingual benchmark that evaluates LLMs' ability to distill long-form, multi-document inputs (64k to 1.8M tokens) into structured tables. AOE comprises 12 tasks across four domains (academic, financial, legal, and medical), each grounded in genuine analytical needs, with schema guidance provided to isolate extraction quality from formatting variance. We evaluate 12 frontier LLMs (both open-weight and proprietary) under four generation settings of increasing autonomy: direct full-document input, RAG-based retrieval, offline document-browsing agent, and online web-search agent. Even the best-performing model achieves only 42.7% Cell F1, and retrieval-augmented approaches often degrade rather than improve performance, revealing that structured extraction from long contexts remains a fundamental challenge - an "Area of Effect" (AOE) that impacts all tested systems.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.26730

EpiLens: Lightweight RAG for Epidemiological Knowledge Acquisition

Vincenzo Perri, Ciro Cattuto, Daniela Paolotti

原文摘要

To prepare for future outbreaks, researchers need to know what studies have been done and what data they use. Mapping a large literature by hand is slow, while large language models alone can misstate or conflate sources. We present EpiLens, a lightweight, open-source retrieval-augmented generation package that applies a fixed retrieval template and output schema to every paper in a corpus and links outputs to source passages. We build a corpus of 2,297 papers from the sources of a multi-pathogen parameter study and evaluate EpiLens's paper-classification workflow against 214 manually labelled papers. Run locally with an open-weight model, so that licensed full texts never leave our hardware, the classifier is comparable to supervised baselines trained on the manual labels, and ahead of them on geography, despite the lack of task-specific training data. The study's early extraction sheets cite published sources for 327 estimates. We link each estimate to a cited document or to corpus studies included by a review. Then, we use the classifier's labels to compare the papers associated with different parameters and pathogens. EpiLens labels more papers linked to reproduction numbers than fatality risks as model-based (53% versus 15%, compared with 62% versus 24% in the manual labels). The gap is consistent with the frequent use of transmission models to estimate reproduction numbers and largely persists within pathogens.

cs.CL · cs.DL · physics.soc-ph

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.34130

Training and Inference Dynamics of PLDR-LLMs: Row-Map Collapse, Renormalization, and Predictive Reduction

Burc Gokden

原文摘要

This monograph develops a unified account of training and inference in Power Law Decoder Representation language models (PLDR-LLMs). Exact finite work identities decompose changes in the absolute energy of the row-centered learned map into parameter contributions, signed interactions, and numerical observation defects. Positive affine blocking retains restarts at the row-constant face, while the augmented AdamW state supplies the complete dynamical description. Predictive renormalization acts on the complete conditional training law for a single pass over distinct corpus target blocks, retaining optimizer memory, remaining data, schedule, and numerical policy. Autonomous reductions require closure; approximate reductions carry successor and emission errors. Finite-population covariance, matched physical clocks, matrix fluxes, and signed temporal energy connect row dynamics to model-wide observations. Absolute row collapse, relative row concentration, operator stabilization, and predictive accuracy are distinguished. Experiments reveal observer and optimizer dependence, reject the tested autonomous row-state candidates, and support finite conditional prediction and state-specific operator reduction. Independent single-pass families exhibit moving finite fluctuation regions without establishing a thermodynamic critical class. Conditional symmetry, head limits, covariance flows, and readout error budgets specify assumptions needed to transfer scaling laws to inference. The theory separates exact identities, conditional dynamical claims, and finite empirical findings, with proofs, selected formal checks, and compact numerical evidence.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05438

HLA-Net: A Physics-Guided Skeleton-Based Framework for Automatic Gravitational Arc Detection in Astronomical Images

Don S

原文摘要

Gravitational arcs produced by strong gravitational lensing provide a unique approach for investigating dark matter distribution, galaxy cluster mass reconstruction and the structure of the Universe. Automated detection remains challenging because gravitational arcs are rare, often faint and morphologically similar to elongated galaxies.In this paper, we propose \textbf{HLA-Net (Hybrid Lens Arc Network)}, an interpretable multi-stage framework for automatic gravitational arc detection that explicitly exploits both the geometric morphology and physical characteristics of gravitational lensing without requiring manually annotated training datasets.The proposed framework was evaluated on astronomical FITS images containing complex galaxy cluster structures. Starting from 169 initial arc candidates extracted from ordered skeleton representations, the multi-stage verification pipeline reduced the search space to 83 geometrically consistent candidates, while robust circle fitting successfully modelled 113 candidate arc structures. The results demonstrate that HLA-Net effectively suppresses false-positive detections while preserving physically reasonable lens candidates through an interpretable and modular verification strategy.

astro-ph.IM · astro-ph.GA · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04689

Uncertainty-Aware Prototype Learning for Open-Set Test-Time Adaptation

Jinwu Hu, Langyu Bian, Jian Sun, Dongjin Yang, Chao Shuai, Yufeng Wang, Kai Zhou, Bin Xiao 等 11 位作者

原文摘要

Open-set test-time adaptation (TTA) aims to adapt source-trained models to unlabeled test streams where covariate-shifted in-distribution (csID) samples and covariate-shifted out-of-distribution (csOOD) samples may coexist. Existing TTA methods are typically designed under a closed-set assumption and therefore lack explicit mechanisms for reliably distinguishing csID from csOOD samples. Consequently, csOOD samples may be mistakenly included in confidence-enhancing adaptation, producing harmful gradients that degrade known-class performance. To address this, we propose Uncertainty-Aware Prototype Learning for Open-Set Test-Time Adaptation (UAPA), a plug-and-play method for reliable open-set adaptation. Specifically, we first introduce Uncertainty-Driven ID/OOD Separation, which combines a classifier-prototype score with a mini-batch-normalized evidence-derived uncertainty score to distinguish csID from csOOD samples. We then propose a Dynamic Prototype Refinement strategy that periodically refines class-specific target prototypes using buffered csID features to progressively follow the estimated class directions. Lastly, we introduce Contrastive Prototype Entropy Adaptation, which applies entropy minimization to csID samples and entropy maximization to csOOD samples, while prototype-level contrastive learning aligns csID features with their corresponding target prototypes and reduces the maximum similarity between csOOD features and known-class prototypes. Empirically, UAPA outperforms the strongest baselines on the CIFAR benchmarks and Tiny-ImageNet-C, improving average OSCR by 2.08 and 1.28 percentage points, respectively.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.00800

A Discrete-Time Variational Objective for Degenerate Diffusion and Equivalence to Flow Matching

Rares Dolga, Harshad Dahake, David Barber

原文摘要

Diffusion models and more recently Flow models have widespread application. In this work we consider degenerate Diffusion models in which the per-step generator is deterministic. We construct a modified variational framework and show a formal equivalence between Flow models and Degenerate Diffusion models. For our discrete-time variational objective we show that the optimal degenerate generator recovers the data distribution in the limit of an infinite number of generator steps. Our work therefore provides a unified perspective, showing that discrete-time implementations of flow matching and the discrete-time Degenerate Diffusion model can be considered within the same simple variational framework, removing the need for the continuous-time machinery normally used to justify flow matching models.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04687

CardioVascBench:Prioritized Diagnosis Generation from Real-World Chinese Cardiovascular Records

Minghao Kong, Muyao Chen, Jianhao Wu, Yuqiang Zhang, Xiangbin Meng, Zirong Liu, Ting Cao, Kaida Ning 等 10 位作者

原文摘要

Identifying the primary diagnosis alone does not fully characterize a model's diagnosis-generation performance. We introduce CardioVascBench, a retrospective benchmark for prioritized diagnosis generation from real-world Chinese cardiovascular inpatient records. It contains 3,262 de-identified cases, with 2,174 for training and 1,088 for evaluation, linking clinical narratives and textual ECG reports to expert-verified, ordered discharge diagnoses standardized to ICD-10. An English translation of the evaluation set supports aligned cross-lingual comparison. Our evaluation protocol combines terminology normalization and rank-aware scoring to separately assess primary-diagnosis identification, reference-diagnosis coverage, and list precision. Evaluation across 36 systems shows that higher primary-diagnosis accuracy does not necessarily imply higher list precision against discharge references. We also provide CardioKG-Agent, a knowledge-enhanced baseline combining entity normalization, constrained graph retrieval, and guideline evidence. In a staged comparison of three baseline models, supervised fine-tuning plus the agent achieves a 73.5% higher mean composite score than fine-tuning alone, representing a system-level gain. These results measure retrospective agreement with recorded diagnoses; agreement between metric rankings and physician judgments remains to be validated. CardioVascBench supports research on diagnosis prioritization and knowledge-enhanced generation.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.04686

Designing AI-Mediated Communication in Teams

Wichinpong Park Sinchaisri, Zhiwei Wang

原文摘要

AI assistants increasingly participate in work that requires employees to exchange information and coordinate decisions. We study how a firm should design this communication when workers' interests conflict with each other's and the firm's. Two workers privately know local conditions and their preferred responses, while the assistant knows aggregate project conditions. The firm discloses project information before workers report and choose their own actions. Transparency improves adaptation but can undermine truthful preference reporting. When workers agree with the firm on the productive direction, coarsening project information under weak coordination can preserve useful preference reporting at a cost in forecast precision. Under strong coordination, the firm instead prefers full project disclosure and factual reports, because preference information induces costly accommodation of private objectives. Under weak coordination, a firm-optimal policy can leave workers worse off than direct exchange; requiring their acceptance can call for further coarsening. Releasing project context after reports can sustain factual communication that early release would prevent. With separate delivery decisions that cannot be revised jointly, endogenous forwarding weakly improves firm-preferred performance over unchanged forwarding and strictly improves it in some environments. Numerical comparisons show that full initial disclosure captures most gains in the aligned environments considered, while further design has greater value when workers can favor opposing directions. The results distinguish the credibility of employees' reports from their organizational value and show how disclosure timing affects both.

cs.GT · econ.TH

查看论文
arXiv ↗PDF ↗