跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+479新增论文
+361其中 AI 相关
+63已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 13:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 17:40 — 2026-11-16 17:40(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:2026-11-16 01:34最近发现新增版本:2026-11-16 13:44库内论文最新更新时间:2026-11-14 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。

23,827 已收录论文19,941 AI 相关6,921 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 23,827 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2611.13270

What drives the emergence of symbolic mechanisms in large language models?

Melody Zixuan Li, Taylor Webb

原文摘要

Recent work has identified a set of emergent symbolic mechanisms that support abstract reasoning in large language models, but it remains unclear what factors drive the emergence of these mechanisms. To address this question, we trained neural networks from scratch on abstract sequence tasks, varying both architectural and data distributional factors, and investigated the effects of these factors on the emergence of symbolic mechanisms. Using representational, attentional, and causal mediation analyses, we first confirmed that transformer-based language models trained from scratch on our task developed symbolic mechanisms. We then found that, across multiple axes of data diversity, greater diversity produced stronger symbolic signatures. Surprisingly, the same signatures emerged in modified transformer architectures and even multilayer perceptrons, indicating that architectural inductive biases are not necessary for the development of symbolic mechanisms. We also observed consistent patterns in an entity-attribute binding task. Together, these findings identify data diversity, not architecture, as the primary driver of emergent symbolic computation in neural networks.

cs.CL

新论文 · v1arXiv:2611.13268

Force-Closure Condition for Cooperative Multi-robot Pushing of Rectangular Objects

Duy Anh Nguyen, Trung Dung Ngo

原文摘要

In cooperative object manipulation, the placement of pushing contacts determines whether force closure can be achieved and agents can generate arbitrary forces and torques on the object correspondingly. This study derives a necessary and sufficient closed-form condition for the planar force closure of a rectangular object, a common object shape in everyday settings, under four frictionless pushing contacts. For a rectangle of length $b$ and width $a$, force closure holds if and only if $(l_1+l_3-b)(l_2+l_4-a)<0$, where $l_1,l_2,l_3,l_4$ are the four edge contact locations. This condition is independent of the object's center of mass and is used to verify contact configurations before contact force allocation. When the condition is not satisfied, the signs of the two factors indicate which opposing contact pair should be adjusted. The condition and adjustment rule are then integrated into a full-pose trajectory-tracking framework as a geometric feasibility layer to demonstrate their use in control. Static wrench feasibility tests validate the proposed condition, while narrow-passage floating-body simulations show that maintaining a force-closure configuration reduces the RMS tracking errors in $x$, $y$, and unwrapped yaw from $12.05$ m, $18.11$ m, and $535.96^\circ$ to $2.24$ m, $2.66$ m, and $2.69^\circ$, respectively.

cs.RO · eess.SY

新论文 · v1arXiv:2611.13262

Adaptive Residual Quantization for Memory-Efficient Temporal Action Segmentation

Gerard Donahue, Guven Gergerli, Ayush Gupta, Reza Ghoddoosian, Enna Sachdeva, Faizan Siddiqui

原文摘要

Temporal action segmentation (TAS) is commonly trained on large banks of pre-extracted frame features, but storing and replaying those features becomes a practical bottleneck for long-form video, especially in incremental TAS where past-task data must remain available to mitigate catastrophic forgetting. Recent TAS replay and condensation methods reduce this burden, but they rely on dense frame-wise annotations and allocate storage through fixed segment-level structures, limiting their flexibility for long procedural videos whose frame complexity varies substantially over time. We introduce Adaptive Residual-Quantized Variational AutoEncoder (ARQ-VAE), a compact and label-free memory representation for TAS features that learns a discrete residual quantization of frame-level video features and then adaptively truncates the residual chain on a per-frame basis, retaining only the residual prefix that best reconstructs each frame feature. This yields a practical compact feature memory that does not depend on frame-wise labels and can therefore support multiple TAS settings with the same stored representation, while a lightweight fine-tuning stage further improves reconstruction quality for the truncated codes that are actually retained. Across standard TAS benchmarks, ARQ-VAE achieves a substantially improved storage-performance trade-off over prior replay and condensation baselines. On Breakfast, our final representation reduces training-set storage from 28 GB for the original I3D feature bank to 10 MB while retaining strong downstream segmentation performance; with ASFormer, it achieves 71.5 Edit and 51.2 F1@50 in the supervised setting. We further show that the same label-free memory remains effective for incremental and unsupervised TAS. We position ARQ-VAE as a practical memory representation for TAS and a promising direction for broader dataset condensation applications.

cs.CV · cs.AI

新论文 · v1arXiv:2611.13259

Choosing Complexity: Cognitive Ability, Overconfidence, and Task Choice

David Gill, Zhongheng Qiao

原文摘要

Workers and organizations routinely choose between complex tasks that differ in their success-payment tradeoff. We study how cognitive ability and overconfidence shape this choice of task complexity, both theoretically and experimentally. Consistent with our model, we find that more cognitively able individuals choose more complex tasks. Conditional on cognitive ability, we find that more overconfident individuals also choose more complex tasks. In about 75% of the decisions, subjects pick their payoff-maximizing task, and higher cognitive ability is weakly associated with more efficient choices of task complexity. But errors are strikingly one-sided: those who fail to choose optimally pick tasks that are too complex. Our findings suggest that organizations should pair task menus and incentives for choosing more complex tasks with information and feedback that help workers assess their ability and probability of success. This preserves the benefits of self-selection while reducing costly overreach.

econ.TH · cs.GT · econ.GN

版本更新 · v2arXiv:2611.05664

Combining Relevant Expert Knowledge Using Mixtures of Feedback Fuzzy Cognitive Maps

Olaoluwa Adigun, Akash Kumar Panda, Bart Kosko

原文摘要

A neuro-symbolic system should combine only relevant answers from expert agents or other knowledge sources. Using only relevant experts for a given input query becomes ever more important for accuracy and scalability as the knowledge network grows and connects ever more knowledge sources. We extend the standard definition of relevance from the legal theory of evidence: An answer is relevant if and only if it is both probative and material for the matter at hand given the knowledge available. We apply this relevancy scheme to mixing the feedback fuzzy cognitive maps (FCMs) of real or artificial experts. The expert FCM directed causal graphs mix or combine into a common knowledge network. We compare the equilibrium limit-cycle predictions or answers of the experts to the answers of the mixture FCM and then estimate the probative status of answers by their difference or variation. A new Bayes-like theorem de-mixes the knowledge mixture into corresponding posterior-like FCMs that also allow relevancy-based comparisons. The result is a final set of relevancy mixing weights that produces a relevancy-mixed FCM knowledge network for the given query. So different queries produce different relevancy-mixed FCMs. We demonstrate this relevancy approach using generated synthetic FCMs from an actual 13-node expert FCM that models the causes and feedbacks of ischemic-stroke risk.

cs.AI · cs.IR · cs.SC

版本更新 · v2arXiv:2611.09794

Seeing What Execution Needs: Benchmarking Task-Conditioned Actionable Spatial Belief for Manipulation

Yina Jian, Mingkun Xu

原文摘要

When should a robot look at the cup, and when at the portafilter? A view that is informative for one task can be useless for another, even at the same workstation. We introduce Seeing What Execution Needs, a benchmark for task-conditioned actionable spatial belief in simulated tabletop manipulation. Its aligned three-domain track contains 1,080 frozen cases (360 each for coffee workstation, drawer/cabinet, and microwave/appliance). The primary coffee protocols -- closed-loop actionability and same-object functional out-of-distribution generalization -- produce over 115,000 evaluator episodes across evaluated methods, budgets, and inference repeats. Each case pairs candidate RGB views with a manipulation command, shared scripted skills, and hidden postconditions, directly measuring whether selected observations support execution. A metadata-assisted diagnostic reference pipeline maintains spatial-functional beliefs and ranks views by missing evidence. At primary budget settings, it reaches 98.8% closed-loop and 98.9% functional-OOD success; removing functional fields or command binding reduces functional-OOD success to 0.0% and 19.7%, respectively. Under a separate full-preview contract, seven vision-language models reach 26-43%. Replacing coverage metadata with frozen RGB-derived scores retains 98.5%/98.9% success; shuffling these scores reduces success to 15%/11%, supporting dependence on image content. Separately, the aligned three-domain evaluation at H=3 supports portability of the benchmark interface under frozen domain-specific schemas. These results suggest that spatial belief for manipulation should be evaluated by whether acquired evidence meets the current command's execution requirements.

cs.RO · cs.CV

新论文 · v1arXiv:2611.13258

Which Acoustic Features Survive Compression? Tracker-Estimated First-Formant Statistics for Codec-Robust Audio DeepfakeDetection

Yash Sukhdeve, Aaron Storey, Masudul H. Imtiaz

原文摘要

Audio deepfake detectors that work well on clean lab recordings often degrade after telephone or platform compression. This paper asks a specific question: which low-dimensional acoustic descriptors stay informative after codec degradation? We screen 36 utterance-level features(formants, PNCCs, LFCCs, prosody) on ASVspoof 2019 data and test on the official ASVspoof 2021 LA set across seven codec conditions. Of 33 statistically significant descriptors, only four show large practical separation (|r| >0.5, bootstrap 95% CIs), all first-formant (F1) measures, highly redundant (PC1: 79% variance). The payoff is stability: the 36-feature SVM degrades 14 pp under codec mismatch (9.5%-23.5% EER), while the four-feature RBF-SVM degrades only 5.9 pp (17.0%-22.9%). The F1 subset varies 3.4 pp across conditions versus 13.1 pp for the full set. F1 differences persist after controlling for speaker identity (p greater than 10^10, mixed-effects model). The results suggest that physically interpretable F1 statistics offer a compact, codec-stable diagnostic signal that may complement higher accuracy neural detectors.

cs.SD · cs.LG

新论文 · v1arXiv:2611.13254

Dependable Long-Horizon LLM Agents: A Trajectory-Centered Empirical Study of Where Errors Enter and Which Controls Reach Them

Shaohuang Wang, Jinghao Wen, Xulei Zhang, Xun Jiao

原文摘要

When an LLM agent fails part-way through a long task, the usual analysis records a symptom: a failure-mode label, or the agent and step judged responsible. It does not say where the error entered, which state carried it to the symptom, whether anything in the trajectory contradicted it, or which control could have caught it. We define an episode record that ties a candidate fault to its origin, propagation, detection, response and consequence, located by operational phase and state domain, and that names the control families whose observation and reach cover it. We turned the record into a written annotation protocol and applied it to 95 failed runs of six multi-agent systems from the public Who&When and MAD corpora, reading each trajectory in full. Faults enter early (median at 0.18 of the run), mostly as wrong decisions or fabrications over task state, and in 37 of 88 Who&When runs before the step the corpus' human labels mark as decisive. In 72% of failed runs the trajectory already contained evidence against the error before the failure; in 88% of those no agent acted on it. Something flagged a deviation in 31% of runs, but no response removed the deviated state. Independent judges reading the unused evidence, task contracts fixed at admission, and re-checking beliefs against the environment reach most episodes; restoring the agent's own state would have sufficed in 35 of 95 runs. A text scan of the raw corpus also shows that 45% of the hand-crafted Who&When failures ended with a provider content-filter crash after which the harness emitted a final answer no agent produced, a failure class that neither symptom taxonomies nor responsible-agent labels represent. Protocol, records and scripts are included.

cs.AI

新论文 · v1arXiv:2611.13252

Splitting for Stability: a Modified Reward Scheme for Transaction-Fee-Only Regimes

Eric Brigham, Baigang Chen, Nicholas Hopper

原文摘要

As Bitcoin's block subsidy declines over time, miner revenue will come to depend increasingly on transaction fees. In fee-dominated regimes, winner-take-all reward structures can create incentives for undercutting and fork-based mining strategies, leading to instability and reduced transaction throughput. To prevent this instability, we propose a reward-splitting mechanism in which the winning block producer receives an $α$-portion of the block reward, while the rest is distributed among other miners; this incentivizes mining on previous blocks with higher rewards, while preserving the incentive to produce blocks with high rewards. We evaluate the proposed reward structure through analysis and simulation. Our analysis derives a local profitability condition for one-step Function-Fork deviations, showing how the winner-side reward, loser-side subsidy, and honest hash power jointly determine whether undercutting is profitable. Simulations show parameter regions in which honest behavior dominates fork-based deviations. In the cases where forking becomes dominant, the learned strategy is the least aggressive variant studied. The analysis and simulations suggest that suitable reward-splitting parameters can reduce the honest participation needed to suppress aggressive forking strategies relative to the winner-take-all structure studied in prior work. Finally, we show that the modified reward scheme does not appear to worsen selfish mining incentives. Together, these results suggest that reward redistribution can mitigate fee-driven fork incentives without introducing stronger selfish mining incentives, providing a possible direction for incentive design in fee-era proof-of-work systems.

cs.CR · cs.GT

新论文 · v1arXiv:2611.13251

Curie's Jarvis: Autonomous Robotic Chemistry Experiments from Printed Protocols

Rumi Loghmani, Bozhang Song, Victor Alvarado, Aliyah Redding, Amir Barati Farimani

原文摘要

A person running a bench experiment works from a printed instruction sheet, tells identical containers apart by the labels written on them, and looks at the bench again before each step. Lab automation usually works the other way around: the procedure is written as a script, and containers stand at fixed positions or carry fiducial markers. We present Curie's Jarvis, a system that lets a robot arm carry out a chemistry experiment on a bench set up for people. It reads the steps from a photo of the printed sheet, finds containers on an ordinary bench with no fixed positions or markers, tells identical-looking containers apart by reading their labels in four camera views, locates its target again before every step, and sets how each step is carried out, including its speed, from what is being handled. On a Franka Panda arm, Curie's Jarvis completed 5 of 5 runs of one protocol from a children's chemistry kit and 4 of 5 runs of another, with no human intervention, and in 160 locates on printed and handwritten labels it identified every container correctly. This brings robots a step closer to doing bench chemistry the way people do.

cs.RO · cs.AI

新论文 · v1arXiv:2611.13250

Using Proof Dependencies to Manage Verification Projects

Lea Salome Brugger, Andrea Keusch, João Pereira, Peter Müller

原文摘要

Verification technology now scales to sizable projects, but techniques for managing such projects fall short. There are no effective ways to assess the progress made so far and to determine which verification tasks to perform next. A key issue is that the successful run of a verification tool provides little indication about what has actually been achieved. The guarantees provided depend on the specifications of the verified code as well as any unverified assumptions made in the proofs, e.g., about the behavior of unverified libraries. Manual inspection of specifications and assumptions to determine progress is error-prone and prohibitively expensive. In this paper, we present automated techniques to assess and guide verification projects. All of these techniques employ an automatic proof dependency analysis that computes, for each proof obligation in a project, the specifications, statements, and assumptions that are needed to prove it. We show that this analysis enables effective proof audits by determining all assumptions a proof depends on. We also use it to determine which statements in a program are constrained by the provided specifications, which indicates how strong a specification is. Based on these two insights, we propose a novel progress metric for verification projects and show how to use it to guide verification projects to maximize progress. We implement our approach in the symbolic execution backend of Viper and lift it to the Go verifier Gobra. Our evaluation on real-world benchmarks, including a verified Internet router, shows that the dependency analysis is sound and sufficiently precise, that our progress metric accurately reflects the state of a verification project over time, and that our guidance outperforms standard bottom-up and top-down verification strategies.

cs.SE

版本更新 · v2arXiv:2609.31235

Purin: A Biology-inspired Mechanism for Artificial Neural Networks

Zishu Liu, Chunbo Luo, Christos Grecos

原文摘要

Artificial neural networks (ANNs) usually represent neural transmission with fixed trainable weights during a training batch, which omits short-term changes in synaptic efficacy. In addition, the discrete time-step simulation requires additional temporal processing that many conventional ANN architectures do not use. To overcome these challenges, we propose Purin, a biology-inspired and ANN-compatible mechanism, that introduces synaptic efficacy modulation into conventional convolutional neural networks. Purin uses a time-interval-based abstraction for neural activities, which allows Purin to introduce short- and long-term synaptic efficacy changes without using discrete time-steps. Purin introduces a bounded factor to represent temporary synaptic efficacy changes, together with two weight matrices that represent input-side and output-side efficacy. The weight matrices are updated by backpropagation and interpreted as the long-term synaptic efficacy changes. Experimental results show that after removing the confounding factors in the AlexNet, VGG11, and GoogLeNet architectures, Purin improves the classification accuracies in all three models across the evaluated datasets.

cs.AI · cs.NE

新论文 · v1arXiv:2611.13246

ExpertCrowd-SWE: Measuring Frontier Coding Agents on Expert-Authored Engineering Tasks in Unfamiliar Codebases

Josip Vrdoljak, Akash Singh, Bas Steunebrink, Alex Yarotsky, John Lorenzo, Achille Nicoletti, Sam Pigott

原文摘要

ExpertCrowd-SWE (EC-SWE) is a benchmark of 100 expert-authored, multi-file software engineering tasks for evaluating autonomous coding agents in large, unfamiliar codebases. Each task is a change request written by a practising engineer against a pinned commit of a real repository, paired with a sealed reference solution and a task-specific grader whose weighted, mostly executable criteria award partial credit; must-pass blockers and pass/fail gates encode what a maintainer would refuse to merge. The tasks span 87 open-source projects and 11 languages. The median ticket is 148 words, while the median reference solution changes 471 lines. Every task image is calibrated before release so that the reference solution scores 1.0 and both the untouched repository and an inert change score 0; nearly half of the tasks also ship alternative, lazy and adversarial control patches that the grader must classify correctly. The final 100 tasks were selected for difficulty against current frontier models. We evaluate seven frontier models, five runs each (3,495 scored runs), in a single platform harness that gives each model its provider-native tool interface. Claude Opus 5.5 (67.3%) and GPT-6 Astra (63.7%) lead without a statistically significant gap, followed by Claude Fable 5.1 (46.5%), Gemini 3.8 Flash (40.0%), and a statistically indistinguishable group of Qwen 3.8 Max, DeepSeek V4.1 Flash and Grok 4.6 (32-34%). No task is fully solved by every model, and on 80 tasks no model earns full credit on all five runs. Scores span 35 points. Depending on the model, agents take a median of 33 to 166 steps per run, with little relation to score. We release 24 tasks with their environments, graders and results, and hold out 76 to limit contamination.

cs.AI · cs.SE

新论文 · v1arXiv:2611.13245

Rethinking Evaluation for Video Capsule Endoscopy: Validation Protocol, Source-Video Diversity, and Cross-Dataset Shift

Smriti Regmi, Debesh Jha

原文摘要

Automated video capsule endoscopy (VCE) classification remains challenging due to severe class imbalance, limited source-video diversity, and variations in image appearance across datasets. Although deep learning models have demonstrated promising performance on established benchmarks, their reliability under different validation protocols and external dataset shift remains insufficiently understood. In this work, we introduce DMSNet, a deformable adaptive multi-scale edge-guided attention network integrating adaptive multi-scale feature fusion, deformable lesion refinement, edge-guided attention, and sparse feature selection. We benchmark DMSNet against 18 representative convolutional, transformer-based, and pretrained vision architectures on Kvasir-Capsule under random frame-level and source-video-disjoint validation protocols. We further identify source-video overlap between the original training and test splits and evaluate model performance on both the complete test set and a source-video-disjoint subset. Under random frame-level validation, DMSNet achieves an MCC of 0.442 $\pm$ 0.020 on complete test set and 0.456 $\pm$ 0.037 on the source-video-disjoint subset. On the external CV2024 dataset, ConvNeXt-Tiny achieves the highest MCC of 0.207, while performance degrades substantially across architectures relative to in-domain evaluation. We further investigate source-video diversity using a per-class cap of 200 training frames. With the total training-set size held fixed, increasing the maximum source-video coverage from four to eight improves MCC for 17 of 19 evaluated architectures. Overall, these findings demonstrate that model rankings and classification performance depend substantially on evaluation protocol, training-source diversity, and cross-dataset shift, emphasizing the need for source-aware validation and rigorous external evaluation of VCE classification systems.

cs.CV

版本更新 · v3arXiv:2606.07537

From Architecture to Output: Testing the Structural Origins of Hallucination and the Amplifying Role of Data

Md. Rejaul Korim Sadi, Toufiqur Rahman Tasin, Golam Mostofa Naeem

原文摘要

Surveys of hallucination classify errors by how an output relates to its source, and often explain them by the model's structure: attention retrieves by association, the maximum-likelihood objective has no term for truth, and left-to-right decoding commits to early tokens. Data, on this account, makes these failures worse rather than causing them. The account is usually argued rather than tested. We test it with interventions that need only sampling access. Study 1 holds pretraining data, tokenizer and scale fixed and swaps attention for a state-space mixer, using five Pythia/Mamba pairs from 130M to 2.8B parameters and four further attention models, on 111 facts presented with a planted false or a planted true statement. Swapping the mixer leaves free-recall failure unchanged (both 2.8B models answer 3 of 200 SimpleQA questions), but it changes what happens to a defect in the input. From 410M upwards, every attention model repeats the planted falsehood more often than its matched state-space model (2.8B: 650 vs. 566 of 666 items, p = 2.5e-20), also on facts both models know, while the state-space models can still read planted facts they did not know. Study 2 replaces the first wrong fact in 111 erroneous answers from three instruction-tuned models. The correct fact cuts the share of answers with a downstream error from 92.5% to 48.1%, but a different wrong fact works as well (p = 0.38), and the models give the right answer in isolation on only 2 of 111 items. The structural account survives in a narrower form. The mixing component decides whether a defect in the context becomes an output error, commitment decides how an error spreads, and on long-tail questions the first error comes from missing knowledge, not from a suppressed truth.

cs.CL · cs.AI · cs.LG

版本更新 · v2arXiv:2605.21317

CRAFT: Conflict-Resolved Aggregation for Federated Training

Ziqi Wang, Qiang Liu, Nils Thuerey

原文摘要

The aggregation of conflicting client updates remains a fundamental bottleneck in federated learning (FL) under heterogeneous data distributions. Naive averaging can produce a global update that improves the global objective while conflicting with specific clients, causing degradation for those clients. In this work, we propose CRAFT (Conflict-Resolved Aggregation for Federated Training), a new aggregation framework that treats the global update as a geometric correction problem. We formulate aggregation as finding the update closest to a reference direction while satisfying conflict-free alignment constraints. We derive a closed-form expression for the constrained optimization problem, avoiding the computational overhead of iterative solvers. Furthermore, we use a layer-wise adaptation to address conflicts at varying feature granularities. We provide a theoretical analysis showing that CRAFT promotes a common-descent structure and mitigates conflicts through its projection geometry. Extensive experiments on heterogeneous benchmarks demonstrate that CRAFT improves the accuracy of the global model while reducing performance disparity across clients compared with state-of-the-art baselines. The source code for CRAFT is available at https://github.com/tum-pbs/CRAFT.

cs.LG

版本更新 · v2arXiv:2609.05423

Characterising divergence between heuristic and language-model ratings of mobile user interface quality

Md Rejaul Korim Sadi, Golam Mostofa Naeem, Toufiqur Rahman Tasin, Syed Mostofa Moosa, Mahmudul Hasan Emon, Mahmudur Rashid, Ferdus Ahmed

原文摘要

Automated assessment of mobile user interface quality is attractive because manual review does not scale, and large language models are increasingly proposed for the task. Whether their ratings correspond to those produced by established rule-based heuristics has not been characterised at scale. We construct a 15,000-screen corpus from the RICO dataset using six documented filters, score every screen with a literature-grounded heuristic scorer, and collect ratings from three open-weight language models across two input representations, yielding 270,000 ratings. We report linearly weighted Cohen's kappa with bootstrap confidence intervals, offset-corrected kappa, intraclass correlation, and Bland-Altman limits of agreement, together with a chance baseline for the tolerance-band agreement rule. Agreement between the two rating sources is consistently weak: raw kappa falls below 0.15 in seventeen of eighteen model-representation-dimension cells. However, fifteen of eighteen cells are statistically distinguishable from zero, and correcting for a constant offset raises five cells above 0.15, so the divergence is better described as a combination of systematic bias and weak covariation than as absence of relationship. Model ratings track structural properties of the interface, but substantially less strongly than the heuristic does, and more strongly from an untruncated structural element list than from a screenshot. We further show that dimensions elicited in a single generated response are correlated by construction, reaching rho = 0.97 in one condition, which constrains what such designs can measure. We report these results as a characterisation of divergence between two automated raters rather than as evidence that either is correct, and we set out the validation a stronger claim would require.

cs.HC · cs.CL · cs.SE

版本更新 · v3arXiv:2507.00275

Deep Double Q-learning

Prabhat Nagarajan, Martha White, Marlos C. Machado

原文摘要

Double Q-learning is a classical control algorithm that mitigates the maximization bias of Q-learning. To do so, it explicitly trains two independent action-value functions and uses them to decouple action-selection from action-evaluation when computing bootstrap targets. Double DQN adapts this decoupling to deep reinforcement learning (RL) but directly trains only a single action-value function and does not fully decouple its estimators. Consequently, the two estimators remain correlated, and overestimation persists. In this paper, we introduce Deep Double Q-learning (DDQL), a deep RL algorithm that explicitly trains two Q-functions through the Double Q-learning objective. DDQL stabilizes training through a combination of techniques, including lower replay ratios, longer target network update intervals, and shared layers. Across 57 Atari 2600 games, DDQL improves aggregate performance over Double DQN, outperforming it on 47 games while further reducing overestimation. We study key design choices of DDQL, including its network architecture, replay ratio, and minibatch sampling strategies.

cs.LG · cs.AI

新论文 · v1arXiv:2611.13241

FlowPlan: Reducing the Token Cost of Coding Agents with Abstraction-Guided Planning and Verification

Melika Sepidband, Jiho Shin, Song Wang, Hadi Hemmati

原文摘要

LLM-based coding agents such as Claude Code can resolve real-world repository issues, but their iterative interaction loop can be expensive. Existing approaches reduce this cost primarily by limiting, compressing, or selectively avoiding information and actions within the repair process. We investigate a complementary question: Can an agent reason about a repair at an abstract program level, rather than repeatedly operating over raw source code, to reduce both the exploration needed to identify a repair and the repeated checking needed to verify it afterward? We present FlowPlan, an abstraction-guided repair approach that structures localization, planning, and verification around per-function control-flow or data-flow graphs. The agent first localizes the candidate fault location on the program abstraction and expresses the intended repair as explicit graph deltas before modifying the concrete source. After the edit, FlowPlan reconstructs the same abstraction and compares the observed structural change with the planned one. Then, a verification checks the complete repair before termination. Across all six benchmark-model settings, FlowPlan does not significantly change resolution rate relative to the vanilla agent while reducing token consumption in every setting, significantly in five of six settings. With Claude Haiku 4.5, it uses only 0.46-0.47x the baseline tokens on SWE-bench Pro, 0.32-0.35x on SWE-bench Verified, and 0.68-0.74x on SecBench; with Sonnet 5, it uses 0.72-0.76x, 0.73-0.74x, and 0.92-0.94x, respectively. Overall, FlowPlan achieves the largest token reduction among the compared methods in three of the six settings and ties the strongest compared method in a fourth. Trajectory analysis shows that FlowPlan saves tokens by replacing much of the costly post-edit re-reading and testing with explicit verification and reducing per-call context.

cs.SE

版本更新 · v2arXiv:2601.16759

Curated endoscopic retrograde cholangiopancreatography images dataset

Alda João Andrade, Mónica Martins, André Ferreira, Tarcísio Araújo, Luís Lopes, Victor Alves

原文摘要

Endoscopic Retrograde Cholangiopancreatography (ERCP) is a key procedure in the diagnosis and treatment of biliary and pancreatic diseases. Artificial intelligence has been pointed as one solution to automatize diagnosis. However, public ERCP datasets are scarce, which limits the use of such approach. Therefore, this study aims to help fill this gap by providing a large and curated dataset. The collection is composed of 19.018 raw images and 19.317 processed from 1.602 patients. 5.519 images are labeled, which provides a ready to use dataset. All images were manually inspected and annotated by two gastroenterologist with more than 5 years of experience and reviewed by another gastroenterologist with more than 20 years of experience, all with more than 400 ERCP procedures annually. The utility and validity of the dataset is proven by a classification experiment. This collection aims to provide or contribute for a benchmark in automatic ERCP analysis and diagnosis of biliary and pancreatic diseases.

cs.CV · cs.AI

新论文 · v1arXiv:2611.13238

STAR: Semantic-Criticality Tiered Allocation of Radio Resources via Zero-Shot Learning

Albert Shaju, Christo Kurisummoottil Thomas, Mingzhe Chen

原文摘要

In remote inference, edge devices transmit high-resolution images over wireless links to a receiver, where an artificial intelligence (AI) model answers task-specific questions about these images to enable reliable decisions. These answers are often determined by a small set of task-causal pixels, such as those of text, whose corruption changes the answer, so these pixels must be delivered with high fidelity. Conventional transmission protects every pixel equally, so it either consumes many resource elements (REs) or corrupts these regions at low signal-to-noise ratio (SNR). To overcome these limitations, in this paper, a zero-shot, domain-agnostic framework, termed semantic-criticality tiered allocation of resources (STAR), is proposed. In particular, a per-pixel semantic-criticality indicator (SCI) is derived from the attention of a frozen vision-language model, so new tasks and domains are handled by changing only the prompt, without retraining. The resulting task causality-aware resource allocation problem over protection tiers is solved exactly by a threshold rule on the SCI, realized by a coded tier for the task-causal pixels and an uncoded, downsampled base layer for the full image. Simulations over a 5G New Radio link demonstrate that STAR attains a semantic accuracy of at least 0.98 for $E_s/N_0 \geq -4$ dB and, at comparable semantic reliability, reduces the REs of robust coded transmission by 59.5% and 91.5% on factory- and vehicle-monitoring datasets, respectively, the latter without any change to the models. Although a deep joint source-channel coding baseline uses fewer REs at comparable semantic accuracy, it must be retrained with labeled data for every new task or domain.

eess.SP · cs.AI · eess.IV

新论文 · v1arXiv:2611.13237

Understanding Computing Instructors' Perceptions of Student Sense of Belonging

Ritesh Kanchi, Teresa Luo, Sam Grunebaum, Alex Oesterling

原文摘要

Students' sense of belonging has been described as a feeling of community acceptance, respect, inclusion, and membership. In computing, student belonging is shaped by psychological, social, academic, and environmental factors, including their relationships with instructors. However, despite prior work emphasizing instructors' influence on student belonging, limited research has examined how computing instructors perceive, understand, and attempt to support belonging. Through nine semi-structured qualitative interviews with introductory computing instructors at large public universities in the United States, we investigated how instructors define, measure, and conceptualize belonging; what interventions they use to support student belonging; and what barriers limit the efficacy of these interventions. Our findings show that instructors defined belonging through value and identity representation, self-efficacy, and community; relied on surveys, observations, and student performance to measure belonging; saw belonging to be influenced by prior experience, major, student and institutional culture, and representation; implemented student-oriented interventions and designed courses around belonging; and identified multi-level challenges to supporting belonging. These results highlight opportunities to design belonging interventions that attend to both prior work and instructor conceptualizations, while also considering tensions in utilizing teaching assistants, balancing students' expectations, and adapting to broader societal trends affecting belonging.

cs.CY

版本更新 · v2arXiv:2611.06356

EEGDash Corpus: A Training-Ready Public Corpus for EEG Foundation Models

Kuber Shahi, Bruno Aristimunha, Arnaud Delorme

原文摘要

Electroencephalography (EEG) foundation models are pretrained on tens of thousands of hours. The largest clinical archives restrict redistribution, while public datasets use different formats and licences. Here, we rebuild the 77 redistributable datasets of the REVE pretraining corpus that reach its 200 Hz input (14,075 hours across 7,272 subjects) and release them as eegdash-corpus-v0, with raw-file access by name through EEGDash and a checksummed Zarr store on Hugging Face, converted with REVE's preprocessing recipe. Every dataset keeps its licence, and any subset of datasets can be selected by name. To test whether this public store pretrains REVE-Base, we train the model twice from scratch with REVE's trainer and score it on seven public OpenEEGBench tasks. First, under linear probing, the frozen encoder reaches 0.331 in chance-adjusted balanced accuracy, against 0.333 for the released model (untrained: 0.200), a difference smaller than the spread between our two pretraining seeds. Second, after fine-tuning, it reaches 0.273 against 0.325 published (0.301 in our rerun), and part of this gap comes from the scoring pipeline. A public, training-ready EEG corpus can therefore pretrain the frozen representations of a foundation model and provide a shared base that other groups can audit.

cs.LG

新论文 · v1arXiv:2611.13236

NCP: Verifier-Guided Optimization of Weight-Space Control Policies

Ekrem Aksoy

原文摘要

We present the Neural Control Plane (NCP), a closed-loop system that observes language-model execution, synthesizes candidate weight-space intervention rules, evaluates them, and maintains a versioned table of admitted policies. NCP separates a pretrained model's inference data plane from the control policy that selects temporary parameter interventions. W-ISA supplies transactional execution and parameter restoration; NCP supplies telemetry, candidate synthesis, admission criteria, priorities, and rule lifetime management. The optimization state consists of active rules and an archive of evaluated candidates, while base-model parameters are restored after each request. In a local SmolLM-135M-Instruct experiment, NCP generated three candidates from development telemetry and evaluated them on separate task examples and a 4,095-target WikiText-2 slice. One projection reduced validation token repetition from 0.4133 to 0.2191, with a perplexity change of -0.0574%. All candidates produced zero newly correct exact answers, so the configured admission gate archived all three and retained the original active policy. Fresh-process repetition and saved-table resumption reproduced the measured outcomes. NCP provides an executable framework for studying recursive self-improvement at the control-policy level through explicit synthesis, verification, and state transitions.

cs.AI

版本更新 · v2arXiv:2609.32797

Derivative-Informed Training of Neural Operators On-the-Fly via Sketched Tangent Consistency

Xinhan Yang, Lu Lu, Shancong Mou

原文摘要

Derivative-informed training improves neural operators by directly supervising their input-output sensitivities, which is crucial when neural operators are used as differentiable surrogates for inverse problems, PDE-constrained optimization, design, and control. However, existing methods rely on offline-generated derivative labels, making data generation slow, storage-intensive, and difficult to adapt across datasets, resolutions, or perturbation bases. We propose sketched tangent consistency loss (sTCL), an on-the-fly derivative-informed training objective that, for PDEs with a known and differentiable residual, enforces sensitivity consistency directly from the governing equation without offline tangent labels or neural-operator architecture changes. sTCL uses randomly sketched input perturbations to provide a lightweight derivative-level physics constraint during training. However, raw forward-sensitivity residual penalties can fail for stiff, ill-conditioned, indefinite, or coupled saddle-point tangent operators. To address this, we introduce lightweight operator-aware loss-conditioning mechanisms selected by a simple tangent-operator decision rule. Across Helmholtz, nonlinear diffusion-reaction, Burgers, Allen-Cahn, and Navier-Stokes, with the same neural-operator backbone for all methods, the PDE-specific sTCL losses achieve solution and Jacobian accuracy comparable to offline derivative-informed training (DIFNO) while eliminating the offline derivative-data generation and storage pipeline. These results show that on-the-fly derivative-informed training need not merely amortize offline tangent-solve cost into training; with appropriate sketching and loss design, sTCL provides an effective drop-in path to derivative-informed neural operators. Code is available at https://github.com/Mou-group-UMN/Derivative-informed-training-on-the-fly.

cs.LG

版本更新 · v2arXiv:2609.04698

LookThere! Sparse Vision by Reinforced Selection

Sreehari Rammohan, Yousef Yassin, Anthony Fuller, Junfeng Wen, Carl Vondrick, Evan Shelhamer

原文摘要

Vision transformers typically treat every image token as equally important, yet for most tasks in computer vision only a fraction are needed. Adaptive computation methods accelerate inference by choosing which tokens to process, but existing methods struggle at extreme sparsity and require heuristics that may not generalize like token diversity and attention scores. We address these limitations with LookThere, achieving a new pareto frontier in performance-compute trade-offs through an end-to-end reinforcement learning framework that jointly trains a shallow input selector and a deep representation extractor. The selector learns where to look and the extractor learns what to see, together saving computation by selecting only what is worth processing for a given task without relying on auxiliary signals. We show that LookThere only selects the task-specific input, excelling at sparse recognition in high-resolution settings (traffic signs, billiards), and maintaining accuracy with as little as 0.2% of the input. It generalizes across tasks and models, including global recognition (ImageNet classification), local recognition (ADE20K segmentation), zero-shot classification (by distillation), and regression (counting). Across all settings, LookThere surpasses state-of-the-art selection to provide a general and scalable framework for specialized and efficient adaptive computation.

cs.CV · cs.LG

新论文 · v1arXiv:2611.13233

Decisions by Discrimination: Differential Evidence for Medical Reasoning

Yunpeng Xiao, Yuzhang Xie, Junhao Huang, Carl Yang, Xiao Hu, Kai Shu

原文摘要

Large language models (LLMs) are increasingly studied for clinical decision support, and medical question answering provides a testbed for evaluating this capability. In particular, medical multiple-choice questions (MCQs) reflect a core challenge in clinical decision-making: plausible options often share overlapping evidence, while only a few decisive factors distinguish the correct option from incorrect ones. However, existing retrieval-based and reasoning-oriented methods mainly focus on supplying broadly relevant knowledge or eliciting reasoning paths, rather than identifying the compact differential evidence that separates confusing alternatives. In this work, we present a retrieval-grounded differential evidence framework for medical MCQs. Our method extracts option-specific pieces of differential evidence and organizes them into concise evidence prompts for answer selection. This design better aligns external knowledge with differential reasoning while reducing irrelevant context. Experiments show consistent accuracy gains across multiple datasets and target LLMs. Ablation studies further show that our framework outperforms both directly using retrieved evidence chunks and closed-source LLM-generated general hints, and that its improvements are not solely explained by answer-proximal guidance, but are consistent with differential evidence serving as a compact aid for reasoning over competing alternatives. Our findings also offer insights for medical reasoning and other decision-making settings with multiple possible choices.

cs.AI

新论文 · v1arXiv:2611.13232

W-ISA: Transactional Execution of Weight-Space Intervention Programs

Ekrem Aksoy

原文摘要

We present W-ISA, a software instruction set and transactional runtime for executing weight-space intervention programs on pretrained language models. Shape-checked instructions express parameter updates, projections, ablations, and rank-one transformations. The runtime applies these programs within request-scoped execution contexts and restores saved parameters after completion or interruption. Activation-based match-action rules connect measured model states to intervention selection. We evaluate restoration and replay on SmolLM-135M-Instruct and Qwen2.5-1.5B-Instruct, and compare materialized rank-one updates with equivalent PyTorch hooks on the latter. In 45 timed requests, both intervention implementations produce identical greedy sequences at 32, 128, and 512 tokens; their maximum prompt-logit difference is 0.000184. On the complete WikiText-2 raw test split, the combined SmolLM attention-head ablation and MLP projection changes perplexity from 22.2353 to 22.3188, a relative increase of 0.3754%. W-ISA separates intervention specification, execution, and measurement, making parameter-level experiments reproducible and composable.

cs.AI

新论文 · v1arXiv:2611.13231

Block-Sparse Gauss-Newton Optimization of Finite Basis Physics-Informed Neural Networks: Sparse Automatic Differentiation Approach

Denis Korolev, Adrian Hill, Jeeeun Lee

原文摘要

In this work, we develop an efficient Gauss-Newton optimization approach for finite basis physics-informed neural networks (FBPINNs). The key ingredient is the overlapping domain decomposition architecture of FBPINNs, which localizes the influence of each subnetwork and induces block sparsity in both the residual Jacobian and the corresponding Gauss-Newton matrix. We characterize this structure and exploit it through sparse automatic differentiation, using graph coloring to partition structurally orthogonal Jacobian columns or rows. This reduces differentiation costs and memory requirements while preserving all structurally nonzero derivative information. The resulting compressed Jacobian representations allow us to assemble the Gauss-Newton system directly in block-sparse form, enabling the use of sparse direct solvers and preconditioned iterative methods. In this way, the otherwise expensive second-order optimization problem is reduced to scalable sparse linear algebra. We demonstrate the approach on multiscale PDEs, where accurate approximation requires rich neural network parametrizations and large numbers of collocation points. Numerical experiments show that our block-sparse Gauss-Newton method attains high accuracy and substantially accelerates optimization relative to first-order baselines while remaining computationally tractable for large problem sizes.

math.NA · cs.LG

新论文 · v1arXiv:2611.13230

Dynamic investment and coordination in teams: Theory and experimental evidence

David Gill, Victoria Prowse, J. Lucas Reddinger

原文摘要

Teamwork requires more than the general skills that team members bring. In successful teams, members invest in team-specific skill or capital that accumulates within the team and raises the return to coordinated production. We provide the first systematic analysis of dynamic investment in such team skill. Adopting a dynamic game approach, we develop a novel theoretical framework where investment in team skill creates persistent benefits but is risky because the benefits depend on successful team coordination. We then take this framework to the laboratory to study empirically the factors that influence dynamic investment in team skill. We find underinvestment compared to the efficient benchmark. However, investment responds strongly to incentives, in line with specific theory-predicted patterns. Pre-registered traits (theory of mind and propensity to coordinate) predict investment and team-level efficiency. We conclude that careful design of team incentives and selection of team members can facilitate the development of team skill.

econ.GN · cs.GT