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
+64已有论文修订
+95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 21:56各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 01:02 — 2026-11-17 01:02(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 21:56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6,922 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 17,708 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:2611.05876

MIGONet: a multiple-input graph neural operator with solver-free discrete manufactured-solution training

Muhammad Hasnain, N. K. Anand, Arun Srinivasa

原文摘要

Surrogate modeling of transport requires operators that capture the combined influence of spatially distributed sources and Dirichlet and Neumann boundary conditions, together with training datasets that can be generated at low computational cost. This work presents MIGONet, a multiple-input graph neural operator, and a discrete method of manufactured solutions (MMS) that trains it without solving a partial differential equation, using steady heat conduction as the model problem. In the discrete MMS procedure, temperature fields are prescribed a priori, and the source terms and Dirichlet or Neumann boundary data are evaluated with the same discrete operators as the reference finite-difference method (FDM), so every training sample satisfies the discrete governing equations by construction. Because the boundary data are derived from each field, a Dirichlet or Neumann condition can be assigned to every boundary segment of every sample, and the boundary specification becomes an operator input. MIGONet supplies representations of the complete source field and boundary data to every node before local message passing. On the rectangular domain, it is compared with a version without the complete-source encoder (MIGONet-local) and with the multiple-input operator network MIONet, using the same training data. MIGONet achieves mean relative temperature errors of 10.31% and 10.64% for curved-wire and Gaussian-spot heating, compared with 45.97% and 48.34% for MIONet and 72.25% and 67.82% for MIGONet-local. For 10,000 samples, discrete MMS reduces data-generation time from 486.65 s to 3.15 s relative to matched iterative FDM labeling. Separately trained MIGONet models are also evaluated on L-shaped, disc-shaped, and ring-shaped domains.

cs.LG

版本更新 · v2arXiv:2503.22771

Unraveling Groundwater Stress: A Model Generalizable Across Space and Time Reveals Co-Declining Water Tables and Recharge Across Bangladesh

Saleh Sakib Ahmed, Rashed Uz Zzaman, Saifur Rahman Jony, Faizur Rahman Himel, Afroza Sharmin, A. H. M. Khalequr Rahman, M. Sohel Rahman, Sara Nowreen

原文摘要

Is Bangladesh replenishing the groundwater it depends on? Answering this question remains difficult in Bangladesh and worldwide because sparse in-situ measurements limit observational capabilities, while existing machine-learning approaches struggle to generalize across time and space. To address this bottleneck, we develop a Teacher-Student framework in which a Teacher accurately learns from sparse annual in-situ minimum (R2 = 0.86) and maximum (R2 = 0.96) depth observations to generate dense spatial patterns, and a Student transfers these patterns from time-varying 25-km GLDAS groundwater storage to high-resolution (2-km) depth maps using location-specific features. The Student achieves R2 = 0.93 over 2003-2022 and generalizes across unseen years (Leave-One-Year-Out R2 = 0.93) and locations (Leave-One-District-Out R2 = 0.70), enabling reconstruction without contemporary in-situ measurements. The reconstruction reveals widespread water-table deepening and a national decline in groundwater recharge of 1.10 mm/yr (p < 0.001). Autocorrelation-corrected analysis identifies statistically significant recharge declines across 55.6% of Bangladesh, compared with significant increases across only 4.9%. This imbalance suggests that pumping-induced recharge enhancement, as proposed by the Bengal Water Machine hypothesis, remains localized rather than widespread across Bangladesh. Together, these findings reveal widespread weakening of groundwater replenishment and provide a scalable framework for monitoring groundwater dynamics in data-sparse aquifers globally.

cs.LG · cs.AI

新论文 · v1arXiv:2611.05874

Feature Puzzles: Single-Image Supervision for Multi-View 3D-Aware Segmentation

Jiahao Ma, Qiang Zhang, Miaomiao Liu, David Ahmedt-Aristizabal, Chuong Nguyen

原文摘要

Humans can easily recognize the same objects across different viewpoints of a 3D scene, whereas teaching models such multi-view-consistent perception typically requires videos or calibrated multi-view captures, which are considerably more expensive and less diverse than large-scale monocular data.~In this paper, we introduce Feature Puzzles, a novel framework for learning multi-view-consistent segmentation using only single-image semantic segmentation supervision. Specifically, we propose a simple yet effective pipeline that constructs multi-view-consistent segmentation pseudo-labels through image cropping and geometric transformations. We further introduce a lightweight, plug-and-play network that leverages the multi-view-consistent image features learned by existing pretrained 3D foundation models and the generated pseudo-labels to perform multi-view-consistent segmentation. Importantly, our flexible framework supports various types of prompts provided from one or multiple views and can be readily extended to open-vocabulary 3D segmentation. Under this single-image supervision, our feed-forward model achieves the best mIoU on NVOS, remains competitive on SPIn-NeRF and ScanNet++ against baselines using per-scene optimization or in-domain multi-view training, and demonstrates zero-shot transfer to open-vocabulary 3D segmentation. Visual comparisons are available on our project page: https://featurepuzzles.github.io/

cs.CV

新论文 · v1arXiv:2611.05873

Can LLM Agents Learn to Test? Maintaining Scoped Experience as Testing Evidence for Mobile GUI Testing

Zimu Liu, Xiaoxi Guo, Xiaolu Tang, Liang Yu

原文摘要

Repeated mobile GUI tests can reuse routes, locators, and recovery strategies from earlier executions. However, a route that worked in one workflow or app version may be irrelevant or misleading in another. We study how an LLM-based tester can retain useful experience while withholding entries contradicted by current observations. We present a maintenance contract for AdaptiTest in which reusable experience has an explicit applicability scope, trace provenance, and a lifecycle for confirmation, revalidation, and withdrawal. The contract reserves persistence for a Reflector role and treats recalled experience as advice. The archived implementation does not establish end-to-end enforcement of every specified mechanism. The design changes retrieved context, not model weights. The evaluation uses read-only Android workflows and archived internal comparisons. A six-task, three-repeat ready subset reports 18/18 completed runs with memory versus 3/18 without it, but a grounded single-agent control also solves the earlier hard-task slice. A separate cross-session probe is excluded from efficacy conclusions because of confounded route schedules and unvalidated state labels. We examine 13 selected real-update hazard records across nine subjects, distinguishing stale-locator observations from policy-based withholding and offline retrieval diagnostics. The latter do not measure live-device failures or actions saved. These events are UI changes, not confirmed regression bugs. The evidence supports a bounded design and case study; it does not establish general efficacy, superiority over independent GUI-agent systems, or unrestricted exploration.

cs.SE

新论文 · v1arXiv:2611.05871

The Invocation Bottleneck in LLM-Based Lossless Compression: What Can Be Removed and What Must Be Traded

Zhe Yan, Yihao Liu, Antonio Boffa, Huanchen Zhang

原文摘要

Large language models (LLMs) compress text far better than classical compressors, but LLM-based compressors are slow, particularly during decompression. We argue that their decoding time has two fundamentally different sources. Execution redundancy, such as per-token host transfers, CPU-side coding, and token-by-token encoding, is work that the coded output does not require and can be removed without changing a single output bit. Sequential dependency, one model call per decoded token, is inherent to lossless decoding and cannot be removed by better execution, only traded for more calls or for more bits. We remove execution redundancy with a GPU-resident pipeline whose block-parallel encoding is made lossless in half precision by batch-invariant kernels, speeding up arithmetic coding by up to 5.8x in encoding and 3.0x in decoding without changing its compression rate. We then study the two ways of trading sequential dependency, speculative dual-model coding (SDMC) and multi-token single-model coding (MSMC), characterize the compression cost of predicting several tokens from a shared prefix, and identify the workloads in which fewer model calls are worth that cost.

cs.IT · cs.DB

版本更新 · v2arXiv:2610.33979

A spinal-inspired spiking neural network for continuous finger-joint kinematics estimation from high-density surface EMG

Cristian David Guerrero-Mendez, Leonardo Abdala Elias

原文摘要

Decoding simultaneous and proportional finger kinematics from high-density surface electromyography (HD sEMG) remains challenging. Although data-driven methods have shown promising performance for finger movement decoding, their limited physiological interpretability remains a relevant limitation. This study proposes and evaluates a spiking neural network (SNN) that incorporates spinal-inspired structures and mechanisms to predict multi-joint finger kinematics from HD sEMG signals. The spinal-inspired SNN includes a spike-encoding computational model with input-noise variability, a phenomenological representation of Henneman's size principle, and excitation/inhibition (E/I) balance. HD sEMG and kinematic data were collected from 23 healthy participants performing grasping tasks under different elbow and wrist postures. Performance was assessed using six prediction metrics and compared against six baseline machine learning and deep learning methods. The proposed method showed a large and significant ($p<0.05$, rank-biserial correlation $r_{rb}>0.7$) improvement over all baseline methods across all accuracy metrics. Performance improved significantly with increasing spike encoder firing rates up to approximately 83 Hz, and with more regular input spike trains compared with a Poisson-like encoder. In contrast, the E/I balance did not significantly affect the decoding performance of the algorithm. The firing rate and inter-spike interval statistics of the SNN differed significantly across motor tasks. These results demonstrate that incorporating neurophysiological principles into SNNs improves prediction performance while providing additional physiological interpretability for simultaneous and proportional finger-kinematics decoding. This approach represents a promising step toward physiology-informed neural networks, with potential applications in motor rehabilitation.

cs.HC

新论文 · v1arXiv:2611.05869

On Convergence of Gradient Temporal-Difference Learning with Regularized Corrections and Eligibility Traces

Jingyi Jin, Martha White, Hao Wang

原文摘要

Temporal-difference (TD) learning underlies many prediction and control algorithms, but can diverge when combined with off-policy learning, bootstrapping, and function approximation. TD with Regularized Corrections (TDRC) is theoretically sound and practically simple, but existing convergence theory covers only the one-step case under i.i.d. sampling, while the Huber Bellman-error formulation has not been extended to TDRC or eligibility traces. In this work, we establish convergence of constrained TDRC($λ$) with diminishing stepsizes and non-i.i.d. off-policy data, for state-dependent and history-dependent $λ$-parameters. We also propose TDRC($λ$)-Huber, which preserves the TDRC($λ$) fixed point while reducing sensitivity to large Bellman errors. For both algorithms, we apply an ODE-based weak-convergence method from stochastic approximation theory. For the nonlinear mean dynamics of TDRC($λ$)-Huber, we give an integral small-gain condition that guarantees uniqueness and global asymptotic stability of the target equilibrium. We then establish convergence of the constrained algorithm, derive computable sufficient conditions for convergence, and identify a regularization-based convergence mechanism shared by linear TDRC($λ$) and TDRC($λ$)-Huber. When the mean TD matrix is positive stable, both constrained algorithms converge under sufficiently strong regularization without requiring positive definiteness.

cs.LG · math.OC

版本更新 · v3arXiv:2610.33767

Local Entropy Fluctuations for Black-Box LLM-Generated Text Detection

Xinpeng Wang, Bruce Rushing, Zhizhen Chen, Zhe Zeng

原文摘要

Zero-shot detection of machine-generated text is vital for mitigating the risks of large language models (LLMs) misuse. While the state-of-the-art dual-model detectors and resampling-based detectors outperform single-model statistical detectors on unprompted continuations, they suffer a catastrophic breakdown on instruction-conditioned text in the black-box setting, where the source model is unknown. We analyze this failure and trace it to poor prompt conditioning for resampling-based methods and diminished cross-model discrepancy for dual-model detectors. Motivated by recent studies that human writing maintains a steady, uniform information flow, whereas machine-generated text exhibits sharp, localized entropy fluctuations, we propose a new metric, the Relative Peak Prominence Rate (RelPPR) to capture this structural contrast along the entropy trajectory and further leverage it as a signal for LLM-generated text detection. Extensive evaluations across diverse model families and datasets demonstrate that RelPPR achieves state-of-the-art black-box detection performance and remains the most reliable detector under various practical situations. Our code is available at https://github.com/brushing-git/entropy-llm-detector.

cs.AI

新论文 · v1arXiv:2611.05866

Auditable Unlearning for LLMs

Piyush Tiwary, Anushka Srivastava, Prathosh A. P

原文摘要

Machine unlearning aims to remove a user's data from a trained model after a deletion request. Existing methods are majorly evaluated on three axes - how well they forget, how much capability they retain, and how robust they are to membership inference attacks, but not on whether the provider can offer the user any evidence that the deletion occurred. To fill this gap, we introduce auditability as a fourth axis, defined as the separation between requested (forget set) and retained (retain set) data under a statistic the provider computes. We show that across eleven unlearning methods on TOFU, MUSE and RWKU no method satisfies all four axes, with different methods falling short on different axes. To address this, we propose a two stage method that can be used on top of any unlearning method, in the the first stage we propose ${GapWiden}$ which uses a hinge loss to increase the difference between audit statistics of forget set and retain set. In the second stage we propose ${GapVeil}$, an inference time rejection-sampler which uses the base model as the drafter and re-samples based on the audit statistics of the drafted response. We observe that using our method, auditability and leakage reach oracle parity for every unlearning method, and forget performance converges to the oracle; retain performance improves for nine of eleven methods but remains short of parity. Our results show that evidence of deletion or auditability can be constructed by design, and that treating it as an explicit requirement changes the viability of existing unlearning methods.

cs.AI

版本更新 · v3arXiv:2609.09742

Breaking Fault Lines: Unifying TEE-Assisted BFT Consensus in Partially Trusted Worlds

Xiaoqing Wen, Tong Liu, Jianyu Niu, Jialin Li, Cong Wang, Yinqian Zhang, Chen Feng

原文摘要

This paper revisits TEE-assisted BFT under a universal partial-TEE model, where an arbitrary subset of replicas execute inside TEEs while the remaining replicas operate without hardware trust guarantees. We show that heterogeneous trust changes the structure of quorum formation and fault tolerance. In particular, we derive a tight resilience bound f < max {n/3, m/2}, where n is the total number of replicas and m is the number of TEE-enabled replicas. The result reveals a sharp threshold phenomenon: TEEs improve fault tolerance only once they exceed two-thirds of the deployment. Guided by this characterization, we introduce two protocol principles: (1) a dual-quorum construction that safely combines TEE-only and mixed quorums, and (2) a TEE-leader fast path that leverages hardware-enforced non-equivocation to reduce both consensus and view-change latency. We realize these ideas in Raftel, which is, to our knowledge, the first HotStuff-style BFT protocol designed explicitly for arbitrary partial-TEE deployments, and in chained-Raftel, a pipelined variant that further accelerates mixed-trust execution. We implement both protocols atop Intel SGX and evaluate them in LAN and WAN environments. Our results show that Raftel achieves up to 625 TPS with sub-670 ms latency in WAN settings, outperforming HotStuff by up to 308 TPS in throughput while approaching the performance of fully TEE-assisted protocols.

cs.DC

新论文 · v1arXiv:2611.05862

CARTBench: Rubric-Based Evaluation of Shopping Advice for Complex and Ambiguous Requests with Timelines

Yuqin Dai, Zhanwei Zhang, Honghui Yang, Zhouheng Yao, Yueqi Zhang, Jingyu He, Chaoyang Shi, Fanding Wei 等 12 位作者

原文摘要

Large language model (LLM) shopping assistants now recommend products in multi-turn conversations. However, reliable evaluation faces Data scarcity and Difficulty Standardizing Criteria. To address these obstacles, we introduce CARTBench for CART (Complex and Ambiguous Requests with Timelines). For Data scarcity, we curate cases from real commercial shopping needs across 17 retail domains, pairing timestamped dialogue with 1,603 product records. For Difficulty Standardizing Criteria, we develop case-specific rubrics guided by Ideal Response Principles, distilled from excellent replies manually selected from successfully completed orders. These principles also guide Principle-Guided CART Prompting, our structured recommendation strategy. The experimental benchmark contains 1,328 expert-annotated criteria across Core, Excellence, and Safety. To answer the CART question, we evaluate 7 flagship commercial API models, including GPT-6.1-Sol and Claude-Opus-5, and 35B+ parameters open-weight models. In the first full-suite evaluation under the frozen rubrics, 3 of 10 models exceed 90% on Core, while none exceeds 45% on Excellence. Therefore, we identify an understanding-to-execution gap between required behavior and high-quality purchase advice. To examine these limitations, we diagnose shared failures in product evidence and unresolved needs, linked to changing requirements and decisive unknowns. Code and data are available at https://github.com/Da1yuqin/CARTBench.

cs.CL

新论文 · v1arXiv:2611.05861

A Complete Characterization of $q$-Ary $2$-Designs in Doubly-Extended Reed-Solomon Codes

Xinghao Wu, Junling Zhou

原文摘要

Let $\mathcal{C}_k$ be the doubly-extended Reed--Solomon code with parameters $[q+1, k, q-k+2]_q$. We give a complete characterization of when its codewords of a fixed weight form $q$-ary 2-designs. The main ingredient is an exact criterion showing that the number of $r$-subsets of $\mathbb{F}_q^*$ with a prescribed product is independent of that product if and only if $\gcd(r, q-1)=1$. Applying this criterion to the minimum-weight codewords of $\mathcal{C}_k$, we prove that they form a $q$-ary 2-design if and only if $\gcd(k-1, q-1)=1$. We further establish a propagation result for MDS codes showing that the $q$-ary 2-design property at minimum weight implies the same property at every nonzero weight. Consequently, $\mathcal{C}_k$ holds $q$-ary 2-designs at all nonzero weights if and only if $\gcd(k-1, q-1)=1$.

math.CO · cs.IT

新论文 · v1arXiv:2611.05859

Generative AI for urban planning: synthesizing land-use maps with satellite imagery via DualControlNet

Qingqi Song, Yuzhou Chen, Lingqian Hu, Shenhao Wang

原文摘要

Various land-use models characterize land-use patterns and facilitate scenario planning. However, existing models are largely predictive, forecasting transitions based on numeric data without synthesizing new land-use maps from simple text prompts. Meanwhile, generative AI in urban systems remains unimodal, weakly controllable, and evaluated mostly by generic image quality rather than domain-specific metrics. To address these gaps, we introduce DualControlNet, a generative land-use model that jointly synthesizes high-resolution land-use maps and satellite imagery, addressing multimodality, controllability, and verification challenges. Trained on over 40,000 paired tiles from Orlando and Chicago, DualControlNet is evaluated using land-use, spatial consistency, and image quality metrics. Relative to unimodal baselines, DualControlNet improves land-use diversity consistency by 62.8% and building coverage ratio consistency by 16.3%, more than doubles cross-modal spatial consistency, and triples visual quality. Scenario-based experiments demonstrate that DualControlNet supports sustainable development through multidimensional controls, increasing density and diversity, and responding to text prompts like "high-density development." Overall, this work advances land-use modeling via a multimodal, controllable, and verifiable generative framework, lowering technical barriers and enabling intuitive exploration of urban futures.

cs.CV · cs.AI

版本更新 · v2arXiv:2609.35456

AutoBCI: Forecast-Guided Agentic Neural Architecture Discovery for EEG-Based Brain-Computer Interfaces

Muyun Jiang, Yi Ding, Wei Zhang, Jinbo Chen, Chenyu Liu, Zhenjie Yang, Yuxin Li, Jingyuan Chen 等 12 位作者

原文摘要

EEG-based brain-computer interfaces support a broad range of applications, yet designing decoding architectures that perform well across diverse tasks remains challenging. We introduce AutoBCI, an agentic framework in which a Designer Agent and a Forecaster Agent support the discovery and selection of EEG decoding architectures across tasks. The Designer Agent performs Pool-Guided Architecture Discovery (PGAD), generating and refining architectures through training and validation across multiple EEG tasks, such as emotion recognition, motor imagery, and sleep staging. The Forecaster Agent performs Performance Estimation from Early Knowledge (PEEK), using architecture code, the training protocol, and early learning curves to predict full-budget validation performance and select promising candidates for continued training. Across 14 EEG datasets spanning motor imagery, emotion recognition, and sleep staging, we evaluate AutoBCI with six LLMs, including Opus 5.5 and GPT 5.6 Sol, and compare the architectures selected by the search procedure against ten baselines: six conventional EEG models and four foundation models. The architecture discovered by AutoBCI with Claude Opus 5.5 achieves 64.16% average test balanced accuracy (bAcc), compared with 63.87% for REVE, the strongest baseline on this metric. Using ten observed epochs, PEEK reduces mean absolute error in predicting average validation bAcc from 2.20 to 1.36 percentage points, a 38.1% reduction relative to the best-observed-score baseline. Code is available at https://github.com/Jiang-Muyun/AutoBCI

cs.AI

新论文 · v1arXiv:2611.05857

Thick Alignment: A Social Framework for Values and AI Systems

Alondra Nelson, Sola Kim

原文摘要

Computer science research on the "alignment" of artificial intelligence (AI) systems treats human values as content to be specified and optimized. Decades of social science scholarship describe values differently, as enacted in ordinary practice, interpreted in social context, and contested across plural orders of evaluation and worth. We argue that the dominant alignment techniques, which we call "thin alignment," convert situated moral or value judgments into one or a few metrics via devices of commensuration such as preference labeling, reward modeling, and consumer ratings. Drawing on philosophical and anthropological accounts of thickness, "thick alignment" instead examines how values take shape, inform the development of AI systems, and become subject to contestation over whose interests they serve. We describe two forms of misalignment in seemingly aligned algorithmic systems that highlight thin alignment: "Halcyon misalignment," which presumes a prior, just equilibrium of technology and values from which a system has departed, and "Mirrored misalignment," which names the risks and harms produced by systems that are aligned in a thin sense yet accurately reproduce an unequal social order. A thick account registers such systems as misaligned. We then trace how researchers have taken up and adapted the concept of thick alignment since it was first proposed in 2023, using these adaptations to refine the concept, and to distill three of its pillars: (1) contextual description that both reflects and constitutes values; (2) interrogation of values across the life cycle of a system; and (3) shared, accountable decision-making through which affected publics help determine which values guide the system. We close by considering implications for AI research and policy.

cs.CY

版本更新 · v2arXiv:2604.27955

Reinforcement Learning in GUI Agents: A Survey Toward Digital Inhabitants

Junan Hu, Jian Liu, Jingxiang Lai, Jiarui Hu, Yiwei Sheng, Shuang Chen, Jian Li, Dazhao Du 等 9 位作者

原文摘要

Graphical User Interface (GUI) agents have emerged as a promising paradigm for intelligent systems that perceive and interact with graphical interfaces visually. Yet supervised fine-tuning alone cannot handle long-horizon credit assignment, distribution shifts, and safe exploration in irreversible environments, making Reinforcement Learning (RL) a central methodology for advancing automation. In this work, we present the first comprehensive overview of the intersection between RL and GUI agents, and examine how this research direction may evolve toward digital inhabitants. We propose a principled taxonomy that organizes existing methods into Offline RL, Online RL, and Hybrid Strategies, and complement it with analyses of reward engineering, data efficiency, and key technical innovations. Our analysis reveals several emerging trends: the tension between reliability and scalability is motivating the adoption of composite, multi-tier reward architectures; GUI I/O latency bottlenecks are accelerating the shift toward world-model-based training, which can yield substantial performance gains; and the spontaneous emergence of System-2-style deliberation suggests that explicit reasoning supervision may not be necessary when sufficiently rich reward signals are available. We distill these findings into a roadmap covering process rewards, continual RL, cognitive architectures, and safe deployment, aiming to guide the next generation of robust GUI automation and its agent-native infrastructure.

cs.AI · cs.CV

新论文 · v1arXiv:2611.05851

Risk Control Certifies Rates, Not Magnitudes: An Audit of Selective Fetal Biometry

Zhengshuai Yang, Linna Jiang, Changyun Li, Guihu Zhao

原文摘要

Prenatal ultrasound biometry must return a head circumference (HC) and refuse when the image cannot support one. Selective prediction trades coverage against error, but its finite-sample guarantees bound the rate of gross errors, not their magnitude. We audit a tool-grounded biometry pipeline on two separately pre-registered four-way splits of the 999 labelled HC18 images, retraining the segmenter three times on each. Calibrating the contour-completeness threshold by exact Clopper-Pearson risk control returns a certificate indistinguishable from a hand-set floor, yet the pipeline still emits a 271.3 mm error: a small, geometrically complete ring fitted to an image whose true HC is 324.6 mm. The accepted candidate scores 0.94 completeness, so the score cannot see the failure, and one outlier among $\approx 150$ answers leaves the certified risk bound ($α= 0.10$) intact. A second, untouched split reproduces the mechanism on a different image (233.3 mm). Constraining the admissibility region---the anatomical range in which the measurand is defined---removes the family instead: raising the lower bound from 50 to 55 mm costs 0.4 coverage points and cuts the worst-case error on both splits to 11.4 and 11.1 mm, whereas suppressing it through the completeness threshold costs 19.0 and 12.1 points. At an anatomically defined 70 mm the frozen tests give 1.91 and 1.81 mm MAE.

cs.AI · cs.CV

新论文 · v1arXiv:2611.05849

A low-rank decoder bottleneck bounds reliability in foundation-model perturbation prediction

Zheyu Zhang, Yuanhao Huang, Fan Feng, Jie Liu

原文摘要

Foundation-model predictors of perturbation response are evaluated primarily by aggregate accuracy. Using their predictions to prioritize experiments requires assessing each prediction's reliability. We audit the state-transition (ST) decoder used in STATE across three encoders (SE-600M, scGPT, and Tahoe-x1) and four cell lines under CRISPRi. The decoder's first attention layer has a low-rank output. Projecting this output onto 4-32 fixed directions estimated from training activations preserves mean per-perturbation Pearson delta correlation (PDC). This low-rank attention bottleneck bounds the decoder's reliability by distance to training responses: PDC declines as the cosine distance from a perturbation's observed response to its nearest training response increases. We propose predicted-NN-distance, the cosine distance from a predicted response to its nearest training response, as a per-prediction confidence score. The score has a mean absolute Spearman correlation of 0.81 with PDC, close to the 0.88 obtained with the observed response. Thresholds calibrated on this score transfer across encoders and cell lines, and the score remains predictive of PDC for drug perturbations.

cs.LG · stat.ML

新论文 · v1arXiv:2611.05847

Time-to-Goal: Learned Temporal Metrics for Long-Horizon Planning with JEPA World Models

Ruilong Yu, Fei Ye

原文摘要

Joint-Embedding Predictive Architectures (JEPAs) support planning by comparing predicted latent states with an encoded goal. For this comparison to guide temporal progress, states closer in time to the goal should receive lower costs. However, training representations for prediction and distribution regularization does not directly enforce this ordering. We examine this mismatch in flat LeWorldModel (LeWM) by analyzing how its Euclidean goal cost changes with temporal separation. Our analysis identifies conditions under which states at different long offsets receive similar average costs, weakening their temporal distinction. To learn the missing ordering explicitly, we introduce Time-to-Goal (T2G), a lightweight metric trained on latent triples from offline trajectories. A margin ranking loss encourages smaller distances for temporally nearer states, requiring no rewards or policy labels. The learned metric then replaces the Euclidean planning cost while the JEPA encoder and predictor remain frozen. Diagnostics on AntMaze and FourRoom show that T2G preserves stronger temporal contrast and improves near--far ranking at long offsets. Across four navigation and manipulation benchmarks, T2G improves the average planning success rate from 32.7\% (flat LeWM) to 63.0\% and approaches or even surpasses the performance of the hierarchical H-JEPA baselines. These results show that learning temporal ordering for the goal cost can substantially improve latent planning even with a flat world model.

cs.RO · cs.CV

新论文 · v1arXiv:2611.05844

Sure Enough to Share? Overconfidence in GenAI Video Discernment is Associated with Sharing Intentions

Haoning Xue, Sijia Qian, Christopher Calabrese, Cuihua Shen, Laramie Taylor, Yixuan Wang

原文摘要

Generative Artificial Intelligence (GenAI) is blurring the line between synthesized and recorded videos, but less is known about people's awareness of their discernment abilities and the consequences of miscalibration. This study examines three forms of overconfidence in GenAI video discernment (i.e., overestimation, overplacement, and overprecision) and their associations with source judgments and sharing intentions in an online study (N = 973). Participants evaluated videos depicting everyday scenes and achieved 62.5% accuracy. Three forms of overconfidence showed distinct patterns: participants overplaced themselves by 12.8 percentile points, but overprecision showed consistent positive associations with sharing intentions and the tendency to classify videos as human-made. Age, GenAI usage, and AI literacy showed consistent positive associations with all three forms of overconfidence. These findings highlight the importance of distinguishing the three forms of overconfidence to better understand GenAI engagement and incorporating metacognition into interventions to support informed media consumption.

cs.HC · cs.CY

新论文 · v1arXiv:2611.05842

PEARL: Prediction Error-Adaptive Regularized Learning for Selective Forgetting under Partial Preference Drift

Rashmi Gangadharaiah, Balakrishnan Narayanaswamy

原文摘要

User preferences shift as needs, context, and tastes evolve. This matters for personalized recommendation, LLM response generation, and RLHF-trained reward models, which can become miscalibrated as preferences drift. Existing non-stationary bandit methods forget uniformly across all dimensions, but real preference shifts are typically partial: some dimensions go stale while others remain valid. Neural contextual bandits accumulate confidence monotonically via the Gram matrix, with no mechanism to direct uncertainty where predictions have gone wrong. We propose PEARL (Prediction Error-Adaptive Regularized Learning), which reverses the Gram update along feature directions where predictions are surprisingly wrong, while leaving confidence intact elsewhere. We prove that (i) any non-adaptive policy suffers linear regret after a preference shift, (ii) no fixed exploration rate achieves low regret in both stationary and non-stationary regimes, and (iii) PEARL's cumulative regret scales with the number of shifted users N_s, not the total population N. On PRISM, a personalized LLM response selection benchmark (1,500 users, 21 LLMs), PEARL beats greedy by +4.0 points and the best neural bandit baseline by +2.5 points (p<0.001), while performing on par with greedy when preferences are stable. It beats sliding-window and discounted approaches by 3 to 10 points, showing that selective forgetting outperforms uniform forgetting. The selection policy is a ~100K-parameter MLP that runs in milliseconds on CPU, leaves LLM weights frozen, and works with any API-based model.

cs.LG · cs.AI

新论文 · v1arXiv:2611.05841

Vision Paper: Why Distributed LLM Post-Training and Decentralized Alignment Are Now Essential

Zhanhong Jiang, Qisai Liu, Soumik Sarkar

原文摘要

This vision paper argues that distributed learning, including federated and decentralized, should become a first-class paradigm in LLM post-training, not merely a privacy add-on. Current methods like RLHF and DPO rest on an invisible assumption: preference data should be centralized. We contend this assumption is scientifically unjustified, practically unsustainable, and ethically problematic. As LLMs deploy into healthcare, law, finance, and multilingual communities, preference data originates from populations that cannot or will not centralize. We develop a three-pillar argument grounded in (1) privacy and data sovereignty, (2) pluralism and representational equity, and (3) robustness and scalability. We formalize key technical challenges unique to this intersection, reference drift, preference heterogeneity, and the DP-utility trade-off for contrastive losses, and propose concrete algorithmic directions, and sketch a research agenda. Our analysis shows distributed post-training is not only necessary but tractable, and ignoring it risks AI that is legally noncompliant, representationally narrow, and brittle at scale.

cs.AI

新论文 · v1arXiv:2611.05839

Makespan Bounds for Synchronous Pebble Motion on Graphs

Lucy McManamon, Jingjin Yu

原文摘要

We study the largest minimum makespan of labeled pebble motion on graphs under a model that permits synchronous pebble movement. While classical pebble motion on graphs allows only one pebble to move at a time, our model permits any number of pebbles to move to an adjacent vertex, provided that no two pebbles collide. At full occupancy every vertex is assigned a pebble and a legal round consists of disjoint cycle rotations. We prove a series of makespan bounds for this problem on graphs with varying structure and pebble density. For cycles with a chord, we extend a known quadratic bound at span two to every fixed span. For random cubic graphs, we convert permutation routing via matchings into legal schedules in two ways, applying cycle-cover batching at full occupancy and disjoint vacancy-delivery paths below full occupancy. For simple 3-connected planar cubic graphs, we prove a tight linear class maximum at every pebble count. We extend the results to increasing degree, common-neighbor conditions, and vertex connectivity. The results describe how graph connectivity, cycle structure, expansion, planarity, and occupancy affect worst-case routing time.

cs.DS

新论文 · v1arXiv:2611.05838

RACE: Calibrated Cumulative Scoring for Rollout-Free Robot Policy Checkpoint Selection

Changyeon Kim, Yekyung Nah, Kimin Lee

原文摘要

Assessing the deployment performance of learned robot policies during training is challenging, as directly measuring task success requires costly real-world trials for each candidate checkpoint. Averaged validation loss offers a rollout-free alternative, but its checkpoint rankings can be inconsistent with deployment performance. We analyze two limitations of this criterion: it penalizes action deviations without considering whether the policy can recover from them, and gives later reference predictions equal weight even when earlier deviations may lead execution away from the reference. We propose RACE, a novel rollout-free metric for ranking checkpoints using a fixed set of held-out successful trajectories. RACE calibrates action deviations against state-conditional thresholds derived from action differences at similar states in these trajectories. We aggregate these scores through a running product, so that a substantial deviation reduces the contribution of subsequent reference predictions. Averaging the resulting cumulative scores over time and across trajectories yields the checkpoint score. In simulation, RACE outperforms baselines across validation sources, while several baselines degrade sharply when the validation set changes. On real robots, its rankings align with deployment success across the evaluated policy backbones and tasks of varying difficulty. Perturbation analyses further show that RACE distinguishes deviations with markedly different effects on task success, even when baselines respond similarly.

cs.RO · cs.AI · cs.LG

新论文 · v1arXiv:2611.05835

Pathwise-Budgeted LLM Routing: Online Allocation with K-Bit Tail-Cost Learning

Hanzhang Qin, Sophie H. Yu, Yuewei Zhang, Zhi-Hai Zhang

原文摘要

Firms using large language models under fixed budgets must decide which model to call and whether to retry a failed task. Because a call's charge is revealed only after completion, one long response can exhaust the remaining budget and leave later tasks unserved. Our objective is to maximize the number of tasks solved before service stops. We develop a contextual bandit policy, ADP-HT, which learns each model's task-specific success probability and constructs conservative cost estimates from coarsened response-length labels on a quantile grid with $2^K$ intervals. The policy weighs predicted success against these costs, adjusting the cost penalty to realized spending and the budget available per remaining task. Under calibration, local regularity, and grid-coverage conditions, we bound the excess allowance in the policy's conservative cost estimates. At a fixed sample size, increasing $K$ reduces the discretization term but increases the estimation allowance. At the tightest tested budgets, ADP-HT solves more than twice as many MATH500 and GPQA tasks as the best implemented baseline. It achieves the highest mean cumulative score at ten of fourteen RouterBench budgets. On LiveCodeBench, it outperforms a deployed commercial router in both default and cost-saving modes at the three lowest test budgets.

cs.LG · math.OC

版本更新 · v3arXiv:2610.04044

Dynamic Quadtree Tokenization and Transformer for Adaptive Mesh PDE Forecasting

Yilin Zhuang, Noah Zambrano, Karthik Duraisamy

原文摘要

The quadratic attention cost of Vision Transformers (ViTs) forces a trade-off between spatial resolution and rollout horizon, particularly for fine-scale PDEs where shocks, reaction fronts, and material interfaces occupy small, evolving regions of the domain. Conventional neural surrogates also lack mechanisms to adapt resolution dynamically. We propose WAMRViT, a ViT that tokenizes inputs as balanced quadtrees using a wavelet-inspired refinement criterion, jointly encodes position and refinement level with 3D rotary positional embeddings, and regrids in cell space during inference for stable long-horizon rollouts. A multi-scale variant retains each leaf at its native source resolution and lets the model learn across resolution levels. Unlike fixed-budget adaptive-tokenization methods, WAMRViT imposes no predetermined token count and supports fully adaptive topology throughout autoregressive rollout. To our knowledge, it is the first machine-learning surrogate to natively tokenize multi-level Adaptive Mesh Refinement (AMR) data. On uniform-grid benchmarks, uniform-patch WAMRViT improves finest-level region-of-interest VRMSE over a finest-patch uniform ViT while using substantially fewer tokens. The multi-scale variant achieves the lowest first-step full-field RMSE and VRMSE on both benchmarks and improves rollout-averaged full-field and refined-region accuracy at long horizons. With parallelized regridding, its end-to-end rollout cost lies between finest-patch and approximately token-matched coarser-patch ViTs. On a complex AMR combustion problem whose finest features cannot be represented natively by the evaluated uniform-grid baselines, WAMRViT operates on adaptive cells built from the simulator hierarchy and substantially reduces finest-level error at matched transformer capacity. Code: https://github.com/tonyzyl/wamrvit

cs.CV · cs.LG

版本更新 · v2arXiv:2605.07139

Structural Rationale Distillation via Reasoning Space Compression

Jialin Yang, Jiankun Wang, Jiajun Wu, Henry Leung, Jiayu Zhou, Steve Drew

原文摘要

When distilling reasoning from large language models (LLMs) into smaller ones, teacher rationales for similar problems often vary wildly in structure and strategy. Like a chef who makes the same dish differently each time, this inconsistency burdens the student with noisy supervision that is hard to internalize. We propose Distillation through Reasoning Path Compression (D-RPC), which constrains the teacher to follow a compact, dynamically maintained bank of reusable high-level reasoning paths. For each training question, D-RPC retrieves the most relevant path and conditions the teacher to follow it, producing rationales that are consistent across similar problems yet diverse enough to cover different problem types. A PAC-Bayes analysis formalizes a trade-off between bank size and coverage, with smaller banks limiting path diversity at the risk of coverage gaps. Our ablations favor an intermediate bank size, consistent with this trade-off. Across five math and commonsense reasoning benchmarks with two student models, D-RPC achieves the highest average accuracy among the evaluated distillation methods, while using fewer tokens than template-heavy alternatives.

cs.CL · cs.AI · cs.LG

版本更新 · v2arXiv:2608.11746

Epiplexity Guided Data Selection and Generation for Out-of-Distribution Generalization

Ellen Su, Andres Potapczynski, Shikai Qiu, Edward Hughes, Andrew Gordon Wilson

原文摘要

Modern systems are increasingly expected to transfer across tasks not specified during training. What data facilitates generalization to unanticipated settings? One hypothesis is that data with more structural information could contain shared circuits and subprograms that may be recycled in a wider array of downstream settings. Epiplexity, a recently proposed measure of the structural information a compute-bounded learner can extract from data, offers a mechanism to reason about this relationship. As existing estimators for epiplexity only operate on data already seen during training, we show how to operationalize epiplexity as an online training signal by greedily maximizing its stepwise gain in two settings. For data selection, we fit scaling laws to the training loss curves of natural data domains to predict the expected epiplexity gain as a function of training tokens, and use this signal to adaptively determine the sampling weights over domains during training. For synthetic data generation, where no domain structure exists, we reward a generator with the change in epiplexity of a learner's synthetic training data and use REINFORCE policy gradients to guide the generator toward an epiplexity-maximizing distribution. In both cases, we find higher epiplexity predicts improved downstream performance on zero-shot and fine-tuning tasks, supporting the hypothesis that data rich in structural information yield representations that better transfer across domains.

cs.LG · cs.CL

新论文 · v1arXiv:2611.05832

StarWorld: A Cross-Layer World Model for Starlink Prediction and Streaming

Bowen Zhang, Pengcheng Luo, Hongjun Xie, Shujin Jia, Genke Yang, Jian Chu

原文摘要

Starlink and other low Earth orbit (LEO) satellite broadband systems exhibit stochastic access dynamics whose effects propagate from network measurements to throughput prediction and adaptive bitrate (ABR) streaming, making reasoning over multiple plausible futures essential. Existing studies mainly characterize realized traces or individual system layers, leaving cross-layer world modeling of these evolving dynamics largely unexplored. To address this gap, we propose StarWorld, a cross-layer world model for Starlink prediction and streaming. StarWorld couples learned stochastic network dynamics with executable prediction, control, and playback processes to imagine multi-step cross-layer futures, while a calibrated Trust Gate determines whether these futures are sufficiently reliable for use. On real Starlink measurements, StarWorld achieves the lowest network-future distributional errors among the comparison methods at the principal horizons and reduces pairwise controller quality-of-experience (QoE) effect error by 76%. These results support StarWorld as a cross-layer imagination environment for studying prediction and streaming outcomes under uncertain Starlink access conditions.

cs.NI

版本更新 · v2arXiv:2512.03416

TokenScale: Timely and Accurate Autoscaling for Disaggregated LLM Serving with Token Velocity

Ruiqi Lai, Hongrui Liu, Chengzhi Lu, Zonghao Liu, Siyu Cao, Siyang Shao, Yixin Zhang, Luo Mai 等 9 位作者

原文摘要

The architectural shift to prefill/decode (PD) disaggregation in LLM serving improves resource utilization but struggles with the bursty nature of modern workloads. Existing autoscaling policies, often retrofitted from monolithic systems like those in AIBrix and DistServe, rely on lagging indicators such as GPU utilization or coarse-grained request counts. This results in slow reactions to load spikes, leading to significant Time-to First-Token (TTFT) and Time-Per-Output-Token (TPOT) SLO violations and costly over-provisioning. We introduce TokenScale, an autoscaling framework that resolves this performance mismatch through two innovations. First, we propose Token Velocity, a novel metric that unifies the prefill, network, and decode stages by quantifying their rate of work. As a leading indicator of system backpressure, it enables proactive scaling. Second, Convertible Decoders allow decoder GPUs to dynamically execute prefill tasks during traffic spikes, creating a rapid-response buffer that absorbs bursts and eliminates the initialization latency of new prefillers. Our evaluation on a GPU cluster with production traces shows TokenScale improves SLO attainment from 50-88% to 80-96% and reduces costs by 4-14% over state-of-the-art systems, including DistServe, BlitzScale, and AIBrix. By uniting a predictive metric with a flexible system design, TokenScale significantly boosts the performance and efficiency of disaggregated LLM serving infrastructure.

cs.DC