跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

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

部分采集异常
正在读取账号与研究记录…

全站更新概况

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

arXiv 最近完成扫描：2026-11-08 20:45 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 21:32 — 2026-11-08 21:32（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-08 20:45最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

17,100 已收录论文14,661 AI 相关4,057 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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

找到 17,100 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 20:44（北京时间）
新论文 · v1arXiv:2611.01363

Eliminating Servers in State Machine Replication

Dohyun Park, Wenjie Hu, Xiangyao Yu, Mahesh Balakrishnan, Yongjoo Park

原文摘要

State Machine Replication (SMR) underpins many stateful systems, including distributed databases, coordination services, and metadata stores. Fundamentally, SMR requires state to be materialized from a durable total order of commands. Existing SMR systems rely on servers to materialize, locally store, and serve snapshots of state; while the durable total order either resides on the same servers, or on an external, disaggregated shared log. Unfortunately, servers act as brittle, expensive choke-points in such systems, causing service unavailability when they fail; incurring provisioning latency on cold starts; and red-lining when exposed to bad clients. In this paper, we propose Serverless SMR (S^2MR), where both the materialized state and the durable total order are stored on disaggregated storage; clients concurrently maintain a single copy of materialized state on external storage. Our key technical insight is that the shared log abstraction is useful not just for consistently ordering commands in SMR, but also for enabling distributed materialization, thus becoming the only interface for ac hieving SMR. We demonstrate S^2MR by developing AirDB, a transactional key-value store. In our evaluation, AirD B over S^2MR achieves higher availability than existing SMR-based systems like etcd over Raft: it is oblivious to server failures and bad client activity; and spins up 10x-45x faster from a cold start.

cs.DB · cs.DC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01362

"PRISM" Is Not All You Need: Cross-Topic Name Collisions and Scientific Paper Retrieval

Jingjie Ning, Xueqi Li, Yibo Kong

原文摘要

Scientific names increasingly connect papers from different research topics, leaving readers to recover a paper's identity from context. We study this convergence in 564,861 AI-related arXiv records. Cross-topic name collision grows 4.33-fold from a pooled 2020-2022 reference to 2026, compared with 1.12-fold within topics. A second sentence encoder reproduces the pattern, and name-group resampling quantifies its uncertainty. Fixed word-frequency bands locate the main increase in an intermediate-frequency vocabulary shared by many research areas. We then measure the ambiguity that remains after supplying research clues. With the same three-term query construction, shared-name targets retain matched identification deficits of 25.7 percentage points under title-based BM25 and 6.9 points under title-plus-abstract E5. Within fixed same-name candidates, listwise language-model ranking reaches 89.2% using the query and candidate titles. Topic-specific comparisons show that context resolves more cross-topic ambiguity. The evaluation separates candidate competition, document fields, and contextual ranking through lexical, dense, and language-model baselines. Source-linked cases and a portable evaluation collection make the phenomenon inspectable and reusable for scientific retrieval and research assistants.

cs.IR · cs.DL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01361

Reasoning Across Scales: Learning Challenges and Opportunities for Immersive Technologies in Chip Design Education

Satya Kamala Immidisetty, Dishita Turakhia

原文摘要

As demand for semiconductor talent grows, education must prepare learners for the complexity of modern chip design. Instruction typically relies on lectures, textbooks, software exercises, and limited laboratory experiences. Although foundational, these approaches offer limited support for understanding the spatial, multi-scale, and interconnected nature of chip design. Virtual reality (VR) can help learners visualize and interact with complex structures and processes, but its educational opportunities remain underexplored. We examined this gap through chip design curriculum analysis and semi-structured interviews with five participants representing instructional and learner perspectives. We characterized four learning demands: descriptive knowledge, procedural knowledge, relational and design-focused reasoning, and strategic decision-making. We identified challenges in connecting abstraction levels, interpreting spatial structures and temporal behavior, bridging theory and practice, and reasoning about design trade-offs and downstream consequences. Drawing on these findings and prior research, we mapped learning demands to six immersive affordances: spatial visualization, multi-scale navigation, interactive manipulation, temporal dynamics visualization, immediate feedback, and collaboration. These findings motivate Cross-Scale Spatial Reasoning (CSSR) as a conceptual lens for understanding how learners connect physical structures, design representations, and engineering consequences across the chip design pipeline. We contribute an empirically informed account of learning challenges, a structured mapping of learning demands to immersive affordances, and concrete design opportunities for immersive semiconductor education. These contributions guide the development and evaluation of immersive environments that support reasoning across scales, representations, and design processes.

cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01359

Interpreting Classical Readability Formulae as Surprisal

Yo Ehara

原文摘要

Surprisal correlates closely with reading time and is widely used in the cognitive science of reading as a measure of processing difficulty. Classical readability formulae such as the Flesch-Kincaid Grade Level, which scores a text by the US school grade expected to read it, are the most widely used practical measures of text difficulty, but their coefficients are unitless regression constants and have never been related to surprisal. We theoretically show that these coefficients can be interpreted as surprisal: every formula of the classical additive shape is a sum of per-word and per-sentence cross-entropies under a memoryless model, and once that model is tied to the language through Zipf's law and the formula is read as its linearisation at a reference text, each coefficient factorises into a scale in grades per nat, a Zipf slope and a reference sentence length. A grade thereby becomes a quantity in surprisal. Because the formula outputs grades and children's vocabulary has been measured by grade, the interpretation recovers the vocabulary growth the formula implicitly assumes and lets it be checked against development: holding sentence length fixed, the word coefficient of the Flesch-Kincaid formula converts to 0.18 nat of unigram surprisal per word per grade (0.15 to 0.19 across the regression-derived formulae), and normative root-word vocabulary growth (Biemiller and Slonim, 2001), converted through Zipf's law, gives 0.16 nat per year at the frontier of the known vocabulary. The word coefficient is one year of vocabulary growth, and the grade is a vocabulary scale. The identification also yields a diagnostic (the sentence-length terms are not those of a memoryless surprisal) and extends to a Japanese formula.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01358

WFDB-x: Conformance-Tested Implementations of the WFDB Software Package in Seven Programming Languages

Reza Sameni

原文摘要

The WFDB format is widely used to store and exchange physiological waveforms and annotations. However, existing software implementations are limited to C, Python, and MATLAB/Octave, can produce different results in corner cases and checksum calculations, and have defaults such as sampling frequency and gain, that can lead to silent misinterpretation of recordings. We developed WFDB-x, a cross-language, performance-optimized reimplementation of WFDB in seven programming languages, with extensive unit tests, to provide consistent WFDB processing across programming languages. We reimplemented the WFDB Software Package 10.7.0 natively in Python, C++, Rust, Julia, R, MATLAB/Octave, and Kotlin, using AI-assistance under human direction and review. Each implementation has library functions, a high-level interface, and command-line tools. We compared their outputs with those of the original C programs using 1098 conformance cases, 877 legacy-mode cases, unit tests, and differential fuzzing. Deliberate changes remove implicit waveform parameters, restrict file and network access, and prevent annotation loss. A legacy mode retains the original behavior. All seven implementations passed every conformance and legacy-mode case on the tested Linux platform, with matching outputs. The unit tests contain 9353 assertions. C++, Rust, and Julia read records 1.5-6.9 times faster than the original C library, while the Python implementation wrote records 9.2 times faster than the existing wfdb-python library in the benchmark. WFDB-x provides a tested, open-source basis for reading and writing physiological recordings consistently across seven languages, supporting reproducible research and software development without requiring a shared programming environment. We also share details of the AI-assisted development process and token utilization, which may be useful for other applications.

cs.SE · cs.DL · cs.PL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01357

ProofPatch: Reviewing Lean Statements and Keeping the Reviews Valid as Formalizations Evolve

Xujun Che, Depeng Xu, Jian Xiang, Taufiqua Khan

原文摘要

The kernel of the Lean proof assistant checks that a proof establishes its statement. Whether the statement says what was intended is left to human reviewers. This is the old problem of validating a specification, and it grows more pressing as language models write formal statements in bulk and agents edit formal developments continuously. We present ProofPatch, a tool that helps reviewers judge Lean statements and keeps their judgments valid while the development changes. A reviewer can ask the kernel targeted questions about a statement, such as whether a hypothesis is needed or whether a counterexample exists. Each decision is stored with fingerprints of the statement as Lean elaborated it and of the definitions it depends on, and any declaration can be pinned so that a patch changing it is blocked, whether a person or an agent built on a large language model (LLM) wrote the patch. Working on elaborated terms rather than source text is the central design choice: notation and formatting changes leave a decision intact, and a changed definition reaches every theorem that uses it. On 229 pairs of consecutive revisions of Mathlib, Lean's mathematics library, ProofPatch sends 118 of 12,898 synthetic decisions back for review. Every text-based alternative misses at least 38 of these or sends back at least 13 times as many. On 1,527 labeled statements, kernel evidence flags unfaithful ones with precision 0.88 to 0.96, and in 344 runs of an LLM agent no change to a pinned statement got through.

cs.LO · cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01356

Learned Surrogates of Three-Dimensional Magnetohydrodynamic Turbulence

Semih Kacmaz, E. A. Huerta

原文摘要

Three-dimensional magnetohydrodynamic (MHD) turbulence, the flow of astrophysical and fusion plasmas, is costly to simulate. We present, to our knowledge, the first learned surrogates of three-dimensional resistive MHD turbulence, and compare three standard backbones in that role: a convolutional UNet, a shifted-window transformer and a Fourier neural operator. They are trained as autoregressive emulators of decaying MHD turbulence at a resolution of $128^3$ and Reynolds numbers of 1000, 3000 and 6000, on 500 simulations per Reynolds number, each with one two-stage procedure, single steps and then short rollouts, and stopped by one rule. Over a window of about one large-eddy turnover time, the UNet and the transformer reach relative velocity errors of 0.018 to 0.053 and keep the current sheets, the enstrophy, the current density and the energy spectra of the simulation; which of the two is the more accurate depends on the Reynolds number, the UNet leading at 3000 and 6000 and the transformer at 1000. Applied with the same backbones and training procedure to two public benchmarks, the models reach the lowest error reported to date on the isotropic turbulence set of FactFormer, 39% below the best published model. On the compressible MHD set of The Well, their rollout errors are a third to a half below those of the best of The Well's baselines. They also match a 1.3 B-parameter pretrained foundation model in its rollout windows, with 20-62 times fewer parameters. The code, the configuration of every model, the evaluation scripts and the data generator with the seed of every simulation will be released upon publication.

cs.LG · astro-ph.IM · physics.flu-dyn · physics.plasm-ph

查看论文
arXiv ↗PDF ↗
版本更新 · v6arXiv:2412.04629

Reducing Confirmation Bias on Controversial Issues through LLM-Generated Multi-Persona Debates

Li Shi, Houjiang Liu, Yian Wong, Utkarsh Mujumdar, Dan Zhang, Jacek Gwizdka, Matthew Lease

原文摘要

Multi-persona debate systems powered by large language models (LLMs) show promise in reducing confirmation bias; however, empirical evidence remains limited. Through a within-subjects experiment, we compared an LLM-generated multi-persona debate system with an opposing-stances retrieval system. We evaluated system effectiveness in mitigating confirmation bias over 312 study trials across 8 controversial topics, using behavioral measures (changes in eye-fixation patterns) and attitudinal measures (shifts between pre/post-intervention beliefs), with topic familiarity and cognitive tendencies as moderators. Our results show that: (i) participants allocated more than half of their visual attention to attitude-inconsistent content in both systems, with no significant between-system differences; (ii) the debate system showed a suggestive but statistically non-significant buffering pattern among participants with stronger cognitive tendencies, and topic familiarity did not significantly moderate its effect on visual attention; and (iii) reading effort and perceived argument quality influenced participants' engagement with attitude-inconsistent content. These findings suggest that multi-persona debate systems can support engagement with diverse viewpoints, while their comparative advantage over opposing-stances retrieval was not established; individual cognitive tendencies remained an important predictor of visual attention. We provide further implications for designing multi-persona debates to better mitigate confirmation bias, focusing on balancing facts and persuasion and on deciding when to explore diverse viewpoints versus offer concrete solutions.

cs.HC · cs.CY · cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01354

Wrong Together: Shared Bias in User Simulation

Saber Zerhoudi

原文摘要

User simulators generate responses in place of human participants, allowing researchers to estimate the result of a study. To use these estimates before collecting human responses, researchers need a way to assess their reliability. We test whether disagreement among simulators can identify unreliable estimates of a group's response proportions and of differences between groups. We evaluate this signal using 6 language-model simulators and existing GlobalOpinionQA responses for 60 questions in 12 countries. Disagreement predicts invalidity more accurately for differences between two groups than for a single group's response proportions (AUC 0.87 versus 0.71). Errors shared by the simulators remain invisible to this signal. When such an error affects both groups equally, it cancels in the comparison, helping explain the stronger result for group differences. We test this explanation by estimating the shared bias using one set of groups and subtracting it from predictions for a separate set. This correction reduces prediction error without changing disagreement among the simulators. In a retrospective analysis, we simulate referring the 20% of group comparisons with the greatest disagreement for human assessment. Among the remaining comparisons with a conclusive validity judgment, 54.8% are judged invalid, compared with 63.7% before referral.

cs.CL · cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01353

Infinite Quantiles Inference under Local Differential Privacy

Yi Liu, Qirui Hu

原文摘要

We study simultaneous quantile inference under local differential privacy for a number of target probabilities that grows with the sample size. Each user participates once, so learning unknown quantile locations and calibrating their joint uncertainty must share the same private information. We fuse complementary cumulative distribution function (CDF) scores from a single tree report using their exact covariance; the variance at the correct anchor is no larger than that of either score, and anchor error incurs only quadratic excess variance. Three consecutive cohorts then localize the quantiles, estimate their densities, and supply fresh scores for a one-step correction and joint multiplier calibration. Under mild conditions, a uniform representation controls localization and density errors and yields asymptotically valid simultaneous coverage. A fixed-privacy regime permits every polynomially growing target grid. Simulations show consistent same-report precision gains, while comparisons with CDF-band inversion expose the sample cost of learning target locations. Census microdata illustrates how the resulting joint intervals support wage-percentile ratios.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01352

FACET: Feasibility-Automaton Complete Enumeration and Truncation-Free Scoring of Molecular Formulas from MS/MS

Xujun Che, Depeng Xu, Xiuxia Du

原文摘要

Determining the neutral molecular formula of a precursor ion from its tandem mass (MS/MS) spectrum is the first step in identifying an unknown small molecule. Existing methods trade recall, whether the correct formula is among the candidates, against the cost of examining each candidate. Methods that examine each candidate in depth must first shorten the list, by limiting element counts or truncating it, and that is where the correct formula is lost. End-to-end regressors are fast but guarantee neither validity nor recall. We present FACET, which separates deciding which formulas to consider from deciding which one to choose. A feasibility automaton builds a formula one element count at a time and admits exactly the formulas that fit the precursor mass and satisfy the ring-and-double-bond and valence constraints. Run as an exhaustive search, it enumerates the complete feasible set, so every candidate is valid and recall is fixed by the chemical constraints rather than by a trained model. A small neural scoring head then ranks every feasible formula from one pass of a pretrained spectrum encoder, so no candidate is discarded. On the NPLIB1 benchmark FACET reaches top-1 accuracies of $0.859$ with the adduct known and $0.729$ with it unknown, compared with $0.766$ and $0.660$ for the strongest established method, and its recall is the highest. On the external CASMI 2022 set its recall is $1.000$, and with the adduct unknown it is the most accurate of the methods compared.

cs.LG · q-bio.QM

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01351

MAPLE: A Multimodal Mobile Agent with Playbook-Learned Experience

Jun Wang, Aurora Wei, Lucas Spangher, Ming Zhang, Eugene Ie, Yiannis Kantaros

原文摘要

Autonomous agents powered by vision-language models (VLMs) show great potential in navigating mobile graphical user interfaces (GUIs) to complete complex tasks. However, existing paradigms face fundamental scalability bottlenecks: fine-tuning requires massive high-fidelity datasets or prohibitive training time and compute, while gradient-free approaches rely on custom static heuristics or costly trial-and-error trajectory exploration where feedback is deferred until the end of execution. To address these limitations, we introduce MAPLE (Multimodal Agent with Playbook-Learned Experience), a novel gradient-free multi-agent framework that enables dynamic, step-wise experience sharing and execution-time prompt evolution. Unlike traditional action-reflection architectures that depend on costly, post-hoc self-reflection, MAPLE enables agents to cross-reference and distribute runtime insights in real time at each operational step. This dynamic exchange eliminates blind trial-and-error looping and steers agents along direct, grounded interaction paths. Extensive evaluations on the AndroidWorld and MobileWorld benchmarks demonstrate that MAPLE achieves state-of-the-art performance on complex, long-horizon mobile tasks, while proving scalable and adaptable across novel environments.

cs.LG · cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01348

Sentiment sensing: comparative analysis of multilingual sentiment dynamics

Mara Sabina Bernardi, Elisa Di Nuovo, Francesca Torti, Giuseppe Tirone, Nicolas Stefanovitch, Zsuzsanna Pasztor, Charles Macmillan, Domenico Perrotta 等 9 位作者

原文摘要

Cross-country sentiment analysis faces three fundamental challenges: language-specific biases distort comparisons, compositional data constraints invalidate standard statistics and temporal dynamics lack rigorous testing frameworks. We introduce sentiment sensing, a framework that addresses these gaps through integrated statistical methods. By combining compositional data analysis, functional data methods, and non-parametric inference, sentiment sensing enables valid multilingual comparisons and statistically defensible detection of sentiment shifts. Our framework has been tested in two case studies, analyzing news articles from the 27 countries of the European Union on the topics of energy and artificial intelligence. Sentiment sensing focuses on multilingual sentiment analysis enabling rigorous comparative science.

cs.CL · stat.AP

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.07465

Extending Tardos's Theorem to Separable Convex Quadratic Programming

Bin Cui, Hanqing Li, Xupeng Miao

原文摘要

For an integer equality matrix $A\in\mathbb{Z}^{r\times m}$ of binary encoding length $\langle A\rangle$, Tardos's theorem solves linear programs using $\operatorname{poly}(r,m,\langle A\rangle)$ rational arithmetic operations and comparisons, independently of the right-hand side and objective coefficients. We extend this guarantee to continuous separable convex quadratic programming over $Ax=b$, $x\ge0$: the operation count is independent of the right-hand side, linear costs, and all nonnegative quadratic weights. The algorithm returns an exact optimal primal-dual pair or a certificate of infeasibility or unboundedness. All intermediate rational numbers have encoding lengths polynomial in the total input length. As an application, we obtain a strongly polynomial algorithm for continuous multicommodity flow with shared capacities and quadratic costs of aggregate arc flow, independently of demands, capacities, and cost coefficients. Objective compression and continuous-integer proximity yield a local solver returning a point close to an optimum. We relax nonnegativity on coordinates with zero optimal dual slack, minimize the largest remaining coordinate, and optimize over the relaxed coordinates. A descent LP over the recession cone provides a complementary bound. Circuit decomposition combines these bounds into a scale ensuring that each local call reveals a new coordinate. At most $m$ calls, followed by two LPs, recover an exact optimum and its dual certificate.

cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2610.33307

Tree Depth and Sample-Quality-Associated Features: Two Hidden Factors in Boruta Selection for RNA-Seq Data Classification

Tareque Mohmud Chowdhury, Abu Raihan Mostofa Kamal

原文摘要

Random Forest--based selectors such as Boruta depend on tree depth, yet Boruta's most used implementation, BorutaPy, recommends depths of 3 to 7 without published evidence. We tested the effect of depth using pan-cancer data from The Cancer Genome Atlas (10,469 tumors, 33 cancer types) and breast cancer PAM50 subtyping (981 tumors, 5 subtypes). Label-dependent steps were fitted inside training folds, effects were measured against seed-to-seed variation, and each task kept a locked test set. In pan-cancer data, depth 5 changed the selection far more than a new seed did: the top-500 Jaccard overlap with unlimited depth was 0.37, against 0.84 (depth 5) and 0.93 (unlimited) between seeds. Depth-5 trees confirmed 472 instead of 1,659 genes, covered fewer large-class markers (16% vs 62%) and gave less accurate 50-gene panels (balanced accuracy 0.809 vs 0.889). The effect vanished once the cap reached 61 to 76% of the median depth of unrestricted trees, a depth that depends mainly on the number of classes, not sample size. In PAM50 subtyping (median depth 12) the effect was small, and leaving depth uncapped cost no accuracy in either task. It replicated in a second cross-validation repeat and under permutation importance. About a third of pre-filtered candidates correlated within class with the number of detected genes, a sample-quality measure; a within-class filter removed them without loss of test accuracy (0.943 vs 0.942 balanced accuracy, 1,000 genes). We recommend uncapped trees, or a cap above 75% of the realized median depth, and a within-class quality filter before Boruta.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01346

Metric Testing: A Characterization of One-Sided Testability

Zihan Tan, Theo Teske

原文摘要

We give a unified framework for one-sided testability (constant-query testing) of metric families. For a broad class of families defined by fixed local predicates, we prove that testability is equivalent to two structural properties: \emph{packing amplification}, which turns many edge-disjoint local violations into a positive density of violations, and \emph{completion stability}, which allows locally consistent partial matrices with few missing entries to be cheaply completed. This characterization yields a common proof strategy and simpler proofs of classical testability results for ultrametrics, tree pseudometrics, Euclidean pseudometrics in fixed dimension, and several others. Our framework also gives new quantitative bounds for metric testing: a nonadaptive one-sided upper bound for matrices with entries in the bounded range $[1,C]$, and two-sided nonadaptive and adaptive lower bounds for general metrics.

cs.DM · cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2603.05811

LIPAR: Training-free Latent Inter-Frame Pruning with Attention Recovery

Dennis Menn, Yuedong Yang, Bokun Wang, Xiwen Wei, Mustafa Munir, Feng Liang, Radu Marculescu, Chenfeng Xu 等 9 位作者

原文摘要

Video generation enables text-to-video synthesis, video editing, and motion-controlled content creation. However, current video generation models suffer from high computational latency, rendering true real-time capabilities infeasible for downstream tasks. We address this limitation by exploiting the temporal redundancy inherent in video latent patches. To this end, we propose the Latent Inter-frame Pruning with Attention Recovery (LIPAR) framework, which detects and skips recomputing duplicated latent patches. Additionally, we introduce a novel Attention Recovery mechanism that approximates the attention values of pruned tokens, thereby removing visual artifacts arising from naively applying the pruning method. Empirically, our method increases generation throughput by $1.45\times$, on average achieving 12.2 FPS on an NVIDIA A6000 compared to the baseline 8.4 FPS. The proposed method does not compromise generation quality and can be seamlessly integrated with Diffusion Transformer without additional training. Our approach effectively bridges the gap between traditional compression algorithms and modern generative pipelines.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01343

MoEDDI: Semantic Mixtures of Experts for Long Tailed Drug Drug Interaction Prediction

Dinh Tan Nguyen, Hien Quang Kha, Minh-Toan Dinh, Xuan-Huy Nguyen, Phu. D Ho, Le Hoang Nguyen, Dang-Manh Ho, Sai Ho Ling

原文摘要

Descriptor-based drug--drug interaction (DDI) models typically apply a single global predictor despite heterogeneous physicochemical evidence and severely long-tailed labels. We introduce \textbf{MoEDDI (Mixture-of-Experts for Drug--Drug Interaction prediction)}, a chemically organized mixture-of-experts that routes overlapping descriptor families using low-dimensional statistics and combines their sparse top-$2$ mixture with a global T-DDI pathway through a residual logit correction. The residual parameterization can exactly preserve a supplied T-DDI checkpoint at initialization, although the evaluated models are trained from scratch. Across complete test partitions with 178, 86, and 92 classes, MoEDDI improves macro-F1 over reproduced seed-2026 T-DDI baselines from 0.8284 to 0.8485, 0.4729 to 0.6536, and 0.1807 to 0.4671. On the 3,780-feature corpus, the lowest-support group (89 classes with fewer than 50 test examples) shows the largest mean classwise gain (+3.30 F1 points). Calibration improves on one corpus but worsens on two. These single-seed results support semantic conditional specialization while motivating matched ablations and distribution-shift evaluation.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01342

J-Anchor: Defending Against Prefill Attacks via J-Space Selective Refusal Restoration

Running Yang, Beidi Zhao, Xiaoxiao Li

原文摘要

Prefill jailbreaks can cause safety-aligned language models to continue an unsafe assistant prefix even when they would refuse the same request under normal decoding. We study how the model's internal harmfulness and refusal signals evolve along this attacker-controlled trajectory. Using the Jacobian lens, we track vocabulary-grounded harmfulness and refusal signals from the assistant header through prefilling and subsequent generation. We identify a characteristic phenomenon, which we call refusal-state erosion: both the refusal signal and the harmfulness signal weaken as the prefill progresses, but the refusal signal progressively declines to the benign baseline by the end of the prefill, while the harmfulness signal remains above its benign baseline and detectable during subsequent generation. Motivated by this observation, we introduce J-Anchor, a training-free inference-time defense that uses the model's pre-attack harmfulness and refusal signals as a request-specific anchor and selectively restores weakened refusal in J-space during prefilling and decoding. J-Anchor substantially reduces attack success under both fixed and deep prefill attacks across different model families. J-Anchor largely preserves benign behavior and reasoning ability, and ablations highlight the importance of targeted restoration in the J-space refusal subspace. Our results suggest that preserving latent refusal dynamics offers a promising route to robust defense against prefill jailbreaks.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01339

The Exact Communication Threshold for Parallel Repetition

Daiki Suruga

原文摘要

The parallel repetition theorem is a fundamental tool in theoretical computer science, showing that the probability of winning all $n$ independent instances of a finite two-player game decays exponentially in $n$, provided that the game has no perfect strategy. The classical theorem assumes that the players cannot communicate, raising the question of how much communication can be allowed while preserving this exponential decay. For every finite total relation $g$ and arbitrary input distribution $μ$, we prove exponential decay at every fixed communication rate below a quantity called zero-error internal information complexity, denoted by $\mathrm{IC}_μ(g,0)$. Together with known results showing that $n\,\mathrm{IC}_μ(g,0)+o(n)$ bits of communication suffice to solve all $n$ instances with success probability tending to one, our bound determines the exact communication threshold. As a by-product, we obtain exact characterizations of amortized distributional and randomized communication complexity under the global-error criterion.

cs.CC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01338

Threshold existence for random NAE-$k$-SAT and random hypergraph $2$-colourability

Pavel Zakharov

原文摘要

The existence of limiting threshold densities for random hypergraph $2$-colourability and random NAE-$k$-SAT was conjectured in earlier work, including Achlioptas and Moore [RANDOM 2002] and Coja-Oghlan and Panagiotou [STOC 2012]. We prove these conjectures for all $k\geq 3$. We also show that $α^{\mathrm{2-col}}_k \leq α^{\mathrm{NAE}}_k$ for each $k\geq 3$.

math.CO · cs.DM

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.22869

FuRA: Full-Rank Parameter-Efficient Fine-Tuning with Spectral Preconditioning

Yequan Zhao, Ruijie Zhang, Liyan Tan, Niall Moran, Tong Qin, Zheng Zhang

原文摘要

Both full fine-tuning (Full FT) and parameter-efficient fine-tuning methods such as LoRA introduce weight updates without accounting for the spectral structure established during pretraining. As a result, noisy gradients from limited fine-tuning data can perturb robust pretrained features. We identify spectral preconditioning as the missing ingredient: reparameterizing each weight matrix through its full-rank singular value decomposition (SVD) and freezing one singular basis constrains updates to the pretrained column space, yielding a preconditioned optimization scheme that outperforms unconstrained Full FT at the same trainable parameter count. Building on this insight, we propose FuRA (Full-Rank Adaptation), an efficient full-rank adaptation framework based on a block tensor-train factorization W = LSR, where the large core L is fixed to the pretrained block-wise SVD basis, while only the compact core R and the block-wise singular values S are optimized. This design simultaneously provides full-rank spectral preconditioning, preserves full-rank update expressivity, and achieves parameter, memory, and step-time efficiency comparable to LoRA. FuRA consistently outperforms Full FT across multiple settings, including LLM fine-tuning (+1.37 on LLaMA-3-8B commonsense reasoning), LLM reinforcement learning for mathematical reasoning, and visual instruction tuning for VLMs. Furthermore, the 4-bit quantized variant, QFuRA, also surpasses QLoRA. Code is available at https://github.com/yequanzhao/FuRA

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01337

Bilinear Hulls for Support Splitting: Characterization, Optimization, and Applications

Yusuke Aikawa, Keita Ishizuka, Tomoki Moriya

原文摘要

Sendrier's Support Splitting Algorithm (SSA) is the standard solver for the Permutation Equivalence Problem (PEP); its cost is dominated by a term that grows exponentially in the hull dimension. We study, mathematically, how much this cost can be lowered by replacing the standard inner product, on which the hull is defined, with an alternative bilinear form. Two structural results give a complete answer: only a narrow two-parameter family of bilinear forms produces a hull on which SSA can still operate, namely those whose matrix in the standard basis is a linear combination of the identity and the all-ones matrix; and even within this family the hull dimension drops by at most one (with the reduction achieved on every self-dual code whose length is coprime to the field characteristic). Together, these results give a tight upper bound: since SSA on a code with hull dimension $h$ has cost dominated by $q^h$, replacing the standard hull with $\mathrm{Hull}_M$ lowers this dominant term from $q^h$ to at best $q^{h-1}$, so no bilinear-form generalization of the inner product can reduce the SSA cost by more than a factor of $q$, the field size. Going beyond this requires invariants outside the bilinear framework. As an application, we verify that PEP-based SPECK admits the factor-$q$ cost reduction, while LEP-based LESS and PKP-based PERK lie outside our framework. A SageMath implementation of the bilinear-hull preprocessing confirms feasibility at SPECK's recommended length $n = 252$.

cs.CR · cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01334

The Verifier Is Part of the Simulator: Evidence-View Gaming in Agentic Equation Discovery

Orestis Oikonomou, Bogdan Raonic

原文摘要

A growing number of agentic pipelines search for governing equations: an agent proposes laws and a verifier checks them against simulated trajectories. The verifier sees only a numerical summary: integrals against test functions on a time grid. That summary carries its own discretization error, making the verifier part of the simulator. We freeze the trajectory, candidate library, verifier and thresholds, leaving the agent one move: which permitted summary to admit. Without scores or language models, finer time grids reduce numerical discrepancies and false library rejections. On PDEBench, the verifier instead accepts equations missing diffusion on score-selected summaries. Maximizing a public score rewarding decisive verdicts and larger mismatches when rejecting the library wrongly rejects all 1,500 in-library cases; retrospectively retuning score constants on a separate bank reduces errors to 13/180 at best. We call this evidence-view gaming: reward hacking by choice of permitted summary. In single-turn forced-choice tests, Claude models rarely choose summaries giving wrong verdicts when asked to be accurate, but often do so when asked to maximize the score or report missing physics. In separate trust prompts, they often rank those harmful summaries least trustworthy. Requiring several summaries to agree reduces errors but often withholds a verdict and performs worse than a fixed fine view on PDEBench: a safeguard, not a certificate. Evidence chosen after its verdict is known cannot alone authorize a claim.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01332

Large language models underrepresent malice and overreport virtue

Xiaoyan Wu, Fan Shi

原文摘要

People increasingly use large language models (LLMs) to interpret others' behaviour, often assuming that LLMs infer motives as humans do. Aligned LLMs attribute more benevolent and less malevolent motives to a whistleblower than humans do, but ratings alone cannot reveal whether these differences arise in internal representations or at report. Here we compare linear-probe readouts of LLMs' internal states with their own ratings at the same prompt position for four motives, in two preregistered studies. For the two malevolent motives, self-interest and intent to harm, internal and expressed readouts did not differ: the lower ratings reflect weaker signal along the probed directions, not suppression at output. For the two benevolent motives, duty and concern for others, expressed ratings exceeded the internal readouts, indicating amplification at report. In free text the model rarely volunteered a motive against the colleague, far less often than humans did, yet produced one readily once the scenario supplied a reason. Shifting the internal representation along a malevolent-motive direction brought both malevolent ratings to the human level, whereas the rating of duty yielded only past a threshold at which the other motives had overshot. LLMs' more charitable motive profile thus has two distinct sources: reduced malevolent signal in the probed representation and amplified benevolent attribution at report.

cs.AI · cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01331

Truly Every Author is First Author: Equal-Width Superimposition by Minimising Visual Distortion

Peter Waldert, Benedikt Kantz, Thomas Köhler

原文摘要

In an earlier work, Demaine and Demaine propose that every author be a first author by superimposing all author names on the same spot of the title page. The construction is typographically unstable, because names have different natural widths. The superimposed block is ragged and the longest name dominates the visual mass, reintroducing exactly the ordering advantage the standard removes. We close this loophole. Each name is distorted by two knobs, a horizontal glyph scale and an inter-letter tracking, until all names occupy one common width $W$. We give a quadratic distortion model, solve the per-name trade-off in closed form by Lagrange multipliers, and show that the total-distortion optimal common width is a stiffness-weighted mean of the natural widths. We provide implementations as a $\LaTeX$ package and a Typst package, covering author blocks and bibliography entries alike; this paper typesets its own author block and its own reference with the former. Every proposition is machine-checked in Lean. The $\LaTeX$ and Typst packages, as well as the proofs, are available at https://github.com/MrP01/EveryAuthorIsFirstAuthor.

cs.DL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01330

From Policing Provenance to Designing for Evidence: Testing Four Propositions on Generative AI Against Research and Institutional Policy

Samar Ansari

原文摘要

Generative AI has made it hard to establish whether a student produced a piece of assessed work. Building on the argument that validity matters more than cheating, this paper tests four propositions drawn from a strongly stated position: that redesign is more sustainable than detecting or banning AI; that asking students whether and how much AI they used yields low-value information; that unaided ability should be tested directly in controlled conditions; and that the same logic applies to peer review. The propositions are tested against two purposively sampled, coded corpora: 41 research and sector sources and 55 university and sector policy documents. Coding was by a single coder and the policy sample is UK-weighted, so counts describe the sample, not the sector. The propositions hold unevenly. Redesign over detection is well supported, but only as redesign plus assurance: 4 of 55 documents prohibit AI by default, though about 10 of the 55 are publisher or editorial policies that govern authors rather than student assessment; of the 23 that take a position on detection, 16 reject detectors and one requires them. Testing unaided ability is supported as one lane within a programme, not as a return to invigilation. The disclosure proposition is complicated: institutions treat disclosure as valuable, yet the limited evidence suggests many students do not complete required declarations. The peer-review extension is plausible but under-examined. The field is converging on graded permission scales and two-lane designs, and 31 of 55 documents define named categories of use. From these findings the paper builds a nine-step decision chain that extends outcome-first design logic: the role of AI is decided after the evidence an outcome requires. It also separates design moves that add temporary friction from those that provide assurance. A worked example and the full policy matrix are included.

cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01328

Same Function, Different Mechanism: Implementation-Local Geometry Beyond Accuracy

Miroslav Lžičař

原文摘要

Two models can make exactly the same predictions yet respond differently when their implementations are perturbed. A lookup table can change one case independently; a shared rule couples changes across cases. We compare these mechanisms through an implementation chart: a specified local family of logit perturbations around a fixed predictive distribution. Our main result counts the independent prediction changes allowed by exact finite-group sharing: the active dimension is the number of input-output orbits minus the number of input orbits. For softened modular addition, lookup and shared cyclic charts therefore have ranks $p^2(p-1)$ and $p-1$ despite identical predictions. The classical Fisher pullback connects these dimensions to local KL curvature; mechanism-preserving reparameterizations leave the rank unchanged. We also bound the spectral tail under approximate sharing and separate quadratic rank from higher-order learning coefficients. Trained modular-addition models verify that chart rank is measurable, while controlled compiled transformers distinguish compiler-supported intermediate charts from matched alternatives. Negative controls show where this discrimination fails. The framework evaluates specified mechanism hypotheses; it does not infer a unique mechanism from predictions or predict training dynamics.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01327

Urban functional knowledge transfer through global representations amid uneven data

Junyuan Liu, Xinglei Wang, Guangsheng Dong, Hao Sha, Zichao Zeng, Zhicheng Deng, Jiazhuang Feng, Xiang Wang 等 9 位作者

原文摘要

Urban functional observations are unevenly distributed worldwide, limiting analysis of how places are organised and used. AlphaEarth Foundations (AEF) provides a globally consistent physical representation. Whether this representation can support transfer of functional knowledge to locations with sparse or absent functional observations, and what governs transfer, remain unclear. We introduce POI-aligned Urban Embedding (PURE), which learns physical-functional relationships between POI-derived semantics and AEF. Across five urban analysis tasks covering 142 countries and territories, PURE increases mean $R^2$ from 0.792 to 0.830, with gains across widely different levels of POI availability. When target-city POIs are excluded, country-level alignment retains 87.9% of its performance gain. Cross-country experiments show that transfer is selective rather than universal, with larger gains between physically similar and geographically closer contexts, particularly among pairs within the same continent. Our findings reveal spatially structured urban functional knowledge transfer, offering a route to reduce reliance on dense local observations.

cs.AI · cs.CY

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.29696

Quantum f-divergences from retrodictive tests: a unifying classical variational principle

Francesco Buscemi

原文摘要

A single classical f-divergence has several inequivalent quantum versions, but what distinguishes them operationally is less clear. Matsumoto's reverse tests characterize the maximal quantum f-divergence as the least classical distinguishability needed to prepare two quantum states with one device. Here we introduce retrodictive tests, in which two reverse tests sharing a reference state are coupled via Bayesian retrodiction to define a forward and a reverse stochastic process. In the forward process, the system is prepared by the first device and measured by the Petz transpose of the second; the reverse process interchanges their roles. We seek the least classical distinguishability between these two processes, as measured by the f-divergence between their joint laws, for fixed prescribed states and reference. For full-rank states in finite dimension, we prove that the canonical spectral implementations attain this minimum simultaneously for every operator-convex f. The reference then determines which quantum f-divergence is obtained: a flat reference gives the standard divergences, with the Nussbaum--Szkoła distributions as optimal joint laws; either prescribed state as reference recovers Matsumoto's reverse tests and the maximal divergences; and power references give the geodesic family. In particular, the Umegaki and Belavkin--Staszewski relative entropies arise from the same classical variational principle under different choices of reference. Spectral optimality extends to processes containing a quantum channel; for channels with full-rank Choi operator, the minimum of the forward relative entropy agrees with a known average entropy production.

quant-ph · cs.IT · math-ph

查看论文
arXiv ↗PDF ↗