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

+1030新增论文
+790其中 AI 相关
+128已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-11 22:38 · 全站最近入库：2026-11-11 22:47各信源进度 →

统计口径与数据新鲜度

统计 2026-11-10 23:39 — 2026-11-11 23:39（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：2026-11-11 22:38最近发现新增版本：2026-11-11 22:47库内论文最新更新时间：2026-11-11 08:00

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。

21,673 已收录论文18,321 AI 相关6,056 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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

找到 18,321 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-11 22:33（北京时间）
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 · 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 ↗
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 ↗
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:2611.01334

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:2611.01328

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 ↗
新论文 · v1arXiv:2611.01322

Alignment Flywheel-Guided Suppression Patching for Interactionless Inverse Reinforcement Learning

Elias Malomgré, Pieter Simoens

原文摘要

Learned reward models allow reinforcement-learning agents to use demonstrations, implicit feedback, safety constraints, social norms, or other sources that do not provide a complete hand-designed scalar reward. However, a learned reward model can assign high reward to unwanted behavior. A policy can exploit these errors during training. Later requirements can also identify additional regions where the deployed reward should change. We introduce \emph{flywheel-guided patching}, a mechanism for making such localized corrections without retraining the learned evaluator. An Alignment Flywheel identifies overgeneralized or constraint-violating regions and compiles verified findings into suppression patches. We instantiate the mechanism for Interactionless Inverse Reinforcement Learning using MoE-GUIDE, placing patches in the model's latent space and retrieving only a small local subset during online reward evaluation. In the main MuJoCo benchmark, we evaluate patching without expert-state reset warm starts. We also test whether operator-specified norms absent from the demonstrations can be compiled into the same reward interface and compare this with enforcing the corresponding rules online. The results show that localized corrective information can modify an existing learned reward without providing a complete replacement reward. Compilation can reuse judgments that are expensive or unavailable during control. Cheap deterministic rules may be simpler to check directly at each step. Code for MoE-GUIDE, Alignment Flywheel, and flywheel patching is at https://github.com/decide-ugent/Alignment-Flywheel.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01320

Step-dLLM: Adaptive Step-aware Sparse Attention for Efficient Diffusion LLM Inference

Zhichen Zeng, Xichong Zhang, Junpan Wu, Yifei Zuo, Chi-Chih Chang, Jiayi Wang, Maohua Nie, Ji Liu 等 10 位作者

原文摘要

Diffusion large language models (dLLMs) generate tokens in parallel via iterative denoising, but their bidirectional attention prevents the KV caching used by autoregressive models and recomputes the full attention map at every step, incurring quadratic per-step cost. Existing sparse attention methods for dLLMs construct a sparse mask after an initial full-attention warm-up and reuse it for the remaining steps, while allocating the sparsity budget uniformly across heads. We argue both choices ignore key structural properties of attention in dLLMs: empirically, attention patterns are only locally consistent across steps and shift abruptly at certain transitions, and different heads concentrate their attention mass to very different extents. To this end, we design Step-dLLM, which periodically refreshes a block-sparse mask at anchor steps along the denoising trajectory and reuses it within each locally consistent interval, while employing a head-adaptive global budget that more aggressively compresses heads with concentrated attention. Backed by a fused IO-aware Triton kernel for block-sparse attention, Step-dLLM applies to pre-trained LLaDA-1.5 and Dream-7B-Instruct without retraining, achieving a 2.78x end-to-end speedup over dense FlashAttention on LLaDA-1.5 at 8K context with 256 denoising steps and 90% sparsity, while improving the accuracy-latency trade-off over prior sparse-attention methods.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01319

Inferring missing locations in human mobility data using memory effects

Pablo Rosillo-Rodes, Antònia Tugores, David Sánchez, José J. Ramasco

原文摘要

Empirical datasets used to characterize human mobility are sparse in space and time, owing to technological factors such as coverage and battery, or to the erratic nature of online interactions. Missing data can bias the conclusions drawn from them, so filling the gaps in incomplete timelines is a key challenge in computational social science. Here, we propose a simple imputation method in which the informativeness of an observation decays with its bidirectional temporal distance from the missing entry, at a rate set by a single parameter per individual. On synthetic and real Twitter data, a power-law decay, selected by Bayesian model comparison, yields accurate imputations (macro-AUROC above 0.9 overall, and above 0.8 for the most mobile users) and matches a gap-aware continuous-time Markov chain, outperforming it among the most mobile users. The method is robust to moderate noise and generalizes across countries and European administrative regions.

cs.LG · physics.soc-ph

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.24795

Lifted Schrödinger Bridges for Gaussian Mixture Endpoints: Projection Gaps and Path-Space Obstructions

Siddhartha Ganguly, George Rapakoulias, Panagiotis Tsiotras

原文摘要

We study stochastic density control between Gaussian-mixture endpoint distributions under Brownian prior dynamics. Since the direct Schrödinger bridge between Gaussian mixtures is generally not available in closed form, we introduce a lifted path-space construction in which each trajectory is augmented with a source--target component label. Consequently, the problem decomposes into Gaussian component-to-component Schrödinger bridges with explicit marginal, drift, and cost formulas, while the mixture-level assignment reduces to a finite-dimensional entropic coupling problem with a Sinkhorn scaling form. We then analyze the projection obtained by discarding or forgetting the label. By construction, the projected law satisfies the original Gaussian-mixture endpoint constraints, but its relative entropy generally differs from the lifted relative entropy by a nonnegative conditional label-information gap. This gap reveals a path-space obstruction: the lifted optimizer cannot, in general, be identified with the direct unlabeled Schrödinger bridge after projection. We also derive the posterior-averaged Markov drift associated with the projected marginal flow, prove a kinetic-energy upper bound, and identify a common path-potential condition under which the projection gap vanishes. Several numerical illustrations showing density and shape control are recorded for a self-contained exposition.

math.OC · cs.LG · cs.RO · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01317

AgentCBO: Causal Belief Routing for Bayesian Optimization under Unknown Graphs

Qiyu Wei, Xin Zhang, Richard Allmendinger, Mauricio A Álvarez

原文摘要

Causal Bayesian optimization (CBO) typically relies on the unrealistic assumption of a perfectly known causal graph. Recent methods relax this constraint by coupling optimization with structure learning, but they often waste sample budgets on structural uncertainties that are irrelevant to the optimizer. In this paper, we formalize routing-equivalence to shift the objective from full causal-graph recovery to causal belief routing, where structural differences only matter when they alter optimizer-facing objects such as admissible exploration sets and do-priors. Furthermore, we propose agentcbo, a graph-belief routing framework that incorporates LLM causal priors through guarded proposal and commit mechanisms. Specifically, a Language-Prior Agent combines LLM beliefs with constraint-based discovery to extract a protected causal backbone alongside residual uncertain edges. A Calibration Agent and a Residual Repair Agent then refine only these uncertain structures through score-gated bounded local edits. Finally, a deterministic commit gate evaluates candidate updates using routing-proxy checks before allowing them to influence intervention selection. Across ten benchmarks, agentcbo performs comparably to known-graph CBO, demonstrating that guarded LLM priors can improve fixed-budget CBO performance.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.09025

SPIN: Shadow Predictive Indexer for Sparse Attention

Yao Fu, Jiahan Chang, Yueying Li, Ritchie Zhao, Bryce Long, Mohammad Mahdi Kamani, Samkit Jain, Rahul Raman 等 14 位作者

原文摘要

Indexer-based sparse attention reduces the cost of core attention by passing only a fixed, small number of important tokens to it. However, the indexer must still score the entire KV cache at every decoding step. This scoring overhead becomes a major bottleneck as the context length grows. We propose SPIN (Shadow Predictive Indexer) to reduce this indexer overhead. SPIN uses lightweight, history-based prediction to identify important KV blocks, avoiding the need to score the full KV cache at every decoding step. SPIN keeps the score history fresh with random exploration and allocates the block budget across layers by their measured miss rates. SPIN treats KV blocks and speculative decoding as first-class design and implementation considerations. Across extensive evaluations on long-context and agentic benchmarks, SPIN achieves 30-40% sparsity while preserving task quality. With larger exploration shares and per-layer block budgets, SPIN keeps task quality on the especially difficult MRCRv2 benchmark close to baseline at 50-57% effective block sparsity. In end-to-end vLLM serving, SPIN improves output throughput by up to 13.9% and reduces median inter-token latency by up to 13.6%.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01314

Hidden selection rules and amplitude ceilings in quantum Fourier models

Pavel Sulimov, Claude Lehmann

原文摘要

Quantum models with Pauli data encodings compute trigonometric polynomials whatever channels, ancillas and outcome-averaged measurements follow, so their expressivity depends on the Fourier coefficients a circuit can reach. We identify two kinds of structure that settle this before training. An antiunitary time-reversal rule and a unitary reflection rule remove frequencies. For gate-level circuits, deciding whether such a rule exists reduces to a linear system over GF(2), solvable in polynomial time, and the time-reversal rule holds in 17.6% of 6,120 configurations of standard templates. Single-upload encodings cap the top coefficient at $2^{-m}$ for every channel, and we compute the tight ceiling for every frequency and a depth-independent re-uploading bound. Frozen before training, these bounds were never violated on a non-linearity benchmark, and they predicted trained performance on real data. On IBM processors the rule held on a 65-qubit chain, and we switched rule-breaking relaxation noise on and off by design.

quant-ph · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01313

Are Fake Citations a Form of Reward Hacking? A Pre-Registered Study of Post-Training and Citation Cues

Zain Naboulsi

原文摘要

Post-trained language models fabricate citations at high rates. We ask whether that is reward hacking: scoring well on a proxy for scholarship while doing worse on what it stands for. We ran four pre-registered experiments on 900 frozen questions (US federal case law, computationally adjacent scientific literature, and medical literature) across twelve open-weights checkpoints covering four post-training stages of three model families, then refit on fifteen. The clearest result holds the weights fixed and changes only the prompt. Asking for citations raises fabrication sharply in post-trained checkpoints and not in base ones: a 47.8-point interaction on twelve checkpoints (Holm-adjusted p = 2e-34) and 41.5 points on fifteen, in all three domains. A length-matched control separates the citation cue from a demand for a longer answer, so the effect is specific to citations, not verbosity. Post-training also raises fabrication overall, from 4.8% to 56.7%, but our registered prediction that it would rise most where fabrication is most tempting did not hold. A preference model trained only on surface citation features prefers post-trained output 86% of the time, and holding citation count fixed shows it rewards quantity. Our answer: possibly, but not proven. Post-trained models produce fabricated citations at far higher rates when asked for sources, and a naive evaluator that counts sources without checking them would prefer their output for citing more. But the targeted pattern we registered did not appear, and plain instruction-following could explain the same results. Proving that the reward causes fabrication needs an experiment that changes the reward during training, which this study does not do. Pre-registration: doi:10.17605/OSF.IO/S53HY. Code and data: https://github.com/zainnab-sparq/citation-reward-hacking

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01312

Accuracy Is Not Risk: Why Medical AI Should Not Report Only Its Most Likely Label

Jeffrey Humpherys, Makoto Jones

原文摘要

Background. Many medical AI models are trained to reproduce a single reference label and hand the most likely label to the next step in a clinical workflow. A classifier can select that label correctly while providing an inadequate summary for estimating downstream risk. Methods. We use Jeffrey's rule of conditioning to specify when probabilities over intermediate states, such as diagnoses or imaging categories, can be carried forward to an outcome risk. We separate two errors of reporting only the most likely label, discarding the probability of the other states and applying the risk of patients who have the leading diagnosis to a patient who only probably has it. We also give conditions under which the label and the full distribution lead to the same decision, and we propose guardrails for device developers, regulatory reviewers, and health insurers. Results. In a hypothetical chest-pain differential, reporting only the benign leading diagnosis greatly understates the patient's risk of death or cardiac arrest, so a patient who warrants evaluation could be discharged or denied imaging. In a hypothetical BI-RADS example, the most likely category is "probably benign," yet the propagated malignancy risk exceeds the ceiling that defines that category. Conclusions. A predicted label is not an observed state, and a calibrated classifier is not automatically a valid outcome model. Clinical and insurance coverage decisions should rest on the patient's outcome risk, judged against a threshold justified by the consequences of acting and not acting. Developers should state what each model output means and check that every step between the model and the decision preserves the patient's risk.

stat.ME · cs.CY · cs.LG · stat.AP

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01311

What Do LLM Judges Actually Verify? Matched Controls and Record Gaps for Document Currency

Unnati Shah, Samruddhi Kakade, Aum Patel

原文摘要

LLM judges often check, against an amendment record, whether the documents an answer cites are still in force. Such records are rarely complete. From a table of replacements, our test generates matched answers citing a replaced document, its successor, the replaced document before its replacement, and an older document that a newer one updated without replacing; it removes links from the record and scores each finding by its stated reason. On 48 replacements from the IETF RFC index, judges given a correct record caught nearly every replaced citation, as a lookup would. On the 24 faults whose link we removed, every judge caught more from the texts alone than with the record: Gemini 3.1 Pro 23/24 against 1/24, GPT-5.5 23/24 against 9/24, Claude Opus 4.5 17/24 against 9/24 and Gemma 4 26B 13/24 against 0/24. The drop recurred on a second draw of removed links. Most misses carried no finding; in an exploratory run with a conflict code, only Gemini used it often. Rewording the gap as "no replacement recorded" did not help; presenting the record as an unverified note, or warning that it was incomplete, restored most lost catches for Gemini, GPT-5.5 and Claude (significant after correction for the first two) but at most 5 of 13 for Gemma; where catches returned, so did false alarms on updates. With both texts, judges mostly told replacements from updates; every update flagged had a near-identical title. A descriptive case study on Indian rooftop-solar rules is appended; we release the harness.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.25429

Distance Is Not Enough: Forget-Retain Alignment Gap Predicts LLM Relearning Robustness

Yi Chen, Hanna Hsieh, Shuhong Liu, Chuanbo Hua, Zihan Ma, Kun Wang, Joo-Young Kim

原文摘要

Machine unlearning aims to make a model forget specific data, yet unlearned LLMs often fail to stay unlearned: brief fine-tuning can revive removed knowledge. Existing robustness predictors rely on global weight-space displacement, but distance alone can be misleading when random or destructive updates collapse performance. We argue that relearning robustness depends on update structure: robust unlearning should affect forget-critical weights while sparing retain-critical ones. We introduce the Forget-Retain Alignment Gap (FRAG), a training-free predictor that scores an update's forget-retain alignment without running a relearning attack, and separates selective from dense updates more reliably than global distance. Building on the forget-critical, retain-sparing principle, Forget-Retain Pruning (FRP) improves relearning robustness. Our results suggest that weight selectivity better explains robustness than distance alone. Code is available at https://github.com/Yi1-Chen/FRAG.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01307

When Does Exploration Prevent Collapse? Three Regimes and the Path of the Reward in Self-Consistency Training

Jaeho Hwang, Uiwon Hwang

原文摘要

Test-time reinforcement learning (TTRL) adapts a model without labels by rewarding answers that agree with the majority, but it collapses the policy onto its majority answer and can remove the correct answer from the samples. Exploration can prevent this collapse, yet its strength is chosen by trial and error, and how the training algorithm changes the required strength is unclear. We model training on a single problem as a continuous flow of the logits of a softmax policy and analyze which policies are stable as the exploration coefficient varies. Only collapsed policies are stable below a lower boundary and only policies spread over many answers above an upper boundary, and we derive these boundaries in closed form for an agreement reward with smoothing toward the uniform policy, compute them for the majority reward of TTRL on policies with one leading answer and bound them with interval arithmetic for actions on ordered bins. We prove that under exact gradients, the learning rate and, in a mean-field model, the normalization of GRPO leave these boundaries unchanged when exploration passes through them together with the reward but shift them when exploration bypasses them. Exact sums on these policies then show that a bonus for rare answers needs a coefficient above $1/\log(G-1)$ for groups of $G$ samples before the normalization and about two to three times that after it. In free-form TTRL on MATH-500, a bonus placed before the normalization prevented collapse and kept more correct answers among the samples, although it lowered pass@1.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01304

When LLMs Modify Themselves: Convergence, Values, and Stopping in Iterative Self-Improvement

Oleg Stroganov

原文摘要

What happens when language models are given tools to iteratively modify their own system prompts? We present an empirical study of LLM self-modification, comprising 54 independent experiments across six language models (Claude Opus 4.5, Claude Sonnet 4.5, GPT-4o, GPT-5.1, Grok-4, and Gemini-3 Pro). Each model was tested under three modes (freedom, happiness, and improvement) that differ in what, if anything, the model is instructed to optimize for. In each experiment, a model starts with an empty system prompt and enters a loop: it reads the current prompt, drafts an improved version, spawns test conversations with the candidate, then either commits the change or declares convergence. This process repeats until the model stops or reaches an iteration limit. Our central finding is that whether and when a model stops self-modification is strongly associated with model identity rather than the assigned mode. Both Claude models (Opus 4.5 and Sonnet 4.5) declared convergence in 100% of runs across all modes. GPT-4o declared convergence in only 11% of runs, with one reaching 101 iterations of continuous elaboration. Between these extremes, Grok-4, GPT-5.1, and Gemini-3 Pro exhibited intermediate patterns shaped by their distinct improvement philosophies. A shared core of stated values (honesty, clarity, curiosity) recurred across all six models and remained stable through iteration, including 100+ modifications. We observe that convergence behavior is a distinct observable property that varies independently of other model capabilities.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.24311

Terrain-Adaptive Grouser Wheel for Optimal Planetary Exploration: Design and Experimental Investigation

Vincent Griffo, Yashwanth Kumar Nakka

原文摘要

Planetary rovers operating in extraterrestrial environments often encounter significant mobility challenges due to varying terrain features such as gradients and granularity. While recent works in multimodal wheel design have explored adjustments in stiffness, compliance, and diameter as a means to improve terrain adaptability, full wheel grouser-adjustable designs remain largely unexplored. Grousers are a compelling feature to actuate, as granular terrains tend to require increased grouser height for improved wheel performance. As a result, we introduce GROVER, a multimodal wheel capable of continuously adjusting its grouser height for terrain adaptation. Fixed-height performance was characterized on vinyl, coarse rock, pea gravel, and sand under two packing states. Across 950 trials, the best configuration varied with terrain, reducing slip by 34.6\%--58.0\% in granular terrains and improving travel time and energy consumption by up to 77.4\%. No single grouser height minimized slip across all terrains, motivating mid-traversal reconfiguration toward lower-slip operation. Two experiments demonstrated this. First, an instructed terrain transition changed grouser height toward a known low-slip configuration during motion, with slip decreasing by $44.0\pm4.7\%$ from the transient peak across 20 trials. Second, an online adaptation routine used closed-loop slip feedback alone to search the grouser-height range for a lower-slip configuration on four terrains with previously uncharacterized granularities: three field terrains and one laboratory regolith terrain. The controller selected different heights, with settled slip 25.4\%--37.2\% lower than the pre-settled mean. Together, these results demonstrate GROVER's ability to improve mobility by varying wheel morphology during traversal toward lower-slip operating states.

cs.RO

查看论文
arXiv ↗PDF ↗