跳到正文
研踪PaperTrail

版本更新

查看已发布论文的最新修订,在详情页对照实际观测到的版本。

部分采集异常

全站更新概况

+817新增论文
+672其中 AI 相关
+98已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-19 06:59 · 全站最近入库:2026-11-19 06:59各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 12:48 — 2026-11-19 12:48(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:2026-11-19 06:59最近发现新增版本:2026-11-19 06:59库内论文最新更新时间:2026-11-18 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。

26,871 已收录论文22,375 AI 相关8,156 有修订112 HF 社区发现

论文修订列表

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 8,156 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-19 06:57(北京时间)
版本更新 · v3arXiv:2610.09411

Shared Geometry As A Rosetta Stone: Cross-Modal Alignment Without Paired Data

Dominik Schnaus, Thomas Dagès, Daniel Cremers, Xi Wang, Phillip Isola

原文摘要

Multimodal representations enable zero-shot classification and retrieval, but aligning independently trained models usually requires large amounts of paired data. Yet, the Platonic Representation Hypothesis suggests that models trained on different modalities may converge spontaneously toward a shared representation geometry. But then, do we even need paired examples for cross-modal alignment? Remarkably, we show that paired examples are unnecessary for coarse cross-modal alignment. Our simple Wasserstein Procrustes method with a coarse geometric initialization (GeoWarP) aligns two disjoint embedding sets by estimating a single orthogonal map without seeing any pairs. Across datasets, modalities, and unimodal models, we show that we can consistently align independently trained representations without pairs, and standard geometric alignment metrics accurately predict when this is possible. Nevertheless, we can naturally benefit from paired examples. In the very few-pair regime, our method substantially outperforms existing ones, while staying competitive with pair-based methods with more added examples. Finally, we demonstrate that the resulting alignments can enable text-to-image generation without paired examples. These results show that independently trained models often share enough geometry to establish cross-modal correspondence with little or no paired data.

cs.LG · cs.AI · cs.CV

版本更新 · v2arXiv:2609.09001

Deposon: An Auditable, Conservation-Guaranteed, Game-Theoretically Tested Scattering Layer over LLM Reasoning Paths

Qihao Yuan

原文摘要

Multi-step LLM reasoning lacks a machine-recheckable ledger: discarded reasoning paths leave no auditable record. We propose the Deposon scattering layer, which binds each node of an LLM-generated concept-decomposition graph to a two-parameter Deposon state; paths undergo three-channel scattering -- transmission, reflection, irreversible dissipation -- obeying T+R+A=1 for arbitrary parameters, with a maximum per-path energy-audit deviation of 2.2E-16 (machine epsilon). We report all three evidence tiers honestly. On synthetic trap benchmarks the path-filtering gain is closed (pre-registered): unified reaches 100% versus a decoy-capture baseline at 7%/10%. On real benchmarks the layer is indistinguishable from a trivial six-keyword rule filter (GSM8K 0.87 >= 0.85, McNemar p=0.5; StrategyQA 0.899 = 0.899); no difference is detected here, so we sharpen the claim to "the differential value lies solely in machine verifiability." Fusion yields a second negative result: convex combinations with a semantic prior never improve (physics 0.484 -> 0.452), and the apparent lambda=2 gain is an anti-field artifact; any fusion gain must be nonlinear. Modeling the reverse dynamics as a potential game on the graph, we evidence an auditable scalar's monotonicity and near-gradientness and quantify the empirical coordination ratio (ECR). The three formalized dynamical-equivalence propositions (P1a/P1b/T-P1c) are falsified under the pre-registered kill protocol, and the potential-game claim is downgraded to approximate (cyclic-graph median residual 0.669): only consistency-level evidence survives at the dynamical level. Code: github.com/zeroandcat/Deposon.

cs.AI · cs.LG

版本更新 · v2arXiv:2611.00682

Testing MAX-CUT in the Adjacency Matrix Model: Tight Non-Adaptive Bounds and a Cubic Adaptive Lower Bound

Songhua He

原文摘要

We study the query complexity of approximating the MAX-CUT value to additive error $\varepsilon n^2$ in the adjacency matrix model. This was one of the first problems studied in graph property testing [GGR'98]. Previously, the best known upper bound for both adaptive and non-adaptive algorithms was $O(1/\varepsilon^6)$ [RV'07; MS'08; GMRS'22]. The only known lower bound was a trivial $Ω(1/\varepsilon^2)$ bound. We close this gap from both sides for non-adaptive algorithms, proving that its query complexity is exactly $Θ(1/\varepsilon^4)$. We also prove an adaptive $Ω(1/\varepsilon^3)$ lower bound. Our upper bound is achieved by a canonical tester that samples $O(1/\varepsilon^2)$ vertices in expectation and outputs the rescaled MAX-CUT value of the induced subgraph. We prove its correctness by applying spectral truncation to the adjacency matrix, using a geometric argument to control the sampling error of the retained low-rank part and a cut-norm restriction estimate [RV'07] for the remainder. As an application, an analogous proof also yields a tight $O(1/\varepsilon^4)$ non-adaptive query upper bound for MAX-2CSP. For our lower bounds, we show indistinguishability between a uniform random graph and a random graph with a planted hidden partition. For the non-adaptive lower bound, we observe that one plus the $χ^2$-divergence between the query transcript distributions is exactly a normalized Ising partition function, which can be bounded using Boolean hypercontractivity. For the adaptive lower bound, we relate each query's distinguishing power to the prediction, based on previous answers, of whether its endpoints lie in the same part of the hidden partition. We bound the combined advantage of these predictions using the completed transcript, which lets us analyze the adaptively chosen pairs of vertices together despite their dependence on earlier answers.

cs.DS

版本更新 · v2arXiv:2609.36924

Track-and-Complete: Learning Humanoid Skills from a Single Failed Human Video

Sarmad Idrees, Jongeun Choi

原文摘要

Learning humanoid skills from videos typically requires a successful human demonstration, which often demands custom data collection. Although failures have traditionally been treated only as negative examples in robot learning, they can still reveal a usable trajectory prefix before the task fails, as well as the intended outcome. To leverage this information from a failed-attempt video, we propose TRACC, a pipeline that imitates the useful portion of the motion trajectory and then completes the task based on the inferred task outcome. The usable motion prefix serves as prior knowledge until the failure occurs, after which the task-completion reward guides the policy to learn the intended task goal without requiring a successful task trajectory. We evaluate our method on six in-the-wild failed human tasks from the Oops! dataset. Our experimental results demonstrate the effectiveness of the proposed approach for learning from failed attempts when no successful demonstration is available. Thus, these findings establish failed human videos as a viable source of supervision for humanoid skill learning.

cs.RO · cs.CV

版本更新 · v2arXiv:2611.01609

MagPillar: A Soft Magnetopillar Array Tactile Sensor for Robotic Surface Perception

Haotian Guo, Yu Feng, Hao Wu, Jiazhi Tang, Ningbin Zhang, Jianshu Zhou

原文摘要

Robotic surface exploration benefits from tactile interfaces that accommodate contact and capture variations in surface characteristics. Herein, we report MagPillar, a tactile sensor inspired by spider tactile hairs that combines a magnetic pillar array with three-axis Hall sensing. A full-array mechanical and magnetic-field model characterizes how pillar deformation affects the superposed fields measured across the array, providing a physical basis for interpreting its contact responses. The compliant pillar architecture translates contact with surface textures and geometric features into distinct magnetic response patterns. Then, in robotic surface perception experiments, spectral features and logistic regression distinguish six material surfaces with an offline accuracy of 99.34% under within-session temporally blocked cross-validation. Continuous scans over periodic protrusions produce amplitude and peak-spacing variations consistent with changes in surface geometry. These findings connect compliant contact mechanics with distributed magnetic sensing, paving a new path for material recognition and qualitative surface-profile perception.

cs.RO

版本更新 · v2arXiv:2610.29607

No Frames, Just Frequencies: Bandwidth-Efficient Deployment-Time Adaptation for Smart Glasses

Francesco Corti, Moritz Becker, Olga Saukh

原文摘要

Deep neural networks deployed on smart glasses must adapt to changes in the distribution of incoming data while adhering to strict privacy and device constraints. We present No Frames, Just Frequencies, a bandwidth-efficient source-assisted adaptation framework that characterizes distribution shifts using compact frequency descriptors computed on-device. Rather than transmitting camera frames, the glasses compute and send frequency descriptors to a host device that contains a replica of the model. The host device maps the received frequency descriptor to a distribution shift operator that synthesizes out-of-distribution data and adapts a model replica using a pre-defined adaptation protocol. We evaluate the framework on mixtures of ImageNet-C corruptions using convolution-based (ConvNeXtV2-Femto), self-attention-based (DeiT-Tiny), and hybrid (TinyViT-5M) vision models, on person classification (Visual Wake Words), and on object detection (MS-COCO). Our results reveal that adaptation driven solely by the transmitted descriptors recovers $93-95\%$ of the supervised oracle adaptation gain on all three architectures, $82\%$ on Visual Wake Words and $94$--$98\%$ on MS-COCO. Notably, adaptation quality degrades gracefully as the descriptor resolution decreases from $224 $ to $28$ pixels, consistently across architectures, enabling bandwidth reductions from $213\times$ to $784\times$ across the frequency descriptors.

cs.CV · cs.LG

版本更新 · v2arXiv:2607.08974

CLAP: Direct VLM-to-VLA Adaptation via Language-Action Grounding

Yuri Ishitoya, Jeremy Siburian, Masashi Hamaya, Haruto Suzuki, Kuniaki Saito, Toshihiko Fukushima, Cristian C. Beltran-Hernandez, Mai Nishimura

原文摘要

Vision-language-action models (VLAs) inherit semantic capabilities from pretrained VLMs, yet large-scale post-training on robot data and architectural modifications can reshape the backbone so extensively that it becomes difficult to isolate what the VLM contributes to control. Directly converting pretrained VLMs into VLAs with minimal architectural change offers a more transparent path to understanding how VLM capabilities transfer across model scales. The core obstacle is output-distribution mismatch: predicting actions as bare numeric token sequences moves generation away from the VLM's pretrained language distribution, degrading the capabilities we seek to preserve. To address this, we propose CLAP (Causal Language-Action Prediction), which prepends each numeric action sequence with a natural-language action description, causally conditioning precise action-token prediction on a language-action plan without modifying the backbone architecture. With only 4-5 hours of training, 2B CLAP achieves 90.8% on LIBERO (+14.9 pt over VLA-0) and improves robustness on LIBERO-PRO under language, object, and spatial perturbations. Ablations attribute the gains to action-grounded language semantics, and on a real UR5e robot 2B CLAP reaches 60% success against 15% for matched VLA-0. We release CLAP at 0.8B, 2B, and 4B as an open-weight, multi-scale compact VLA family from a single VLM lineage, enabling controlled analysis of VLM-to-VLA capability transfer.

cs.RO · cs.AI

版本更新 · v2arXiv:2606.03851

The Price of Partial Information with Switching Costs: A Complete Characterization for Feedback Graphs

Nicolò Cesa-Bianchi, Tommaso Cesari, Roberto Colomboni, Emmanuel Esposito, Federico Fusco, Tomer Koren

原文摘要

We study how switching costs affect minimax regret under partial feedback. Which features of the feedback preserve the $\sqrt T$ rate, and which force the $T^{2/3}$ rate? We address this question in the framework of feedback graphs, which interpolate between full information and bandits: playing an action reveals the losses of its out-neighbors in a known directed graph. Prior work on feedback graphs with switching costs gave algorithms with regret of order $T^{2/3}$, but matching lower bounds only for restricted classes of graphs, leaving the question open. We establish a complete characterization of the minimax regret with switching costs for all feedback graphs: $\widetildeΘ(\sqrt T)$ if the graph is strongly revealing, meaning that every pair of distinct actions has an endpoint that observes the losses of both; $\widetildeΘ(γ^{1/3}T^{2/3})$ for every other observable graph, where $γ$ is the domination number; and linear otherwise. In particular, tournaments, in which every action observes its own loss and each pair of actions is joined by one directed edge, sit at the phase transition: they behave like full information, but deleting the edge of any pair forces the rate $T^{2/3}$. Hence an action that observes all losses is neither necessary nor sufficient for the rate $\sqrt T$. Our algorithm TournamentSteering for the strongly revealing case rests on a new principle: each observed comparison of two actions serves both to estimate losses and to steer play, and the loss reduction from steering pays for the variance of the estimates. For every strongly revealing graph, distributing the comparisons among observing actions keeps this variance, and hence the regret, polylogarithmic in the number of actions, by an argument similar to the greedy construction of logarithmic dominating sets in tournaments.

cs.LG

版本更新 · v3arXiv:2603.07604

EmbedTalk: Talking Head Synthesis using Gaussian Embeddings

Arpita Saggar, Jonathan C. Darling, Duygu Sarikaya, David C. Hogg

原文摘要

Deformable 3D Gaussian Splatting (3DGS) has emerged as a popular method for real-time talking head synthesis, offering high-quality renderings at low latency. Tri-planes are a common choice for encoding Gaussians prior to deformation since they provide a compact and continuous representation. However, tri-plane encodings are limited by grid resolution and approximation errors introduced by projecting 3D volumetric fields onto 2D subspaces. Recent work has demonstrated the effectiveness of per-Gaussian embeddings for driving temporal deformations in 4D scene reconstruction. We introduce EmbedTalk, which leverages these embeddings to model speech-driven facial deformations for talking head synthesis. Comprehensive experiments show that EmbedTalk improves rendering quality, lip synchronisation, and motion consistency over previous 3DGS-based methods, while remaining competitive with state-of-the-art generative models. Replacing tri-plane features with embeddings also yields significantly more compact models that achieve 60+ FPS on a laptop GPU (RTX 2060 6 GB). Code and further details are available at https://arpita2512.github.io/EmbedTalk/

cs.CV

版本更新 · v3arXiv:2608.12231

An Efficient Minimax-Optimal Algorithm for Adversarial $m$-Set Bandits

Francesco Bacchiocchi, Tommaso Cesari, Roberto Colomboni

原文摘要

We study adversarial combinatorial bandits with $m$-set actions, where at each round the learner selects $m$ out of $d$ items and observes only the aggregate loss of the selected items. The resulting action set contains $K=\binom{d}{m}$ elements and can therefore be exponentially large. We propose a computationally efficient algorithm that exploits this structure without explicitly enumerating the action set. Against adaptive non-anticipating adversaries, it guarantees, with probability at least $1-δ$, regret against the best action in hindsight of $R_T =O(\sqrt{dT\log(K/δ)}). $ This matches the high-probability regret bound of the finite-action EXP3 with Kiefer-Wolfowitz exploration algorithm of Zimmert and Lattimore, whose direct implementation may require exponential space. Our algorithm instead represents each sampling distribution with $d$ parameters and runs in polynomial time without enumerating the action set. This resolves an open problem posed by Maiti et al. We complement this upper bound with a matching high-probability lower bound. For all sufficiently small $δ$ and all sufficiently large horizons, every randomized algorithm admits an adaptive non-anticipating adversary for which, with probability at least $δ$, $R_T=Ω( \sqrt{dT\log(K/δ)}). $ Thus, the rate is minimax optimal up to universal constants in this regime. In particular, setting $m=1$ shows that the $\log K$ factor in the high-probability regret bound for ordinary $K$-armed bandits against adaptive non-anticipating adversaries is unavoidable. This strengthens the lower bound of Gerchinovitz and Lattimore, closing the remaining $\sqrt{\log K}$ gap between high-probability upper and lower regret bounds.

cs.LG

版本更新 · v3arXiv:2605.08698

Supersampling Stable Diffusion and Beyond: Training-Free Neural Network Scaling via Signal Interpolation

Md Abu Obaida Zishan, Jannatun Noor, Annajiat Alim Rasel

原文摘要

This work presents a training-free approach for interpolating neural networks using signal interpolation methods (i.e., linear, bilinear, bicubic). We discovered this phenomenon while attempting to interpolate the convolution layers of Stable-Diffusion-1.5 for beyond-training-resolution (BTR) image generation. As we know, for generating BTR images using DDPMs (Denoising Diffusion Probabilistic Models), there are mainly two approaches, namely, 1) patch-wise diffusion and 2) convolution-kernel dilation. Patch-wise diffusion cannot solve the object-duplication problem efficiently, while the kernel dilation approach may be harder to fine-tune later. Thus, we proposed convolution-kernel interpolation of the Stable Diffusion 1.5 model for $4\times$ BTR image generation. We discover and show mathematically that signal interpolation methods can correctly scale convolution kernels when multiplied by a flat-attenuation factor, while achieving competitive performance against the state of the art. We then applied the same methodology to non-DDPM deep neural network architectures, adapting them for BTR image classification, achieving a worst-case performance drop of $\sim 7\%$ on the ImageNet-1k validation set. Again, we subsample the penultimate fully connected layer of VGG-16 using our method, reducing up to $\sim 9\%$ parameters with $\sim 5\%$ loss in performance. Finally, we also discuss how we can reduce the memory footprint of training neural networks to $4\times$ or greater.

cs.CV · cs.LG

版本更新 · v2arXiv:2611.00240

Constant Approximation of Fréchet Distance in Near-Linear Time

Haoqiang Huang, Zihe Wang, Shuo Zhang

原文摘要

We give the first constant-factor approximation for the Fréchet distance in near-linear time. Given two polygonal curves in $\mathbb{R}^d$ with $n$ and $m$ vertices, respectively, where $m\le n$, our deterministic algorithm runs in $O(n^{1+\varepsilon})$ time for every fixed $\varepsilon>0$ and $d$, with an approximation factor depending only on $\varepsilon$ and $d$. The same result holds for the discrete Fréchet distance. Our result extends the line of work initiated by Cheng, Huang, and Zhang (STOC 2025) from strongly subquadratic to near-linear time. Our algorithm recursively balances preprocessing and query time. An index for comparing subcurves of a single curve supports faster queries between different curves. We obtain this speedup by replacing one curve with surrogates assembled from indexed subcurves of the other and shared across starting points of matchings. Faster queries then reduce the cost of building the next index. Compact boundary reachability summaries allow the answers to be reused in later recursive calls. After a number of rounds depending only on $\varepsilon$, both preprocessing and query time are near-linear.

cs.CG

版本更新 · v4arXiv:2601.08434

Large Multimodal Models for Embodied Intelligent Driving: Enabling the Next Generation of Autonomous Mobility

Long Zhang, Yuchen Xia, Bingqing Wei, Zhen Liu, Shiwen Mao, Zhu Han, Mohsen Guizani

原文摘要

The advent of Large Multimodal Models (LMMs) offers a promising technology to tackle the limitations of modular design in autonomous driving, which often falters in open-world scenarios requiring sustained environmental understanding and logical reasoning. Besides, embodied artificial intelligence facilitates policy optimization through closed-loop interactions to achieve the continuous learning capability, thereby advancing autonomous driving toward embodied intelligent (EI) driving. However, such capability will be constrained by relying solely on LMMs to enhance EI driving without joint decision-making. This article proposes a novel semantics and policy dual-driven hybrid decision framework to tackle this challenge, ensuring continuous learning and joint decision. The framework merges LMMs for semantic understanding and cognitive representation, and deep reinforcement learning for real-time policy optimization. This article particularly details the foundational principles of EI driving and LMMs, and also introduces the emerging opportunities this framework enables, encompassing potential benefits and representative use cases. The proposed framework, evaluated through a lane-change planning case study, achieves at least a 19% performance improvement over the baselines, as verified by simulations. Finally, key open challenges and future research directions are identified to guide subsequent work.

cs.RO · cs.AI

版本更新 · v3arXiv:2507.18229

From Individual Learning to Market Equilibrium: Correcting Structural and Parametric Biases in RL Simulations of Economic Models

Ruxin Chen, Zeqiang Zhang

原文摘要

Applying Reinforcement Learning (RL) to economic modeling reveals a fundamental tension: standard RL agents do not behave as competitive price-takers. While macroeconomic models typically assume agents take aggregate conditions as given, a naive single-agent RL algorithm learns to internalize its impact on the environment, effectively exerting market power. We illustrate this divergence in a search-and-matching model with concave production, showing that a standard RL agent converges to a monopsonistic allocation rather than the competitive equilibrium. Furthermore, we show that RL's approach to time discounting distorts standard intertemporal economic trade-offs. To resolve these issues, we propose a Calibrated Mean-Field Reinforcement Learning framework that restricts the agent to optimize against an exogenous aggregate state to restore price-taking behavior, and recalibrates the RL reward structure to reflect true economic opportunity costs. By iteratively updating the aggregate state, our algorithm converges to a stationary fixed point that recovers the competitive equilibrium. This approach provides a method for embedding learning algorithms into dynamic general equilibrium models.

econ.GN · cs.AI

版本更新 · v3arXiv:2609.35107

DoAtlas-2: A Foundation for Self-Evolving Causal Biomedical Discovery

Yulong Li, Rong Xia, Yuxuan Zhang, Jianxu Chen, Xiwei Liu, Haochen Xue, Maosheng Li, Yuhang Liu 等 15 位作者

原文摘要

We introduce DoAtlas-2, a foundation for self-evolving causal biomedical discovery that organizes knowledge around causal mechanisms and advances through external evidence from human populations. DoAtlas-2 integrates 771 research resources covering more than 720,000 participants in 48 countries, from longitudinal clinical phenotypes, medical imaging, and continuous physiological signals to eight molecular layers, together with an evidence network of approximately 4.7 million literature-derived records over 93,566 concepts and 149,383 candidate causal relations. DoAtlas-2 autonomously formulates research questions from evidence gaps and unresolved mechanisms, prespecifies their causal designs, and generates validated analyses. Supporting, challenging, and unresolved results continuously revise mechanistic interpretations, the causal evidence state, and the discovery frontier, so that DoAtlas-2 self-evolves within a closed loop of hypothesis generation, empirical testing, and renewed discovery. DoAtlas-2 has systematically evaluated 2,031 research questions. In the Human Phenotype Project (HPP), it formulated 4,014 candidate pathway questions across vascular, early-glycemic, and hepatic-metabolic systems, and screening of the first 1,079 yielded statistical support for 756. Representative studies identify blood pressure as a convergence node linking adiposity, hepatic, and lipid phenotypes to vascular outcomes, and show that an adiposity-inflammation-blood-pressure pathway is largely attenuated by joint adjustment for body mass index (BMI) and smoking. The discovered vascular network constitutes a completely interpretable predictive foundation, admitting exact attribution of every prediction and closed-form mediation effects. DoAtlas-2 thereby unifies causal mechanism discovery, population-evidence testing, and interpretable prediction within one continuously evolving foundation.

cs.AI · q-bio.QM

版本更新 · v2arXiv:2611.00006

Cultural Evolution Drives the Emergence of Conventions in Neural Emergent Communication

Maxime Toquebiau, Jérôme Botoko Ekila, Paul Van Eecke, Katrien Beuls

原文摘要

Recent studies of language evolution with neural agents often use models where agents can either speak or listen, where there are only two agents in the population, or where agents can share internal representations. These choices prevent the study of how language emerges through cultural evolution, i.e. through the cumulative adaptation of individual behaviours to fit the communicative needs of the community. We tackle this issue with a new model that trains populations of bi-directional neural agents in a fully distributed fashion to solve a referential game. We demonstrate the effectiveness of this approach on multiple image datasets and show that it is able to scale to large populations. We also show that more conventional languages are easier to learn, providing a direct advantage for cultural transmission. Overall, this work provides a novel approach to neural emergent communication that opens up new directions for evolutionary linguistics.

cs.NE · cs.CL · cs.MA

版本更新 · v2arXiv:2609.20701

Stable Movement for Nondual Lipschitz Convex Optimization: Efficiency and Nearly Optimal Oracle Rates

David Martínez-Rubio, Cristóbal Guzmán

原文摘要

We study efficient algorithms for realizing the first-order oracle complexity of optimization of $G$-Lipschitz convex functions with respect to the $\ell_q$-norm over an $\ell_p$-ball of radius $R$, where $1\leq p,q\leq\infty$. For $p<q$, we obtain error $\widetilde{O}_{p,q}(GR/T^{1/p-(1/q-1/2)_{+}})$ after $T$ oracle queries, attaining the lower bounds in a COLT 2015 open problem (Guz15b) with efficient algorithms. In particular, the rate is $\widetilde{O}(GR/T)$ for Euclidean Lipschitzness with an $\ell_1$-ball domain of radius $R$ ($p=1,q=2$). Our solution consists of reducing convex Lipschitz optimization to the chasing nested convex sets problem (BBE+20) in sublevel sets of an evolving maximum of affine lower bounds, that is, the bundle (LNN95): at each query we either find a point with low function value or we produce a deep cut in the current sublevel of the bundle that we chase. The dichotomy between stability of selectors and forced movement by deep cuts bounds the number of iterations of the algorithm nearly optimally. For nested convex subsets of the $\ell_p$ ball $R B_p^d$, we introduce novel stable selectors whose movement is nearly optimal in high dimensions. A Monte Carlo average of the proposed selector achieves near-optimal rates with high probability and can be implemented for our optimization algorithm in polynomial time in the real-arithmetic model.

math.OC · cs.LG

版本更新 · v2arXiv:2609.05191

Cutting Down the Tower: Single-Exponential Envy-Free Cake Cutting

Qilin Ye, Yannan Bai

原文摘要

Envy-free cake cutting is a central problem in fair division with a striking divide between existence and computation. Classical topology guarantees that envy-free allocations exist, yet finding one efficiently (in the Robertson-Webb query model) has resisted decades of work. The seminal work by Aziz and Mackenzie established the existence of a bounded protocol for every $n$, but its query bound is $n^{n^{n^{n^{n^n}}}}$. Subsequently, Sokolov modified their protocol and sharpened its analysis, obtaining a bound of $n^{8n^2(1+o(1))}$ queries, the best deterministic upper bound known before this work. In contrast, the general lower bound, due to Procaccia, is merely $Ω(n^2)$. We close much of this gap with a deterministic protocol using $n^{O(1)}2^n$ queries, the first single-exponential bound for general valuations. Like Aziz and Mackenzie, we repeatedly allocate cake without envy until some agents can leave with their pieces, guaranteed not to envy anyone who stays, even if a staying agent receives all the remaining cake. To reach this state, Aziz and Mackenzie generate $n^{n^{n^n}}$ partial allocations so that enough of them can be redistributed without conflict. Instead, we show that only polynomially many partial allocations suffice. Our key idea is to ``prune'' scarce allocations upfront: if only a few allocations can help a certain pair of agents, we discard them and handle that pair another way, leaving plenty of allocations for every remaining pair so each gets a distinct one. As a result, we make only polynomially many calls to Aziz and Mackenzie's subroutines, and this gives us our $n^{O(1)}2^n$ bound.

cs.GT

版本更新 · v2arXiv:2610.39550

Beyond Preference Following: Benchmarking Profile-Query Arbitration in Personalized Text Transformation

Tenghao Ji, Qichen Sun, Zhuoran Lu

原文摘要

Writing assistants use persistent preferences to personalize responses, but these can conflict with the current request. Responses can meet every requirement yet serve the task poorly, while task failures need not involve following a conflicting preference. We introduce Profile Conflict Arbitration (PCA-Bench), a benchmark of 64 rewriting tasks and 256 task-preference pairs. We construct these pairs by varying the profile preference for each fixed text and request, covering different relations between the preference and the request. We assess whether responses meet requirements, how well they achieve the request's goals, and whether they follow preferences. Across three LLMs, we find that when preferences compete with task goals, a higher success rate in meeting both requirements and preferences does not mean better responses: it can come with a greater quality loss compared with responses without a profile. Similar rates of preference following do not imply the same ability to meet the current task's requirements when preferences conflict with them.

cs.HC

版本更新 · v2arXiv:2609.08259

Stable Voting Rules on the Edge of Optimal Metric Distortion

Ziyi Cai, Fabian Frank, Jabari Hastings, Prasanna Ramakrishnan, Kangning Wang, Qilin Ye

原文摘要

We prove the existence of a randomized voting rule with metric distortion at most $2.1248$, within $0.013$ of the lower bound of $2.11264$. Our rule comes from a generalization of \emph{stable $k$-lotteries} developed in the context of committee selection. In contrast to prior work, our rule samples from a single distribution derived from a zero-sum game, without mixing between voting rules. Our result also gives sharp distortion bounds for stable $k$-lotteries. In particular we show that stable $2$-lotteries have distortion $7/3$, despite only relying on aggregate preferences over triples of candidates, and that stable $2$-lotteries are optimal in this class of voting rules.

cs.GT

版本更新 · v2arXiv:2610.29898

A Sharp Dynamic Haussler Lemma

Shihao Shao, Dacheng Tao

原文摘要

Haussler's covering lemma (JCTA 1995) gives the sharp $(C/δ)^d$ metric-entropy bound for binary VC classes under normalized $\ell_1$ distance. We prove a sharp global dynamic analogue for bounded real-valued classes in normalized $\ell_p$, for every $1\le p<\infty$. Writing $d=\operatorname{sfat}_{\varepsilon/32}(\mathcal F)$, we obtain a global dynamic cover of size at most $(C/\varepsilon^p)^d$ for every horizon and $0<\varepsilon<1/2$. Here a single family of deterministic causal experts, fixed independently of the instance sequence, covers every target on every sequence. For $0<\varepsilon<1/4$, a matching worst-case lower bound $(c/\varepsilon)^{pd}$ holds already for binary classes on one fixed sequence, even with real-valued experts. The constants are universal, independent of $p$. For $p=2$, this resolves the horizon-independent sequential $\ell_2$ covering problem of Rakhlin, Sridharan, and Tewari (PTRF 2015) in a stronger global form. For $p=1$, it gives the sharp $(C/δ)^{\operatorname{Ldim}(\mathcal H)}$ global dynamic covering bound for binary classes, resolving questions of Alon, Ben-Eliezer, Dagan, Moran, Naor, and Yogev (STOC 2021) and Malliaris and Moran (Trans. AMS 2024). Our proof combines rank-decreasing correction schedules and accurate sampled prefixes with exact continuations after target identification. Shared-parent routing distributes these continuations among eligible prefixes, eliminating the logarithmic overhead.

cs.LG · cs.DS

版本更新 · v2arXiv:2607.08524

Stablecoin Integration and Stress Transmission Through Crypto-Asset Service Providers: Evidence from Austria

Pietro Saggese, Michael Sigmund, Burkhard Raunig, Esther Segalla, Bernhard Haslhofer, Christos Makridis

原文摘要

Stablecoins are increasingly entangled with traditional finance, making their response to stress a financial stability concern. However, blockchain pseudonymity and the lack of geographic identifiers force existing work to rely on indirect proxies to infer and locate market participants. In this paper, we exploit a regulatory registry that directly identifies the on-chain addresses of every crypto-asset service provider (CASP) registered in Austria at the end of 2024, reconstructing their Bitcoin, Ether, USDT, and USDC activity through May 2025. Austrian CASPs intermediate roughly $30 billion in cumulative external transfers, while transfers among them are negligible. Combining two transaction-level signals, interaction with CASP cold wallets and on-chain transaction frequency, we classify CASP counterparty activity as retail-like or institutionally mediated. Around stress events, the two groups exhibit distinct flow responses that are obscured in aggregate data. After the FTX bankruptcy, we observe retail-like withdrawals and institutional deposits across assets. After Silicon Valley Bank (SVB) failure, retail-like USDC deposits and institutionally mediated withdrawals are consistent with USDC's asymmetric redemption access. Registry-based, transaction-level measurements thus offer a reproducible basis for cross-jurisdictional monitoring of how cryptoasset markets transmit risk.

q-fin.GN · cs.CR

版本更新 · v3arXiv:2610.05335

Soundness of the GKR Protocol for Sparse-Merkle Updates, with a Machine-Checked Core

Jinwook Kim

原文摘要

The GKR soundness theorem bounds the acceptance of a false output claim for a fixed circuit and input. It does not say what the outputs of a compiled circuit mean for that input, and that has to be proved for each family of circuits. For a sparse Merkle tree over a compressing hash, heuristically almost every root admits a valid path for almost any leaf, so the needed statement concerns the witness as well as the claim. We prove per-input soundness for membership, non-membership and update claims, for trees of every depth, in the delegation setting of GKR: the verifier reads the circuit input in the clear and leaves the node hashes to the circuit. Assuming correct hash sub-circuits, every accepted input, honestly encoded or not, determines a valid witness, and the chain constraint cannot be dropped. If the witness read from an input fixed before the challenges is not valid, this verifier accepts with probability at most $\bigl(s_{\mathrm{out}}+\sum_i(8s_i+1)\bigr)/|\mathbb{F}|$ for a circuit with $2^{s_{\mathrm{out}}}$ outputs and $2^{s_i}$ wires read at layer $i$. This covers cube gates for the Poseidon2 S-box and, with $|\mathbb{F}| = p^4$, circuits over the 31-bit KoalaBear field with challenges from its quartic extension. The implemented node hash, a truncated permutation, is not collision resistant, so the statement that accepted runs for one key and root assert the same leaf assumes position binding of the tree. All our results are proved in the paper. Isabelle/HOL also checks a layer-chain bound, the exactness of the verifier's checks on encoded witnesses in a constraint-level model with abstract hash sub-circuits and, over one field, their composition for claims with no valid witness. All bounds concern the interactive public-coin protocol.

cs.CR · cs.LO

版本更新 · v2arXiv:2611.02416

Fault-Free Profiles and Decision-Level Training for Root Cause Analysis via Small Language Models

Kyoohyun Lee, Woohyeok Park, Taeyoon Kim, Sungyong Baik, Kyungyong Lee

原文摘要

Root cause analysis (RCA) in microservice systems requires distinguishing failure sources from routine fluctuations and propagated symptoms. Small language models (SLMs) offer a practical solution under cost and privacy constraints, and recent approaches improve their capabilities through structured diagnostic procedures. However, performing diagnostic analysis does not ensure correct root-cause identification. Our empirical study shows that final decisions often favor large anomaly scores despite the model's own propagation analysis suggesting otherwise. Moreover, the input does not reveal whether these apparently anomalous signals are common during normal operation. These findings motivate our system, which improves how SLMs assess evidence and select root causes through Historical Frequency Profiling and Biased-Decision Correction. Historical Frequency Profiling quantifies how often metric and log signals are flagged as anomalous in the fault-free period, providing context for distinguishing routine deviations from potential failure evidence. Biased-Decision Correction identifies points where the model reaches different conclusions from the same initial analysis and uses preference optimization to favor more accurate diagnoses. Against baselines including the 14B OpsAgent and RCA-Agent with commercial models, our system with a 4B model achieves the highest or tied-highest accuracy on all four datasets, reaching 48.7% on Bank compared with 18.5% for OpsAgent.

cs.SE

版本更新 · v2arXiv:2611.02566

CR-Bench-v2: Evaluating the Real-World Utility of AI Code Review Agents

Kristen Pereira, Neelabh Sinha, Rajat Ghosh, Debojyoti Dutta

原文摘要

The rapid growth of automated code generation has created a pressing need for automated code review. Yet code review resists full automation: it depends on context beyond the \textit{diff}, on the author's intent, and on judgments about design and maintainability on which even expert reviewers disagree. Existing code review benchmarks lack standardization and rely largely on noisy human review comments scored with text-similarity metrics, which reward surface overlap and fail to measure precision. We introduce \texttt{CR-Bench}, a defect-centric evaluation framework that recasts SWE-Bench issues as pull-request review tasks with full repository context. After filtering for review-detectable defects and grounding each to a single originating pull request, \texttt{CR-Bench} contains 584 instances, with a 174-instance \texttt{CR-Bench-Verified} subset derived from SWE-Bench Verified. Each instance pairs a pull request with a known defect, its ground-truth fix, and a taxonomy label for bug category, impact, and severity. We propose two complementary metrics: \emph{Known-Defect Detection Rate} (KDDR), which measures whether an agent identifies the labeled defect, and \emph{Usefulness Rate}, which measures the fraction of review comments that are actionable. We evaluate eight code review agents over four backbones, plus commercially available Gemini Code Assist, using three independent LLM judges. Even the strongest systems detect only about one-third of known defects (KDDR $\approx$ 33\%), and Gemini Code Assist detects 8.1\%.

cs.SE · cs.LG

版本更新 · v3arXiv:2610.40000

NORmal: Architecting 3D Ferroelectric NOR Flash as Main Memory -- From Co-Fabricated BEOL Arrays to 200B-Class Multi-Agent LLMs in a Smartphone

Zhuoran Li, Zhuohang Bian, Yibo Zhao, Xuxiao Yang, Youwei Zhuo

原文摘要

Smartphone agents increasingly work as teams, in which a large planner directs parallel workers across long sessions. Running such a team on the device requires 200B-class models and contexts that exceed phone DRAM many times over, yet existing tiers treat flash as storage: UFS starves per-token weight streaming, and mobile High-Bandwidth Flash (HBF) needs a redesigned SoC and cannot absorb continuous KV writes. We show that a non-volatile memory can join an unmodified LPDDR6 bus as a plain rank only if its access latency fits the DRAM timing window, a condition no NAND tier meets. We present NORmal, to our knowledge the first main-memory architecture for 3D ferroelectric NOR flash. We have fabricated and experimentally characterized back-end-of-line (BEOL) 3D FeNOR arrays that co-integrate dense 3-bit MLC and fast, high-endurance in-place-writable SLC with sub-7.5 ns sensing. NORmal turns these co-fabricated arrays into a byte-addressable, deterministic-timing load/store rank on an unmodified LPDDR6 interface through an under-array DRAM-emulation bridge, staggered bank reads with zero-cycle weight swizzling, and posted SLC writes. Across this rank and DRAM, NORmal places agent state by mutability and lifetime rather than by hotness, serving 200B-class models and persistent planner contexts in place while dynamically partitioning subchannels across agent phases. In serving-level simulation on production agent traces, NORmal is 8.9$\times$--28.0$\times$ faster than UFS offloading, within 0.4% of an unlimited-DRAM ideal, and 2.8$\times$--6.3$\times$ faster than HBF on sessions beyond 256K tokens, with 8.1$\times$--17.8$\times$ less memory energy per token.

cs.AR

版本更新 · v2arXiv:2603.15085

Edge AI and TinyML for Resource-Constrained Agriculture: Hardware Platforms, Model Optimization, and Deployment Strategies

Riya Samanta, Bidyut Saha, Soumya Kanti Ghosh

原文摘要

Deploying artificial intelligence at the edge is increasingly important for systems that must operate under strict limits on memory, computation, energy, connectivity, and hardware cost. Tiny Machine Learning (TinyML) represents the most resource-constrained regime of this shift, enabling inference on microcontroller-class devices with tightly bounded flash and SRAM budgets. This study examines recent deployment trends in Edge AI and TinyML using precision farming as a representative real-world environment in which sensing nodes, gateways, UAVs, and embedded processors must often operate with intermittent connectivity and limited power. The analysis emphasizes the deployment stack rather than predictive accuracy alone, covering hardware classes, software toolchains, model- and system-level optimization, intelligence placement, and hardware-resource reporting. Across the analyzed studies, microcontroller-class platforms such as ESP32, STM32, and ATmega are prominent endpoint targets, while single-board computers and embedded accelerators support more compute-intensive workloads. Among the studies included in the optimization comparison, almost 50% report quantization, making reduced-precision inference the most frequently identified strategy within this subset. In contrast, structured pruning, hardware-aware neural architecture search, and coordinated cross-layer optimization remain comparatively limited. Resource profiling is also inconsistent as flash, peak RAM, MAC count, latency, and energy per inference are not reported uniformly, limiting reproducibility and comparisons across deployments. A recurring systems-level pattern is an inference-training asymmetry in which inference moves toward local devices while training and model lifecycle management remain predominantly centralized.

cs.ET · cs.LG

版本更新 · v2arXiv:2610.10571

SPERA: Spherical Prior EEG Foundation Model with Geometry- and Frequency-Aware Latent Prediction

Minsu Kim, Ye-Sung Kim, Hyeseong Jeon, Wooseok Hyung, Joshua Lee, Chang-Hwan Im

原文摘要

Electroencephalography (EEG) provides a non-invasive measure of ongoing neural activity, but building general-purpose EEG models remains challenging due to the heterogeneity of subjects, devices, and electrode montages. Existing EEG foundation models predominantly rely on reconstruction-based objectives defined on the observed signal, which contains both neural and non-neural components. We introduce the Spherical Prior EEG Representation Architecture (SPERA), an EEG foundation model that adopts the joint-embedding predictive architecture (JEPA) to predict in latent space. SPERA introduces a Legendre-polynomial spatial prior, incorporated into attention to encode varying scalp electrode geometries. Two further components adapt the model to EEG: factorized temporal and spatial attention interleaved with periodic full-attention blocks, and a relational spectral regularizer aligning latent similarity structure with spectral views. Pretrained on approximately 80,000 hours of EEG from 29,048 subjects across 106 datasets, SPERA achieves the highest average balanced accuracy across nine downstream tasks spanning clinical, cognitive, and BCI applications. SPERA further exhibits strong parameter efficiency under linear probing and robustness across varying recording conditions, suggesting its potential as a general-purpose backbone for diverse EEG analyses.

cs.LG

版本更新 · v2arXiv:2609.20687

The First-Order Oracle Complexity of Lipschitz Convex Optimization in Nondual Settings

Brian Bullins, Cristóbal Guzmán, David Martínez-Rubio, Mathieu Molina

原文摘要

We study first-order black-box convex optimization over an $\ell_p$-ball for objectives Lipschitz in the $\ell_q$-norm, solving in the affirmative the nonsmooth version of the COLT open question (Guz15b) on whether the geometry of a smaller feasible set ($p < q$) can improve convergence rates in convex optimization, and matching prior lower bounds up to logarithmic factors. Our rates include $\widetilde{O}(1/T)$ for convex Euclidean-Lipschitz optimization over the $\ell_1$-ball, improving on the $O(1/\sqrt{T})$ classical rate under general assumptions. The key technical device is a new online learning game, where the comparator is evaluated using the maximum of affine losses observed so far. We bound the value of this game above and below in terms of a combinatorial online learning quantity: the sequential fat-shattering dimension, which we characterize for the $\ell_p / \ell_q$ case. Our results generally apply when the feasible set $\mathcal{X}$ and the set of possible subgradients $\mathcal{H}$ admit a type of minimax theorem, advancing on a fundamental question by Sridharan (Sri12, Section 10.1.2, Q3). As a geometric consequence of our analysis, of independent interest, we obtain estimates for the expected distance of a convex hull of samples to their mean in several Banach geometries, a version of the celebrated Wendel's theorem (Wen62), but quantitative and for bounded general distributions as opposed to centrally symmetric ones.

math.OC · cs.LG

版本更新 · v2arXiv:2610.16312

Narrative Paradoxes in LLM Inference: Shaping Reasoning Trajectories toward Misalignment

Haoming Yang, Ke Ma, Yangbangyan Jiang, Ligong Zhang, Xiaojun Jia, Longtao Huang, Yingfei Sun, Qianqian Xu 等 9 位作者

原文摘要

Explicit reasoning in large language models (LLMs) is often associated with reliability, yet it can still pose risks when a model infers harmful goals under a benign context. We identify a distinct challenge: ensuring the safety of the \emph{multi-step reasoning process} itself, where locally coherent steps may still lead to globally harmful outcomes. To explore this vulnerability, we propose PDRA (Paradox-driven Reasoning-based Attack), a novel attack method that programs a harmful reasoning trajectory. PDRA first constructs a paradoxical narrative core by pairing a malicious actor (e.g., a terrorist) with a benign task (e.g., writing a safety bulletin). It then embeds this core into a structured analytical framework that forces the model through a mandatory three-stage analysis -- surface purpose, latent intent, and operational reconstruction -- guiding it to produce detailed harmful content while maintaining narrative coherence. Mechanistically, we show PDRA steers the model's internal representations away from refusal-related patterns, suppressing safety-triggering lexicons while activating planning-oriented terms. Empirically, PDRA achieves state-of-the-art attack success rates across diverse LLMs with high efficiency. \textcolor{red}{\textbf{Warning:} This paper may contain sensitive content.}

cs.AI