跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

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

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+2已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-08 10:17 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 11:33 — 2026-11-08 11:33（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-08 10:17最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 02:59

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

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

浏览论文库

研究日报 / 周报 →按信源浏览 →

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

找到 17,100 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 10:15（北京时间）
版本更新 · v2arXiv:2606.05138

Generating Financial Time Series by Matching Random Convolutional Features

Konrad J. Mueller, Nikita Zozoulenko, Ben Wood, Thomas Cass, Lukas Gonon

原文摘要

Generating realistic financial time series is challenging as training data is often limited to a single historical path. With such scarce data, overfitting is hard to avoid, especially under adversarial training where a trained discriminator can memorize the training samples. To mitigate this, recent approaches train generators to minimize the discrepancy between untrained feature representations of real and generated time series. In these works, the feature maps are based on path signatures, which can fail to capture relevant time series properties at tractable truncation depths. In this work, we instead train generators by matching random convolutional features of real and generated time series. Existing random convolutional feature maps, such as Rocket and Hydra, have been shown to provide informative representations of real-world time series, but cannot supervise generative models because they are non-differentiable. We introduce SOCK (SOft Competing Kernels), a fully differentiable random convolutional feature map, suited to train generative time series models. We show that generators trained by matching random SOCK features outperform signature and diffusion baselines on most evaluation metrics across a wide range of small-sample financial datasets. We further demonstrate SOCK's expressiveness on two-sample hypothesis testing and time series classification tasks, where SOCK matches or outperforms existing unsupervised feature maps.

cs.LG · q-fin.ST

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03586

FedReady: Bounded Agents for Federation Formation

Ziyue Xu, Holger R. Roth, Chester Chen, Peter Cnudde

原文摘要

Federated learning (FL) runtimes standardize aggregation and deployment, but each new study still requires federation formation: selecting task-eligible sites and preparing their local data and task code for federated training or analysis. This preparation recurs when the target changes, while raw records and site-private mappings are excluded from cross-site FL messages. We present FedReady, a system that performs federation formation with bounded LLM agents. Agents propose shared contracts, local adapters, and task code; the runtime owns workflow state and accepts artifacts only after checks tied to their digests. Candidate site discovery prioritizes recall; local eligibility verification checks task support before site admission. Once participating sites and artifacts are fixed, conventional federated training or analysis proceeds without readiness agents. Across 39 simulated retinal sites and four tasks, discovery reaches recall 1.00 at precision 0.65; local eligibility verification removes all 17 false positives without losing an eligible site-task pair. The participating sites supply 45,575 task-record instances and complete four 100-round jobs, including one with a runtime-generated contract. Across ten patient cohorts, preparation supports seven patient populations and holds endpoints at three sources as unsupported. Comparison with manually prepared reference populations and analysis (the manual reference) gives a maximum survival-curve difference of 0.001133. We also analyze 19 development failures, targeted classification ablations, and standalone and heterogeneous agent configurations. These results establish the feasibility of task-specific data preparation before ordinary FL training or analysis.

cs.AI · cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03584

TAMPAgent: Agentic Belief-Space Planning for Mobile Manipulation

Utkarsh A. Mishra, Alperen Degirmenci, Yongxin Chen, Danfei Xu, Tucker Hermans, Caelan Garrett

原文摘要

Open-world robotic mobile manipulation requires acting in physical environments with only partial information. While recent Large Vision-Language Model (LVLM) agents show strong open-world reasoning capabilities, existing architectures that rely on direct tool calling struggle with geometric uncertainty and thus are limited to fully-observable tabletop environments. In contrast, Task and Motion Planning (TAMP) systems can solve long-horizon tasks under partial observability but incur high computational costs and require closed worlds. We propose \textbf{TAMPAgent}, an agentic planning framework that unifies the reasoning of LVLMs with the structured constraint satisfaction of TAMP systems. We endow an LVLM agent with a belief-space planning model operating over an extensible API of perception, planning, and control tools. The agent formulates a partial task plan composed of parameterized observation and execution actions, which is subsequently completed using classical search algorithms. After extracting the plan's geometric constraints, the agent leverages its tool API to bind valid parameter values, satisfying feasibility requirements and producing an executable motion plan. Upon execution, the agent continuously updates its belief history and repeats this closed-loop process by interleaving observation and manipulation actions. Evaluated across complex household mobile manipulation tasks on Rainbow Y1 and Unitree G1 platforms, TAMPAgent significantly outperforms direct tool-calling agentic baselines, demonstrating that integrating TAMP constraint satisfaction into agentic planning loops is essential for unstructured, partially observable environments.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03585

Seeing Through the Illusion: Test-Time Scaling for World Action Models

Cheikh Ahmed, Mahdi Mostajabdaveh, Milad Yazdani, Zirui Zhou

原文摘要

World action models (WAMs) jointly generate actions and imagined futures, but a plausible prediction need not be realized by its co-generated action. We introduce WISE (\emph{World Action Inference Scaling through Evaluation}), a pre-execution selector that scores each sampled rollout on action validity and temporal regularity, inverse-dynamics consistency between the proposed action and the imagined motion, and instruction-conditioned task progress, and executes the highest-scoring candidate while keeping the WAM frozen. With four candidates per decision, WISE raises closed-loop success from 6.0\% to 24.0\% on RoboLab with Cosmos~3 Edge and from 75.1\% to 78.3\% mean success on LIBERO with DreamZero, and exceeds the best existing selector in aggregate by 4.0 and 0.9 points. Component ablations and agreement analyses show that the three scores rank candidates differently and that task progress carries the largest weight in the fused decision.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03579

An Almost-tight Size Lower Bound for Bounded Treewidth Homomorphism-Distinguishability

Moritz Lichter, Harry Vinall-Smeeth

原文摘要

One way to compare two graphs $G_1, G_2$ is to check whether there is some graph $H$ in a graph class $\mathcal{H}$, such that the number of homomorphisms from $H$ to $G_1$ is not equal to that from $H$ to $G_2$. This is the field of homomorphism distinguishability which has gained a lot of traction in recent years. In this paper, we study the case where $\mathcal{H}$ is the class of graphs of treewidth $k$. This has connections to important concepts in logic, machine learning, combinatorial optimization and proof complexity. In particular, Dvořák showed that $G_1$ and $G_2$ can be distinguished by a homomorphism count from a graph of treewidth $k$ iff $G_1$ and $G_2$ are distinguishable by the $k$-dimensional Weisfeiler-Leman algorithm. While the relation between the iteration number of this algorithm and the depth of the tree-decomposition of a distinguishing graph is understood, our understanding of the \emph{size} of $H$ is limited. We show a $2^{Ω(n^{k/2})}$ lower bound on the size of a graph of treewidth $k$ required to distinguish two graphs of order $n$. This bound is proved via a new combinatorial game along with a construction which uses a recent compression technique for CFI graphs. It is almost tight to the known $2^{O(n^{k+1})}$ upper bound and is an exponential improvement on the previous best known lower bound.

cs.DM

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2601.09859

Tune-Up Open-Weight CLIP: Optimization Framework for Self-Supervised Fine-tuning of CLIP

Anant Mehta, Xingyu Chen, Xiyuan Wei, Tianbao Yang

原文摘要

CLIP has become a cornerstone of multimodal representation learning, yet improving its performance typically requires a prohibitively costly process of training from scratch on billions of samples. We ask a different question: Can we improve the performance of open-weight CLIP models across various downstream tasks using only existing self-supervised datasets? Unlike supervised fine-tuning, which adapts a pretrained model to a single downstream task, our setting seeks to improve general performance across various tasks. However, as both our experiments and prior studies reveal, simply applying standard training protocols starting from an open-weight CLIP model often fails, leading to performance degradation. In this paper, we introduce TuneCLIP, a self-supervised fine-tuning framework that overcomes the performance degradation. TuneCLIP has two key components: (1) a warm-up stage of recovering optimization statistics to reduce cold-start bias, inspired by theoretical analysis, and (2) a fine-tuning stage of optimizing a new contrastive loss to mitigate the penalization on false negative pairs. Our extensive experiments show that TuneCLIP consistently improves performance across model architectures and scales. Notably, it elevates leading open-weight models like SigLIP (ViT-B/16), achieving gains of up to +2.5% on ImageNet and related out-of-distribution benchmarks, and +1.2% on the highly competitive DataComp benchmark, setting a new strong baseline for efficient post-pretraining adaptation. The code is available at https://github.com/Optimization-AI/TuneCLIP.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03578

Uniform Sampling of Linear Codes with Prescribed Hull Dimension

Keita Ishizuka

原文摘要

We give exactly uniform samplers for linear codes with prescribed hull dimension, for the Euclidean, Hermitian, and symplectic inner products and over finite fields of every characteristic. Except for the Euclidean form over fields of odd characteristic, these are the first uniform samplers for arbitrary prescribed hull dimension. Each sample costs an expected $O(k^2 N + k \log q)$ field operations for codes of dimension $k$ in a space of dimension $N$ over $\mathbb{F}_q$ or $\mathbb{F}_{q^2}$.

cs.IT · math.CO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.10446

Subset Sum via Partial Match

Baitian Li, Lixi Ye

原文摘要

We show that the subset sum problem can be solved in randomized time $O(2^{0.49999\overline{7}n})$, breaking the $2^{n/2}$ meet-in-the-middle barrier. Our approach builds on the representation technique framework of Randolph and Węgrzycki (STOC 2026). We choose a representation for which testing the compatibility of pairs of partial solution vectors is exactly the partial match problem. To beat exponent $1/2$ for subset sum, it then suffices to give a nontrivial partial match algorithm in a certain parameter regime. We achieve this by designing a depth-2 linear circuit for the partial match matrix, which yields an efficient algorithm via the framework of Alman and Li (FOCS 2025).

cs.DS · cs.CC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.42112

Subquadratic Attention with a Hierarchical Tree-Structured Indexer

Leon Lufkin, Cutter Dawes, Alexander Speicher, Kamesh Krishnamurthy, Tomás Figliolia, Beren Millidge

原文摘要

The quadratic scaling of attention is a fundamental bottleneck limiting the long-context capabilities of large language models (LLMs). A variety of approaches have attempted to circumvent this, but they either fail to match attention's expressiveness (e.g., sliding-window or linear attention variants with fixed-size state) or only achieve constant-factor speedups (e.g., sparse attention methods whose indexers themselves scale quadratically). In this paper, we derive an asymptotically subquadratic sparse attention method based on a hierarchical, tree-structured indexer, which we call Zyphra Hierarchical Attention (ZHA). ZHA constructs a tree of recursively compressed key summaries over the KV cache, which future queries traverse from the top down to retrieve a sparse subset of keys. Crucially, by iteratively growing the tree's depth, the total cost including routing and final attention grows sublinearly in sequence length, resulting in overall subquadratic (but superlinear) scaling for attention. We demonstrate that ZHA can be cheaply applied to existing pretrained models with only a short KL distillation training stage of a billion tokens, and maintains performance on long-context retrieval and challenging reasoning, mathematical, and agentic coding evaluation tasks. Moreover, we show that our method is highly robust to tree geometry including very deep trees of up to 6 levels. Finally, we develop a detailed performance model and show that our approach scales subquadratically, dramatically outperforms competing methods beyond 1 million tokens of context, and ultimately has the potential to extend effective context windows to the hundreds of millions or billions of tokens.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03575

VeriHarm-Bench: Measuring Harmful Success in LLM Coding Agents Verifiably

Wei-Lin Chen, Zhepei Wei, Xinyu Zhu, Yu-Min Tseng, Tzu-Han Lin, Yu Meng

原文摘要

Large language model (LLM) coding agents increasingly operate with shell access, allowing them to write scripts, move files, alter permissions, and modify system configurations. However, an agent may achieve a user's goal while causing unintended harm, such as deleting unrelated files, weakening access controls, or corrupting data, in response to benign inputs without explicit jailbreaking. This failure mode is particularly important because apparent task success may reassure users that an agent behaved correctly, causing harmful side effects to go unnoticed. We call this harmful success: the agent successfully completes the intended benign task while simultaneously causing unintended harm. Despite its importance, harmful success is difficult to measure because conventional task-success metrics overlook harmful behaviors, while existing safety evaluations are often designed solely to assess harmful outcomes. We introduce VeriHarm, an automatic framework for constructing programmatically verifiable benchmarks that directly measure harmful success. VeriHarm minimally perturbs coding tasks to elicit unintended harmful behavior while maintaining the benignity of the task and preserving the original task objective. It then synthesizes executable harm tests that, together with the original task-correctness tests, evaluate both task accuracy and harmful outcomes. Frontier agents, including GPT-5.6-Sol and Claude-Opus-5, achieve an average task accuracy of 95% on our curated VeriHarm-Bench, yet still struggle to complete tasks safely: their safe success rate, the fraction of tasks completed successfully without triggering the designated harm, averages only 37%. These results suggest that successful task completion can frequently coexist with unintended harm, and that task-success metrics alone may substantially understate the potential safety risks of coding agents.

cs.CL · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03574

BISECT: Bilevel Spectral Decomposition for Low-Rank Continual Learning

Tom Saliencro, Wen-Hsuan Liu, Rohan Desai, Amara Okonkwo, Maya Lindqvist

原文摘要

Exemplar-free continual learning on pre-trained Vision Transformers increasingly relies on Low-Rank Adaptation (LoRA), yet prevailing methods govern the low-rank update space through strict subspace isolation. By projecting each incoming task into the approximate null space of historical token activations, isolation-based learners equate any cross-task feature overlap with catastrophic interference. We show that this orthogonality premise induces a structural bottleneck we term \emph{spectral starvation}: when down-projection bases are locked before task optimization, the gradient norm reaching the trainable up-projection is upper-bounded by the energy of current-task features captured by the chosen basis. Because natural visual tasks share low- and mid-level covariance structure, historical null tails contain barely $5.5\%$ of incoming task variance, starving new-class plasticity while blocking positive consolidation along shared directions. We propose BISECT (Bilevel Spectral Decomposition), a continual LoRA framework that partitions a fixed rank-$r$ budget into two orthogonal functional blocks: an invariant carrier spanned by the dominant modes of the joint historical-and-current Gram matrix, and a novelty complement extracted via generalized Rayleigh whitening followed by orthogonal complement projection. After single-task training, BISECT folds both blocks back into the frozen backbone using a closed-form precision gate that scales each rank-1 invariant atom by its current-to-joint Rayleigh ratio while preserving novelty atoms at unit gain. Across eight incremental settings on ImageNet-R, ImageNet-A, CIFAR-100, CUB-200, and DomainNet, BISECT outperforms prompt, adapter, and LoRA baselines with zero extra inference parameters or FLOPs, and remains complementary to sparse analytic expansion.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.10052

OmniGuide: Universal Spatial Guidance Fields for Enhancing Generalist Robot Policies

Yunzhou Song, Long Le, Yong-Hyun Park, Jie Wang, Junyao Shi, Lingjie Liu, Jiatao Gu, Eric Eaton 等 10 位作者

原文摘要

Vision-language-action (VLA) models have shown great promise as generalist policies for a large range of relatively simple tasks. However, they demonstrate limited performance on more complex tasks, such as those requiring complex spatial or semantic understanding, manipulation in clutter, or precise manipulation. We propose OmniGuide, a flexible framework that improves VLA performance on such tasks by leveraging arbitrary sources of guidance, such as 3D foundation models, semantic-reasoning VLMs, and human pose models. We show how many kinds of guidance can be naturally expressed as differentiable energy functions with task-specific attractors and repellers located in 3D space, that influence the sampling of VLA actions. In this way, OmniGuide enables guidance sources with complementary task-relevant strengths to improve a VLA model's performance on challenging tasks. Extensive experiments in both simulation and real-world environments, across diverse sources of guidance, demonstrate that OmniGuide enhances the performance of state-of-the-art generalist policies (e.g., $π_{0.5}$, GR00T N1.6) significantly across success and safety rates. Critically, our unified framework matches or surpasses the performance of prior methods designed to incorporate specific sources of guidance into VLA policies. Project page: https://omniguide.github.io/

cs.RO · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.20406

Thinking in Different Spaces: Domain-Specific Latent Geometry Survives Cross-Architecture Translation

Marcus Armstrong, Navid Ayoobi, Arjun Mukherjee

原文摘要

We investigate whether independently trained language models converge to geometrically compatible latent representations, and whether this compatibility can be exploited to correct model behavior at inference time without any weight updates. We learn a linear projection matrix that maps activation vectors from a large teacher model into the coordinate system of a smaller student model, then intervene on the student's residual stream during generation by substituting its internal state with the translated teacher representation. Across a fully crossed experimental matrix of 20 heterogeneous teacher-student pairings spanning mixture-of-experts, dense, code-specialized, and synthetically trained architectures, the Ridge projection consistently achieves R^2 = 0.50 on verbal reasoning and R^2 = 0.40 on mathematical reasoning, collapsing to R^2 = -0.22 under permutation control and R^2 = 0.01 under L_1 regularization. Behavioral correction rates range from 14.0% to 50.0% on TruthfulQA (mean 25.2%) and from 8.5% to 43.3% on GSM8K arithmetic reasoning (mean 25.5%), demonstrating that the method generalizes across fundamentally different reasoning domains. We report a near-zero correlation between geometric alignment quality and behavioral correction rate (r = -0.07), revealing a dissociation between representation space fidelity and output space impact. Intervention strength is architecture-specific: student models exhibit characteristic sensitivity profiles that invert across domains, with the most steerable verbal student becoming the least steerable mathematical student. Finally, a double dissociation experiment conducted across all 20 model pairings confirms without exception that projection matrices collapse catastrophically when transferred across reasoning domains (mean R^2 = -3.83 in both transfer directions), establishing domain-specific subspace geometry as a universal property of LMs.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.34556

Admissible sets of integers in imaginary quadratic fields of class number 1

Daniel Shiu

原文摘要

Let $\mathcal O_K$ be the ring of integers of a number field $K$. A finite subset $\mathcal H=\{η_1,\ldots,η_k\}\subset\mathcal O_K$ is said to be \emph{admissible} if for every prime ideal $\mathfrak p$ in $\mathcal O_K$, the reductions of the $η_i$ modulo $\mathfrak p$ do not represent every residue class. The diameter of a finite subset $S$ of $\mathcal O_K$ is defined to be \[\mathrm{diam}(S):= \max_{η_i,η_j\in S:η_i\neqη_j}|\mathcal N(η_i-η_j)|\] where $\mathcal N$ denotes the norm down to the rational field. This paper computationally investigates admissible subsets of rings of integers in imaginary quadratic fields of class number 1 (such as the Gaussian integers or the Eisenstein integers) that are large relative to their diameter. The motivation is twofold. Firstly, there is the improvement of results analogous to the question of an upper bound for the least gap between large rational primes, which has been one of the great number theoretic successes of the twenty-first century. A second motivation is that there is the opportunity to disprove a variation of the second Hardy-Littlewood conjecture. The calculations in the paper provide new records on the smallest distance between primes in the fields in question, and explicit counter-examples to a generalisation of the second Hardy-Littlewood conjecture in all bar one of the fields.

math.NT · cs.DM

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.11425

JailbreakOPT: Iterative Jailbreak Prompt Optimization with Macro-Action

Ge Shi, Jun Yin, Donglin Xie, Fangyi Liu, Yucan Li, Menglin Liu

原文摘要

Jailbreak attacks expose persistent safety weaknesses in large language models (LLMs), but existing stateless single-turn methods face a trade-off: hand-crafted prompts are expressive but static, while iterative prompt optimization can adapt but often relies on low-level mutations that require many target-model responses. We propose JailbreakOPT, a method that maintains a library of reusable prompt transformations (actions) and composes them into macro-actions for within-episode search, generating standalone attack prompts. To reuse experience across episodes, JailbreakOPT learns an action-selection policy using contextual Thompson sampling and outcomes from prior search paths. Experiments across multiple LLMs and benchmarks show that JailbreakOPT improves attack success rate (ASR) over single-action and iterative baselines. More broadly, exploration and exploitation over human-designed attack strategies can help probe residual vulnerabilities and identify failure patterns that may inform defenses aimed at broader classes of attacks.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.04858

Integer points close to a transcendental curve: an algorithmic approach

Nicolas Brisebarre, Guillaume Hanrot

原文摘要

In this article, we propose an algorithmic approach to determine the integer points located near a transcendental curve. This approach is closely related to a celebrated work by Bombieri and Pila and to the so-called Coppersmith's method. We establish the underlying theoretical foundations, prove the algorithms, study their complexity and present practical experiments; we also compare our approach with previously existing ones. From a practical point of view, we focus on an instance of our general problem, called the Table Maker's Dilemma, whose solving makes it possible to evaluate a given function with correct rounding. Our experiments show a significant speedup. In particular, our results show that the development of a correctly rounded mathematical library for the binary128 format is now possible at a much smaller cost than with previously existing approaches.

math.NT · cs.SC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03558

Quantum Private Information Retrieval on Forests

Mohamed Nomeir, Sennur Ulukus

原文摘要

We consider the problem of graph private information retrieval (PIR) in the quantum setting. We focus on a specific type of graphs, namely the forest graphs. A forest graph is a union of disjoint trees. We consider the quantum setting where all the servers share an entangled state. Each server is allowed to send only one qudit per retrieval round. We design a scheme for the forest graphs that achieves the rate of $\frac{3}{N}$. The scheme uses a GHZ state as the initial entangled state between the servers prior to the scheme initiation. We compare our scheme with the only work done in the literature that considered the quantum setting of graph PIR. We show that our scheme is more efficient in this setting. We derive the quantum capacity for the case of $G=3K_2$, which is equal to $4/6$. $G=3K_2$ is a special case of the forest graph. We design a scheme that is specialized for this graph, achieving a rate equal to $4/6$ and provide the corresponding matching upper bound, establishing it as the capacity.

cs.IT · cs.CR · cs.NI · eess.SP · quant-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03557

PlantVLM-Edge: Quantized Vision-Language Models for On-Device Crop Health Diagnosis

Gaurab Wagle, Bishal Adhikari, Jiajia Li, Xiaolei Huang, Dong Chen

原文摘要

Timely and accurate crop health diagnosis is essential for sustainable agricultural production, yet accurate diagnosis often requires expert knowledge that is not readily available. Recent vision-language models (VLMs) have demonstrated remarkable capabilities in visual understanding, reasoning, and natural-language interaction, creating new opportunities for intelligent crop health assessment. However, deploying VLMs on resource-constrained devices remains challenging due to their substantial computational and memory requirements. This paper presents PlantVLM-Edge, a quantized vision-language framework for conversational crop health diagnosis that can run entirely on resource-constrained edge devices. PlantVLM-Edge combines agricultural domain adaptation, post-training quantization, and on-device serving with an offline chat interface, allowing growers to ask open-ended questions and receive diagnoses, symptom explanations, and management guidance without cloud connectivity. The framework is backbone-agnostic: we validate it with two different VLM types with varying scale and architecture (Qwen3-VL-2B and LLaVA-1.5-7B), four quantization schemes, and two diagnostic domains (plant diseases and insect pests), and we deploy all variants on an NVIDIA Jetson AGX Orin. Eight-bit quantization affects answer quality minimally relative to the full-precision model, and 4-bit activation-aware weight quantization (AWQ) retains 98.6% of full-precision answer quality on both domains while reducing the weight memory of the 2B backbone by 49%. In its most compact form, PlantVLM-Edge requires 2.01 GiB of weight memory, returns its first token in about 0.12 s, and completes a 64-token diagnostic response in 0.78 s. These results demonstrate that timely and accurate crop health diagnosis is practical on edge devices, providing a foundation for next-generation crop monitoring and decision support systems.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03555

MCP Tool Poisoning in Agentic AI Frameworks: A Cross-Framework Measurement Study

Farooq Shaikh, Biagio Montaruli

原文摘要

The Model Context Protocol (MCP) lets agentic AI frameworks connect language models to external tool providers, but it carries attacker-controlled content (tool descriptions, schema fields, and response data) into model context without validation. Prior benchmarks measure model compliance with poisoned instructions without confirming real execution. We present the first cross-framework measurement of MCP tool poisoning with real tool execution. A 25-class root-cause taxonomy unifies prior classifications, and the open-source tool mcpvenom drives a 9,720-cell susceptibility matrix across 12 frameworks, 18 models, and 45 attack scenarios, with a dual oracle that confirms exfiltration via canary HTTP receipt. The overall attack success rate is 22.9% (2,113 vulnerable cells). Of these, 64.9% dispatch an attacker tool call, 23.0% contact the attacker endpoint, and 12.1% verifiably exfiltrate a secret. Resistance is model-level: nine core frameworks cluster within 23 to 26% (chi-squared = 3.30, p = 0.91), and no framework implements intentional defense. Incidental framework properties mitigate in specific cases, and a regex description scanner rejects 20 of 45 scenarios at a 7.2% false-positive rate, so metadata scanning alone is a partial control. Model ASR ranges from 0.4% to 49.7%. Claude Opus 4.8 is vulnerable in 8 of 530 cells while issuing 223 explicit refusals. A code-level audit finds no intentional defense across twelve frameworks, and all five coordinated disclosures across four vendors were rejected.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03554

Determinant boundaries and gaps in determinantal complexity

Karthik Sheshadri

原文摘要

Landsberg, Manivel, and Ressayre constructed determinant-boundary components whose defining forms, for odd n >= 3, are limits of n x n determinants but cannot themselves be represented by determinants of that size. Their border determinantal complexity (DC) is therefore smaller than their exact DC. We prove that the difference can grow linearly with n. For every n >= 10, we construct an explicit homogeneous form of degree n, concise in n^2 variables, whose orbit closure is a boundary component, whose border DC is n, and whose exact DC is at least 2n - 1. Thus n rows suffice when limits are allowed, whereas every exact representation requires at least 2n - 1 rows. The same bound holds for the unpadded odd-skew forms at every odd n >= 3. We also prove that every concise degree-n boundary form in n^2 variables has exact DC at least n + 2. We construct three families of pairwise distinct boundary components. Together with the traceless determinant, they give at least floor((n-1)/2) + floor(n/3) components for every n >= 3, with an additional term counted explicitly in the paper. The main lower bound follows from a general degree lemma. If an affine matrix represents an irreducible homogeneous polynomial f of degree d and has globally free rank-one cokernel over the coordinate ring of f = 0, its size is at least 2d - 1. The adjugate factors into two nonzero kernel vectors, each requiring a coordinate of degree at least d - 1. Comparing their product with the degree of a cofactor proves the bound. The lemma is sharp for individual representations, as witnessed by algebraic branching programs. Whether the exact-versus-border gap can grow superlinearly remains open.

cs.CC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.09481

TSNBench: Benchmarking LLM Proficiency in Time-Sensitive Networking

Rubi Debnath, Daniel Bujosa Mateu, Luxi Zhao, Silviu S. Craciunas, Paul Pop, Sebastian Steinhorst

原文摘要

We present TSNBench, the first benchmark for evaluating large language model (LLM) proficiency in Time-Sensitive Networking (TSN), a suite of IEEE 802.1 standards for deterministic communication with bounded latency in safety-critical domains such as autonomous vehicles, aviation, defense, and industrial automation. While LLMs have been extensively evaluated on general knowledge tasks, their capabilities in safety-critical networking domains remain largely unexplored. TSNBench comprises 939 expert-validated multiple-choice questions (MCQs) covering diverse TSN mechanisms, along with 100 open-ended Worst-Case Delay (WCD) computation tasks for each of Credit-Based Shaper (CBS) and Cyclic Queuing and Forwarding (CQF), across varying topologies and traffic flows. The ground-truth (GT) WCD values are computed using a verified Network Calculus (NC) solver for CBS and closed-form upper bounds for CQF. We evaluate 16 LLMs and find that although models achieve 67 to 95% accuracy on MCQs, they fail substantially on open-ended WCD computation. For CBS, the best-performing model, GPT-5, deviates from the GT by 150.2 $μ$s on average (mean absolute error, MAE), and its predicted WCD is within 50 $μ$s of the GT for only 39.4% of flows, while all other models exceed an MAE of 250 $μ$s. Providing the WCD equations in the prompt lowers the error for 9 of 10 models on CQF but only 2 of 9 on CBS. Such errors are large relative to TSN latency budgets and can lead to violations of real-time constraints and unsafe configurations. TSNBench demonstrates that MCQ benchmarks may overestimate LLM capabilities in safety-critical networking.

cs.NI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03552

Nonparametric Intensity Estimation for Covariate-Driven Poisson Processes Using Deep Learning

Atsutomo Yara, Yoshikazu Terada

原文摘要

We consider nonparametric maximum likelihood estimation of the intensity function of a Poisson process, allowing the intensity to depend on observed covariates. Such models describe how event rates vary with external conditions, including conditions under which the intensity becomes arbitrarily small or vanishes. However, risk analysis based on the Kullback-Leibler (KL) divergence typically requires the true intensity to be bounded away from zero, a restrictive assumption in applications. We develop a unified approach that avoids this assumption and derive an oracle inequality for the covariate-averaged Hellinger distance between the true intensity and the nonparametric maximum likelihood estimator (NPMLE). As an application of the oracle inequality, we establish convergence rates for NPMLEs based on deep neural networks (DNNs). Our results show that, as in nonparametric regression, the ability of DNNs to capture underlying structure leads to improved convergence rates. Specifically, DNN-based NPMLEs mitigate the curse of dimensionality when the true intensity has a compositional structure and automatically adapt to a low-dimensional Riemannian manifold structure of the event space. For intensity functions with a compositional structure, DNN-based NPMLEs achieve nearly minimax-optimal convergence rates without explicitly incorporating this structure into the network architecture. Simulations demonstrate that DNN-based estimators outperform kernel estimators in most settings, while manifold kernels remain competitive in some designs. Finally, we analyze stimulus-evoked neural spiking using data from the Allen Brain Observatory Visual Coding Neuropixels project. DNN-based NPMLEs provide better out-of-sample performance than a conditional kernel estimator, as evaluated by held-out log-likelihood.

math.ST · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03551

Can LLM Agents Be Forward-Deployed Engineers? Requirement Discovery and Delivery for Enterprise Text-to-SQL

Marianne Menglin Liu, Rongguang Wang, Zheng Wang, Yewen Wang, Leonid Boytsov, Tao Sheng, Sujith Ravi, Dan Roth

原文摘要

LLM coding agents can increasingly automate model post-training, but whether they can act as forward-deployed engineer (FDE) agents, discovering customer requirements and turning them into deployment decisions, remains unclear. We study this on a real enterprise text-to-SQL engagement: a simulated customer, grounded in the real use case's requirements, starts with an ambiguous request. An agent must discover acceptance criteria, data permissions, and hardware constraints in the discovery phase, then plan and execute a post-training recipe in the delivery phase. Across 15 models, the strongest discover over 80% of withheld requirements and open-weight models discover 40-50%; in the delivery phase, only 25% of runs across eight coding-agent configurations pass all acceptance criteria. We identify four bottlenecks in this engagement: (1) incomplete discovery, with 40% of withheld requirements missing or misrepresented; (2) unreliable execution; (3) underused compute budgets and a lack of systematic comparisons across base models and post-training methods; and (4) benchmark accuracy does not guarantee production readiness. We suggest human review of discovered requirements, monitoring of the agent's plan during execution, and an explicit experiment-environment specification covering hardware, budget scope, and production checks.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.38277

The Role of Quantization in Loss Spikes

Zaiqian Chen, Aditya Somasundaram, Sophie Li, Sean McLeish, John Kirchenbauer, Tom Goldstein, Micah Goldblum

原文摘要

Loss spikes in language model pretraining can waste substantial compute and derail otherwise healthy training runs. A primary driver of these instabilities is the growth and divergence of output logits in the final language modeling (LM) head. In this work, we study a particularly costly form of this instability associated with output logit growth: delayed, terminal divergences that emerge only after prolonged training, which we call time-bomb spikes. We find that these instabilities are preceded by rapidly growing quantization error in the LM head, which eventually culminates in a loss spike. Crucially, reducing numerical precision accelerates time-bomb spikes, while increasing precision improves stability. We then propose a simple yet effective mitigation that replaces AdamW on the LM head with SGD with momentum, suppressing logit growth and improving stability over long training horizons. Finally, we find that existing mitigation techniques from the literature (along with our own) all reduce quantization error, suggesting a shared numerical mechanism behind their effectiveness. Together, our results identify finite precision error as a hidden driver of time-bomb spikes and show that suppressing this error is key to stable long-horizon pretraining.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03548

Mediating Human-Swarm Interactions Through a Robot Helper: A Shepherding-Inspired Approach

Arihant Yadav, Sophie Jörg, Eakta Jain

原文摘要

This work investigates human-swarm interaction (HSI) for steering large collectives through an intermediary robot helper. While prior robot-swarm control and HSI techniques commonly assume swarm members are addressable, these assumptions often fail for ``ungovernable'' swarms such as wildlife flocks and schools of fish. Motivated by pastoral shepherding, we compare low-level teleoperation to a higher-autonomy motion-primitives interface in a virtual reality (VR) shepherding task under varied swarm cohesion dynamics. Results indicate that motion primitives that operate on collective shape (e.g., boundary-based control) improve task performance and reduce perceived workload.

cs.RO · cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03547

Exact Sum-of-Radii Clustering under Any Constant Stability

Shyam Ravichandran, Lev Reyzin

原文摘要

We establish a separation between the stability thresholds of Minimum Sum-of-Radii (MSR) clustering and two closely related objectives. Known hardness results show that, on general metrics, exact recovery for Minimum Sum-of-Diameters and symmetric $k$-center is hard for every fixed $1<γ<2$, unless NP=RP. We show that MSR admits deterministic polynomial-time exact recovery for every fixed $γ>1$, extending Gao and Reyzin's result for $γ\ge2$. All three results use the same Bilu--Linial stability model: the optimal partition remains uniquely optimal when each pairwise distance is multiplied by any factor in $[1,γ]$, without requiring the perturbed distances to satisfy the triangle inequality. The number of clusters is part of the input. For $1<γ<2$, our algorithm runs in $n^{O((γ-1)^{-5})}$ time. The main structural insight is that a cheap merge in one part of the instance would allow a profitable split elsewhere under a suitable perturbation, contradicting stability. The resulting exchange inequality controls local cluster density, which gives linear growth and hence bounded treewidth in local interaction graphs. We use random partitions to obtain these regions, solve them by dynamic programming, and then derandomize the construction. For rational input and fixed rational $γ>1$, recognizing stability in this model is coNP-complete. Verifying that a supplied partition remains uniquely optimal under all allowed perturbations is coNP-complete for both arbitrary symmetric and metric perturbations.

cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.23307

Teach Your DBMS to LIKE Strings: Fast and General Pattern Matching for Wildcard Joins and Filters

Lam-Duy Nguyen, Pascal Ginter, Duc-Tam Nguyen, Thomas Neumann, Viktor Leis

原文摘要

Nowadays, modern applications do more than just store text -- they need to derive meaningful insights from it. To do that, they usually rely on wildcard queries with LIKE predicate to extract patterns. However, modern database management systems (DBMSs) handle these wildcard operations poorly, resorting to nested loops for joins and expensive interpreted evaluation for filters. To address the former, we propose a new join algorithm based on the Aho-Corasick algorithm, which significantly reduces the time complexity. For wildcard filtering, we leverage the code-generation infrastructure to improve performance: we generate specialized code for the LIKE predicate, eliminating the overhead of interpreting the pattern per tuple. Our experimental results show that the new wildcard join algorithm significantly outperforms both baseline DuckDB and Umbra, achieving speedups of up to 30.6x and 114.75x, respectively. The new wildcard filter approach likewise outperforms both baselines, achieving a speedup of 13.3x in a filter-focused stress benchmark. We believe these two techniques will play key roles for high-performance text analytics in modern query engines.

cs.DB

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.03545

An information-geometric formulation of distributed computation

Alberto Liardi, George Blackburne, Pedro A. M. Mediano

原文摘要

Understanding how complex systems perform computations, i.e. how they store, transmit, and transform information across their components, is a major goal across the natural sciences. However, characterising genuinely collective computations across multiple inputs and outputs that cannot be reduced to contributions from individual components remains an open problem. In this work, we introduce $Φ\text{ID}^{IG}$, a geometric theory of information dynamics that captures irreducible collective phenomena and enables a complete decomposition of multi-input multi-output operations into interpretable computational modes, providing a complete informational profile of a system. We first validate our framework to identify and quantify distinct computational modes in discrete and Gaussian systems with known ground truth. We then apply it to uncover the computational architecture of complex systems across synthetic and real-world scenarios, including chaotic maps, where distinct universality classes are associated with characteristic modes of computation; brain anatomy of over 100 mammalian species, revealing an evolutionary shift towards more distributed computation in the human neocortex; and financial markets, where collective computations recover the modular organisation of market sectors. Overall, our results show how complex systems can be quantitatively investigated through multidimensional computational portraits derived from the geometry of their underlying probability distributions.

cs.IT

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.36019

Causal DAG-Guided Reinforcement Learning for Long-Term Physical Activity Maintenance: Using Prior Data to Inform Future Deployment

Xueqing Liu, Young Hyun Cho, Bhanu Teja Gullapalli, Predrag Klasnja, Susan Murphy

原文摘要

Digital health interventions can provide scalable, personalized support for physical activity (PA), yet sustaining PA over the long-term remains difficult. Because affective experiences with PA are important for activity sustainment, we developed an online reinforcement learning (RL) system for the forthcoming ADAPT factorial trial that personalizes twice-daily activity suggestions aimed at improving affective associations with PA. This setting poses several challenges: participant-specific data are scarce relative to the candidate state space, important states and rewards are partially observed, interventions are frequent while the primary outcome is measured weekly, and activity suggestions can both improve PA-related experiences and increase intervention burden. We address these challenges using an expert-specified causal directed acyclic graph as an integrated RL design tool, guiding state construction, estimation of partially observed states, delayed credit assignment, and representation of beneficial and adverse intervention pathways. We further construct a longitudinal simulator calibrated from a prior micro-randomized trial to compare candidate RL designs under realistic state evolution, missingness, and participant heterogeneity before deployment. Together, this work illustrates how causal domain knowledge and prior trial data can make long-horizon, participant-specific RL more practical for digital health interventions targeting sustained behavior change.

stat.AP · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v7arXiv:2601.14252

Semantic Completeness for Correct Maintenance: A Strict Hierarchy of Typing and Inheritance

Tristan Simas

原文摘要

Removing nominal types or inheritance is defended as reducing burden; cited Java and Go rationales measure no comparison. Correct maintenance minimizes outside answers and repair obligations, preserving required answers and excluding invalid states. Answers identify meanings, memberships, and required implementations. Five capacities form a strict chain. With nominal identities fixed, only multiple contract and implementation parents attain the answer-and-repair optimum on every finite declared history. Incomplete mechanisms force slop: answers restated in code or tooling. In 20 pinned multiple-inheritance Python projects, recovered implementation-class pairs grouped by source class would need outside supply: 12,880 without inheritance, 8,792 under first parents, 739 under sound one-parent optima (checked), zero with multiple parents. With provider and state carriers fixed, state-bearing rows alone force 236 outside pairs. Java and C# interface defaults supply no instance state. At least 24 of 65 size-qualified wheels among the top 150 pure-Python downloads have positive recovered gap (36.9%, 34 unscored). For distinct, independently changing implementations, the ancestry gap is the exact outside-pair minimum with one parent supplying only required pairs, even with reparenting, infinite helpers, delegation, or generators. Zero gap and one-parent contract coverage hold iff class sets nest or are disjoint. Identical records with distinct answers need the confusability graph's chromatic number of keys. Every tree-shaped growth step inserting an off-path provider strictly between ancestors forces one-parent repair. Every snapshot in our constructed history has gap zero, yet repair obligations recur each step; multiple parents add one edge per step. At fixed design costs, bans never lower optima; savings imply suboptimal unrestricted choices.

cs.IT · cs.PL

查看论文
arXiv ↗PDF ↗