跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

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

部分采集异常
正在读取账号与研究记录…

全站更新概况

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

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

统计口径与数据新鲜度

统计 2026-11-07 21:24 — 2026-11-08 21:24（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

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

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

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

浏览论文库

研究日报 / 周报 →按信源浏览 →

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

找到 17,100 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 20:44（北京时间）
新论文 · v1arXiv:2611.01404

Serving Agentic Robot Fleets: Workload Characterization, KV-Cache Thrashing, and Admission Control

Sida He

原文摘要

Agentic robots combine a vision-language brain, a tool-using harness, and a vision-language-action (VLA) policy. Serving a fleet of these agents introduces two coupled resource constraints: the brain repeatedly revisits long, growing key-value (KV) cache states, while the VLA executes action chunks under tight control deadlines. We characterize 80 LIBERO-PRO episodes generated by GPT-6-Astra, RPent, and pi0.5 (1,862 brain turns and 1,582 VLA inference chunks), profile both layers on H800 graphics processing units (GPUs), and replay the resulting agent programs on a vLLM serving engine. Brain contexts reach 215k tokens; the median Astra request takes 7.78 s, while the intervening environment-step gap is only 1.0 s. Under a 0.25 s action-chunk deadline, one VLA GPU meets the 1% starvation target for one robot; under a 1.0 s deadline, its measured capacity reaches at least 32. In sustained brain replay, increasing concurrency from 20 to 32 robots reduces throughput from about 2.4 to 0.6 requests/s as repetitive prefill displaces generation. A static active-episode cap restores 2.24-2.25 requests/s and raises completed trace-program throughput from 1.30 to 5.00-5.55 episodes/min. Our measurements expose the workload-dependent shift between action deadlines and brain KV residency, and establish practical principles for capacity planning and admission in sustained agentic robot fleets.

cs.RO · cs.DC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01402

Improved NP-Hardness of Approximation for Max-3-Cut and for Max-k-Cut with Small k

Ziang Ni

原文摘要

We prove that Max-3-Cut is NP-hard to approximate within a factor of $27/29+\varepsilon \approx 0.931$. This improves the factor $16/17 \approx 0.941$ of Austrin, O'Donnell, Tan and Wright, the best NP-hardness result for Max-3-Cut since 2012. (Their result, unlike ours, also holds for 3-colourable graphs.) We also improve the NP-hardness of Max-$k$-Cut for every $k$ from 4 to 20; for instance, we obtain $45/47 \approx 0.957$ for Max-4-Cut and $33/34 \approx 0.971$ for Max-5-Cut, where the previous factors were 0.987 and 120/121. Our reductions are gadget reductions from Håstad's linear equations over $\mathbb{Z}_3$, with gadgets that have at most six auxiliary vertices. The main new idea is a negation trick: since the negation of an assignment is again an assignment, equations with right-hand sides $t$ and $-t$ can be handled together, and this makes the resulting predicates symmetric under all permutations of the colours. We complement it with a general soundness criterion for such reductions: in effect, the best strategy of the adversary is to use a single colour pattern everywhere. This criterion is the strongest analysis that uses Håstad's theorem as a black box, and, using LP duality, we show that under it no gadget reduction from these equations can beat $27/29$ for Max-3-Cut. Finally, we observe that a classical reduction from Max-3-Cut to Max-$k$-Cut, applied more carefully, already gives $82/85 \approx 0.965$ for Max-4-Cut on 4-colourable graphs, improving the previously stated $85/86$.

cs.CC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.21395

Exponentially Larger Deletion-Correcting Codes and Constant-List-Decodable Insertion-Deletion Codes

Han Mao Kiah, Hengjia Wei, Ruixiao Zeng

原文摘要

We establish improved asymptotic rate bounds for adversarial insertion--deletion codes. For binary unique-deletion correction in the linear-deletion regime, we strictly improve Levenshtein's classical lower-bound expression. At deletion fraction $δ=0.1$, our achievable rate increases from $0.162009$ to $0.194890$, a relative gain of approximately $20.30\%$. For list decoding with any prescribed finite list size $L$, we obtain new achievable-rate bounds for binary deletion and insertion codes. Our approach combines the Lovász local lemma with refined counting of common subsequences and supersequences, using generating functions and run-restricted sampling. We also establish a combinatorial reduction that trades $L$ units of insertion budget for one unit of deletion budget without changing the code or increasing the list size. It transfers insertion lower bounds at $γ+Lδ$ and deletion upper bounds at $δ+γ/L$ to mixed errors. We also derive a run-counting Levenshtein-type list-decoding upper bound and a higher-order Elias-type upper bound. The latter recovers Yasunaga's asymptotic unique-decoding bound at $L=1$ and strictly improves the Haeupler--Shahrasbi--Sudan insertion upper bound for every fixed $L$ and $0<γ<q-1$. Numerical comparisons quantify the gains and the remaining gaps.

cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01400

RadPose: ISAC-based RF 3D Human Pose Estimation

Geo Jie Zhou, Kunzhe Song, Ruxin Lin, Huacheng Zeng

原文摘要

Human pose estimation under adverse lighting and occlusion conditions remains challenging for camera- and LiDAR-based systems. Although mmWave radars provide robustness to illumination and occlusion, they rely on dedicated hardware and licensed spectrum, limiting scalability. In this paper, we present RadPose, a learning-based monostatic integrated sensing and communication (ISAC) framework that enables mmWave communication devices to perform 3D human pose estimation. Unlike specialized radars, RadPose leverages monostatic full-duplex operation to extract channel impulse responses (CIRs) directly from standard OFDM communication signals, generating 3D radio point clouds without additional sensing hardware. To address the sparsity and noise of RF observations, RadPose employs a cross-frame transformer-based pose inference network with semantic-guided spatial attention and target-driven temporal attention for robust spatio-temporal aggregation. It further adopts a joint-aware inverse kinematics refinement module based on graph convolution to enforce skeletal topology, bone-length consistency, and anatomical plausibility. Extensive experiments demonstrate RadPose achieves competitive accuracy compared to state-of-the-art radar-based approaches while maintaining robust performance in unseen and occluded scenarios. The dataset and source code are available at https://github.com/Geo-Chou/RadPose.

cs.CV · cs.NI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01399

Deterministic $n^{O(\log n)}$ Graph Isomorphism Algorithm via Inherited Decompositions

MohammadTaghi Hajiaghayi, Mahdi JafariRaviz

原文摘要

We give a deterministic $n^{O(\log n)}$-time algorithm for graph isomorphism. To our knowledge, this is the first proof of such a worst-case bound for general graphs. The algorithm uses the local-certificate and color-refinement steps of Babai's quasipolynomial algorithm, but retains the decomposition of each recursive instance when it solves an auxiliary coloring problem. There are two reasons for retaining this information. First, a local test can make progress without removing many vertices: it can eliminate a layer of permutation symmetry. A logarithmic bound on the total weight of these layers allows tests of constant size. Second, the auxiliary bipartite graphs arising in the symmetry-breaking step can be represented inside the current instance, after retaining a row decomposition when necessary. These recursive calls inherit the progress already made. The analysis gives a recurrence with quadratic logarithmic cost and a fixed power decrease in every fresh recursive call, improving the explicit cubic logarithmic exponent in the analysis of the corrected Luks--Babai algorithm. We present the algorithm through colorings, partitions, and bipartite graphs, and collect the permutation-group ingredients in one appendix. The result extends to string isomorphism and returns one isomorphism and generators for the full automorphism group.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01396

SpecUltra: A Unified Foundation Model for Heterogeneous Spectral Images

Weili Kong, Baisen Liu, Xiaojun Bi, Jiaming Pei

原文摘要

Spectral imagery, including hyperspectral image (HSI) and multispectral image (MSI), exhibits substantial heterogeneity in band numbers, wavelengths, spectral resolutions, hindering unified modeling and cross-sensor transfer. From the perspective of imaging physics, these heterogeneous observations can be regarded as discrete measurements of an underlying continuous spectrum acquired through different sampling processes. Motivated by this perspective, we propose SpecUltra, a unified foundation model for heterogeneous spectral images. Specifically, SpecUltra employs 3D convolutional tokenization and wavelength-aware 3D RoPE to encode relative wavelength and spatial relationships, enabling fine-grained spatial-spectral modeling within a shared coordinate system. We further construct MultiHyper-200K, a large-scale multi-sensor HSI dataset, and pretrain SpecUltra using auxiliary-token-assisted mask image modeling (MIM), where a level token indicates the radiometric product type and register tokens absorb sensor- and acquisition-dependent variations. To bridge the spectral-granularity gap between HSI and MSI, we introduce Spectral Kernel Transformation (SKT), which transfers pretrained knowledge in parameter space by constructing MSI embedding kernels from fine-grained HSI-pretrained kernel slices. This design preserves pretrained spectral priors while maintaining compatibility with the pretrained backbone. Experiments on HSI and MSI classification and segmentation benchmarks demonstrate state-of-the-art or competitive performance across disparate sensors and downstream tasks.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01394

ERIA: An Instruction-Optimized Agent for Clinical EEG Reporting

Ahmed Sameh, Gayal Kuruppu, Neeraj Wagh, Bridger Brundy, Yogatheesan Varatharajah

原文摘要

Clinical EEG interpretation requires integrating technical quality, background and behavioral states, interictal and ictal abnormalities, and overall clinical context across long recordings. We introduce ERIA (EEG Reporting and Instruction-Optimized Agent), a locally deployable framework in which a single 27B language-model controller analyzes whole-recording EEGs by orchestrating specialized parametric and signal-processing tools. ERIA combines learned tools for background abnormality, sleep-wake state, seizure-like activity, and interictal epileptiform discharges with deterministic spectral, amplitude, symmetry, montage, and signal-quality analyses. Rather than fine-tuning the controller or using multi-agent orchestration, ERIA keeps the controller weights, specialist tools, and safety constraints fixed and optimizes only its natural-language analysis policy with GEPA (Genetic-Pareto), using feedback from expert-written EEG reports. GEPA improves physician-aligned whole-recording report quality over the raw policy, and the optimized policy transfers to external EEG benchmarks. On CerebraGloss-Bench and BrainBench Foundational Analysis, ERIA remains competitive with the models evaluated in the original benchmarks. These results show that specialist tools and language-level policy optimization can extend the clinical and general EEG capabilities of a single locally executable model while preserving local inference and traceable tool use.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2503.09508

Gain-Sharing Optimization in Randomized Primal--Dual Analysis: Structure and Certification

Pan Xu

原文摘要

Randomized primal--dual guarantees for online matching and allocation often depend on a gain-sharing function that determines how algorithmic gains are distributed among dual variables and, in some settings, also affects allocation decisions. We study the best certificate obtainable by optimizing this function within a specified algorithm--analysis template. For an admissible function class F, we formulate the problem as the functional optimization $Γ(F)=\sup_{f\in F} L[f]$, where $L[f]$ is the worst-case expected dual-feasibility factor. We develop two complementary certification methods: auxiliary linear programs with explicit finite-grid error bounds, and a continuous approach based on monotone Volterra comparison and residual-based numerical verification. We apply them to the vertex-weighted Stochastic Balance template for online matching with stochastic rewards under uniform vanishing success probabilities. For the configuration-LP benchmark and specified dual updates, we optimize over the full admissible class $F_0$ of continuous non-decreasing functions from $[0,\infty)$ to $[0,1]$, and prove $Γ(F_0)\in[0.5802,0.5805]$. We also show that the more tractable subclass used for auxiliary-LP certification attains the same optimum.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01393

Layer-wise CPU-GPU Scheduling for LLM Inference on Memory-Limited Consumer GPUs

Naoto Sugiura, Yuta Tokusashi, Hiroki Matsutani

原文摘要

As large language model inference environments expand toward consumer devices, it remains challenging to efficiently run models that exceed GPU memory capacity in single-GPU settings. The latency of transferring weights that do not fit in GPU memory accounts for about 98\% of inference time and remains a major obstacle. In this paper, we focus on the fact that during the decode phase, layer computation time on the CPU can be shorter than weight transfer time, presenting an opportunity to hide weight transfers by utilizing this computation time. Therefore, we propose a method to hide transfer latency by executing certain layers on the CPU during the decode phase while asynchronously transferring the next layer's weights to the GPU in the background of that computation. To realize this scheduling, we formulate the placement of CPU/GPU computation and weight transfers as a latency minimization problem and perform optimization using an approximation model with relaxed temporal constraints. Evaluation results confirm that in a consumer desktop environment, our approach accelerates OPT-30B inference by 3.5x compared to HuggingFace Accelerate and 6.3x compared to DeepSpeed Zero-Inference.

cs.DC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01391

Vocabulary Aligned Explanations for Computer Vision Models

Erfan Mirhaji, Nikhil Krishnaswamy, Jill Zarestky, Lisa Mason, Nathaniel Blanchard, Sarath Sreedharan

原文摘要

Optimizing vision models for accuracy does not force the model to learn and utilize human-understandable and domain-specific concepts and rules. We propose explaining image classifications through domain-specific concepts, visual evidence, and expert knowledge expressed as logical rules. We introduce FLUENT (Framework for Localized, Uncertainty-Aware Explanations in Normative Terminology), a post-hoc framework that ranks expert-authored rules combining jointly required, alternative, and absent concepts. To account for prediction errors, FLUENT combines predicted labels and concept states with empirically estimated likelihoods and concept priors. It scores each rule by calculating support over satisfying assignments to the concepts mentioned in that rule, then normalizes these scores to express relative confidence among candidate explanations. The selected rule is illustrated through occlusion-based highlights for positive concept mentions in the query image and localized examples in retrieved reference images for negative mentions. These illustrations are intended to show end users unfamiliar with the domain what the concepts named in an explanation look like. FLUENT combines domain knowledge and model accuracy, and delivers visual concept highlights and explicit rule confidence to explain an image in the vocabulary of an application domain.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01390

Same Path, Less Time: Training-Free Fast Execution of Vision-Language-Action Models under Inference Latency

Fuyi Chen

原文摘要

Vision-language-action (VLA) models predict chunks of future actions, yet deployed robots waste time in two ways that are independent of model capability: they halt while the next chunk is inferred, and they move at the speed of slow, cautious demonstrations. Existing remedies remove one loss each, and stacking them fails, because asynchrony and speed-up each change the correspondence between planned progress and executed motion. We present Path-preserving Time Scaling (PTS), a training-free execution layer for frozen action-chunking policies built on one principle: the robot's motion is a time reparameterization of a reference path, and the path changes only in response to new observations. A path layer decodes every replan deterministically in one step and enters it at the progress consumed during inference. A time layer sums the planned increments, keeps the arm at 1x while the gripper moves, and caps the rate by the actuator's linear range and by chunk feasibility under latency. We show that misaligned entry and stochastic sampling add a bias and a variance to the continuation error, and derive a break-even success rate that states when speeding up pays off. On LIBERO with two frozen VLAs under injected inference latency, PTS raises task throughput over the strongest deployable baseline by 33% for pi0.5 and 104% for SmolVLA while matching or improving the success rate, is best on all six model-suite combinations, and exceeds zero-latency 1x execution. Against asynchronous 1x execution with the same one-step decoder, the time layer alone adds 28% and 38%. On LIBERO-Dynamic it improves on stop-and-wait execution by 38% and is comparable to asynchronous 1x execution.

cs.RO · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01389

A GPU-Accelerated and Geometry-Aware Quantum-Classical Framework for Optimized PES Scans with CUDA-Q

Panayiotis Christou, Shuwen Kan, Ying Mao

原文摘要

Hybrid quantum-classical workloads, particularly Potential Energy Surface (PES) scans in quantum chemistry using batched VQE and QAOA, involve many structurally similar Hamiltonians differing only in coefficients. Existing warm-start and meta-optimization strategies reuse parameters between instances but still consume fixed quantum-classical resources, ignoring cross-instance structural similarities. We present OptiPESS, a GPU-accelerated runtime system for adaptive resource allocation in hybrid quantum-classical execution. OptiPESS introduces the Locality-Occupancy-Variance (LOV) metric, a lightweight, geometry-aware measure of Hamiltonian similarity, coupled with efficient alignment and Pauli-classification passes. Using LOV, OptiPESS performs distance-aware scheduling of iteration and shot budgets, predicting which instances can be skipped, quick-solved, or fully optimized. Implemented atop CUDA-Q with persistent multi-GPU execution and near-linear scaling, OptiPESS reduces classical and quantum evaluations by up to 78.3\% and wall-time by up to 74.8\% while maintaining baseline accuracy. This demonstrates how lightweight static analysis and adaptive scheduling can transform quantum-classical co-execution from fixed-budget loops into a predictive, resource-aware runtime.

quant-ph · cs.ET

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01387

Three-phase time minimization transportation problem with non-idle phases: a polynomial two-witness algorithm

Sailesh Kamalahasan, Raghav Paladugu, Archana Khurana

原文摘要

The three-phase time minimization transportation problem partitions the origin-terminal links into three sets used in consecutive phases and minimizes the sum of the phase shipment times. Optimal solutions may leave a phase idle, as in the main example of the original study. We require every phase to carry a positive integer quantity while leaving the split of the total requirement across phases free. Discarding idle solutions from the original algorithm does not, in general, solve this variant. We prove that the optimum is attained by fixing one witness link in each of two phases and deciding the third phase by a single network flow computation, with the optimal Phase-3 time of each witness pair located by binary search. The resulting exact algorithm is strongly polynomial. It extends to any fixed number of phases, whereas, when the number of phases is part of the input, even non-idle feasibility is strongly NP-complete; feasibility alone is fixed-parameter tractable in the number of phases via known rainbow-matching results. We also characterize the minimum time of each phase. On the main example, non-idleness raises the optimum from 38 to 41. On 3,650 random instances with up to $50\times50$ links the algorithm took at most 50.2 seconds, and non-idleness raised the optimal value in 41% of the 2,250 instances with equal phase sizes; on 90 sampled instances it was faster than a mixed integer programming solver on 80 with a direct formulation and on 65 with a tighter threshold formulation.

math.OC · cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01386

Learning by Doing: Autonomously Compiling and Curating Agent Skills from Verified Traces

Daniel Chalef, Peter Evans, Pavlo Paliychuk, Mehul Patel, Preston Rasmussen, Jack Ryan

原文摘要

Memory systems for production LLM agents mostly store semantic memory (facts about users and domains) or episodic memory (earlier interactions). Research systems such as Trace2Skill, WikiSkill, and SkillRevise learn procedures from agent runs, package them as Skills, and evaluate them on benchmarks. We describe Zep Agent Skills, a production service that gives deployed agents this procedural memory. The service uses only verified attempts as evidence, cites the supporting events for each field of a Skill, and governs the admission and distribution of each Skill version. The service records each task attempt as a Trace with ordered events, an outcome, and a verification strength. A compiler with separate Reflector and Curator roles turns verified Traces into versioned Skills. Scans and admission gates control which candidates become active, and verified use outcomes change the search rank of each Skill. The Agent Skills format is an open standard that Anthropic originated and donated to the Agentic AI Foundation, so any host of the format can load a compiled Skill. Agents retrieve Skills through lexical search with progressive disclosure, over an API or MCP. We evaluate Zep Agent Skills on $τ^3$-bench banking, AppWorld, and EnterpriseOps-Gym. Skills compiled from the Traces of a teacher model increase the pass rate of three weaker executor models on the same tasks, at every reasoning effort, by 4.5 to 18.8 points. Most of the gain is on the tasks that the teacher solved. On ALFWorld, Skills compiled from the runs of a small model give a gain similar to or larger than the gain that prior work reports for continuous fine-tuning, with no training.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2403.11207

MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data

Paul S. Scotti, Mihir Tripathy, Cesar Kadir Torrico Villanueva, Reese Kneeland, Tong Chen, Ashutosh Narang, Charan Santhirasegaran, Jonathan Xu 等 11 位作者

原文摘要

Reconstructions of visual perception from brain activity have improved tremendously, but the practical utility of such methods has been limited. This is because such models are trained independently per subject where each subject requires dozens of hours of expensive fMRI training data to attain high-quality results. The present work showcases high-quality reconstructions using only 1 hour of fMRI training data. We pretrain our model across 7 subjects and then fine-tune on minimal data from a new subject. Our novel functional alignment procedure linearly maps all brain data to a shared-subject latent space, followed by a shared non-linear mapping to CLIP image space. We then map from CLIP space to pixel space by fine-tuning Stable Diffusion XL to accept CLIP latents as inputs instead of text. This approach improves out-of-subject generalization with limited training data and also attains state-of-the-art image retrieval and reconstruction metrics compared to single-subject approaches. MindEye2 demonstrates how accurate reconstructions of perception are possible from a single visit to the MRI facility. All code is available on GitHub.

cs.CV · cs.AI · q-bio.NC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01384

Benign population landscapes do not transfer to empirical risk minimization in nonsmooth optimization

Penghao Wang, Mateo Díaz, Liwei Jiang

原文摘要

Benign landscapes provide a geometric explanation for the success of iterative methods on nonconvex problems arising in data science. The landscape is benign if every local minimizer is global and every other critical point is a strict saddle. For methods that avoid strict saddles, convergence to a critical point therefore implies convergence to a global minimizer. For smooth stochastic optimization, a common strategy for establishing such landscapes proceeds in two steps: $(i)$ establish benign geometry for the population objective---which is often easier to analyze---and $(ii)$ transfer this geometry to the empirical objective using concentration of gradients and Hessians. Recent work has extended saddle-point avoidance guarantees to weakly convex nonsmooth optimization through the notion of active strict saddles. We show, however, that benign population geometry need not transfer to empirical objectives in this setting. Specifically, for robust phase retrieval with Gaussian measurements---a well-studied and highly structured problem---the population objective is benign. Nevertheless, the empirical objective has sharp spurious local minima with probability bounded away from zero as the sample size tends to infinity. This asymptotic probability lower bound is independent of the dimension.

math.OC · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01383

Toward Executable Multi-framework Front-end Code Generation with Self-Correction

Linxiao Li, Haoran Ma, Chenyue Wang, Jiaye Lin, Haochen Sui, Jiechao Gao

原文摘要

Generating codes from UI screenshots has recently benefited from MLLMs, yet existing methods centered on HTML targets and transfer poorly to multi-frameworks such as React, Vue, and Angular. However, unlike HTML, which does not entail compilation issues, generating executable code in multi-framework settings is more challenging due to framework-specific differences in syntax and failure modes, as well as the need to maintain global consistency across files. To address this problem, we study executable multi-framework front-end code generation and propose MESCoder, a tree-structured self-corrective generation framework. Our method first extracts a structural scaffold from the screenshot and then constructs sub-trees and assembly relations step by step, transforming large project generation into a sequence of localized decisions. On top of this scaffold, we introduce a unified Project Agent that continuously revises its own partial project under runtime sandbox feedback and dynamically chooses between local repair and cluster level repair. For training, we adopt a two-stage strategy that first initializes the policy offline to learn basic multi-framework generation and repair priors, and then refines it with online reinforcement learning to optimize long horizon executability and final page quality. The resulting framework models multi-framework executability as a conditioned project state transition process and improves the stability and quality of complex front end generation through self correction. Experiments show that our method improves executability, while narrowing the visual-fidelity gap to HTML-based generation. Code is available at https://github.com/leo-lilinxiao/MESCoder.

cs.LG · cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.18587

Dual Dimensionality for Local and Global Attention

Zhiyuan Wang, Xuan Luo, Sirui Zeng, Xifeng Yan

原文摘要

Decoder-only Transformers compute attention over the KV cache of preceding tokens. Keys and Values are typically represented with the same dimensionality, regardless of their distance from the prediction target. In natural language, however, the next word is most strongly influenced by the immediately preceding tokens. We hypothesize that local and distant tokens impose asymmetric demands on representational capacity: local tokens are more critical for predicting immediate outputs and thus require richer representations, whereas distant tokens primarily serve as long-range memory, for which lower-dimensional representations may suffice. We formalize this idea as Distance-Adaptive Representation (DAR), which preserves full-dimensional representations within a local context window while assigning reduced-dimensional representations (e.g. 1/2 or 1/4 of the original dimensionality) to tokens beyond that window. Across multiple pretraining scales (70M to 410M parameters), as well as continued supervised fine-tuning on a 1B-scale model, this approach closely matches the performance of full-dimensional baselines. In contrast, uniformly reducing dimensionality across all token positions leads to worse performance. These results challenge the common assumption that key and value dimensionality should be uniform across token positions. We further develop an efficient realization of DAR that achieves model quality comparable to the MLA baseline while reducing the average KV-cache size by 68.8\% at 8K context and achieving up to a $1.9\times$ decoding speedup at 128K context on the evaluated models. Our findings suggest a new direction for designing attention architectures that allocate representational capacity according to token distance to reduce KV-cache during inference.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.00929

Modeling Social Dynamics with an LLM-Enabled Agent Based Network-Dynamic (LAND) Model

Lynnette Hui Xian Ng, Kathleen M. Carley

原文摘要

Social dynamics encode the process in which individual network and discourse interactions aggregate into collective influence, narrative dominance and coordinate behavior. This paper uses the the GhostField architecture, a hybrid LLM-Enabled Agent Based Network-Dynamic (LAND) model as a social simulation framework to build the AuraSight scenario. In the AuraSight scenario, 314,244 heterogeneous cyber social agents and human actors exchange 529,327 messages over 30 days surrounding a fictional international song-writing contest. We methodologically examine emergent social dynamics across four analytical layers: ego-network topology, semantic network evolution, coordination dynamics and influence dynamics. Our results show how generated social simulations do also produce social dynamics, and how the dynamics of coordination and influence emerge not from individual agents but from the recursive interaction between network topology and narrative exchange.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01378

Information-Theoretic Design of Sparse Autoencoder-Based Steering

Hirofumi Morise

原文摘要

Sparse autoencoder (SAE)-based activation steering is a lightweight approach for modifying the behavior of large language models (LLMs) by adding small vectors to hidden states during inference. However, designing effective steering interventions remains challenging. In this work, we develop an information-theoretic framework for analyzing SAE activations through empirical feature-firing distributions. The central object of the framework is the Jensen--Shannon divergence (JSD) between such firing distributions, which quantifies how far a generated or intervened state deviates from a dataset-induced target distribution. Based on an analytic divergence response for virtually shifted states, we construct steering vectors toward the target firing distribution. The same divergence can also be used to monitor deviation from another empirical distribution, such as a general valid-language distribution. We demonstrate the effectiveness of the steering in a question-mode generation task study. We further use teacher-forced pulse experiments to show that local interventions induce structured downstream JSD responses in later layers, and apply the framework to a safety-related target--contrast response setting for feature analysis.

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01377

A Self-Exploring and Self-Evolving Paradigm for Adaptive Edge AI Development

Leming Shen, Qiang Yang, Xinyu Huang, Zijing Ma, Yuanqing Zheng, Chris Xiaoxuan Lu

原文摘要

Large Language Models (LLMs) exhibit powerful code generation abilities, fostering agentic systems to automate edge AI application development. However, existing agents typically operate via fixed agentic workflows and predefined design spaces, struggling to handle rapidly evolving demands of real-world scenarios (e.g., heterogeneous data modalities, diverse task pipelines). Unlike prior systems that treat LLMs mainly as code generators following rigid workflows, we fully exploit their reasoning capabilities to allow agents to determine their own workflows on the fly. To this end, we propose SE2, a self-exploring and self-evolving paradigm for adaptive edge AI development. Inspired by human learning processes, we distill development into four atomic operations (retrieve, reason, code, test), and empower agents to explore workflows by dynamically and adaptively selecting an appropriate next operation based on the current context. Extensive evaluations show that, with adaptive workflows, the synthesized programs achieve up to 26% higher accuracy and consume 28% lower resources than state-of-the-art baselines, while maintaining superior adaptability to unforeseen edge AI scenarios. This highlights the potential of reasoning-driven adaptive agentic workflow in edge AI development.

cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.08843

M$^3$: Reframing Training Measures for Discretized Physical Simulations

Yuan Mei, Xingyu Song, Xiaowen Song, Naoya Takeishi

原文摘要

Neural surrogate models for physical simulations are trained on discretized samples of continuous domains, where the induced empirical measure leads to uneven supervision, biasing optimization and causing spatial inconsistencies in physical fidelity. To mitigate this measure-induced bias, we propose M$^3$ (Multi-scale Morton Measure), a scalable framework that balances training measures by partitioning space according to physical variation and allocating supervision across multiple scales. Applied to three industrial-scale datasets with diverse discretizations, M$^3$ consistently improves predictions in the continuous physical domain, achieving up to 4.7$\times$ lower error in large-scale volumetric cases. These gains persist under aggressive subsampling (160M $\rightarrow$ 16M $\rightarrow$ 1.6M points), where M$^3$-trained models outperform those trained on higher-resolution data, reducing physics-weighted relative $L_2$ error by 3--4$\times$ and the corresponding MSE by up to 13$\times$. These results highlight data distribution as a key factor in operator learning and position M$^3$ as a scalable, data-efficient approach for physically consistent modeling. Code is available at https://github.com/PhysDataRefine/M3.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01376

State-Augmented Learning for Post-Deployment Adaptation of Coexisting O-RAN Applications

Wonhyeok Ko, Yeonseo Jeong, Songnam Hong

原文摘要

Fixed control policies in Open RAN can require retraining when service requirements, traffic loads, or interacting applications change. We propose ATTUNE, a state-augmented learning method for an energy saving application that coexists with a learned mobility load balancing application under a service constraint. ATTUNE conditions the energy saving policy on a Lagrange multiplier and updates this scalar during operation using measured service degradation, while keeping both applications' network parameters fixed. To train a single policy across service requirements, ATTUNE samples target service levels uniformly and maps them to multipliers through an adaptive table. This procedure accounts for policy-dependent multiplier responses and improves energy savings compared with training over a widened fixed multiplier range. We characterize the induced distribution of service levels and the convergence and fluctuations of the online update. An exact finite-window identity establishes convergence of average measured degradation to the target when the projection corrections vanish on average. Simulations show that a single ATTUNE policy achieves energy savings comparable to policies trained separately for each service requirement. It adapts to changes in the target, load, and partner application without retraining, increases energy savings at light load, and maintains target tracking for separately trained application pairs. No statistically significant increase in cell switching is detected in the evaluated comparisons.

cs.LG · cs.NI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.26015

Instruction-Tuned Models Locally Produce More Syntactic Overlap -- But Not More Conditional Reuse -- Than Humans Do

Zandi Eberstadt

原文摘要

Syntactic convergence - the tendency of speakers to adapt in language towards the grammatical profiles of their interlocutors - is a well-documented, largely implicit feature of human dialogue. Whether large language models exhibit analogous syntactic convergence towards human users relative to human baselines (including across a broad range of syntactic constructions) remains an open question. Using substitution-paradigm data from Blevins et al. [2026] in which model generations replace one speaker's turns in pre-existing human dialogues, this study measures turn-adjacent reuse of context-free grammar (CFG) rules across sixteen open-weight Llama and Gemma models (1B-70B, pretrained and instruction-tuned) at 1,901 matched positions per model. Every model showed greater CFG-rule overlap with the preceding human turn than with a sampled unrelated human prime (a context-associated effect that does not isolate syntactic priming from topical continuity), and this actual-versus-random difference was larger for lower-frequency rules. Each instruction-tuned model also showed greater natural-output overlap with the actual prime than the human response it replaced, and all eight matched architecture pairs exhibited greater actual-prime overlap after instruction tuning. However, relative to pretrained variants, instruction-tuned outputs overlapped more with unrelated primes, showed a smaller actual-versus-random increment, and had lower conditional rule-reuse odds once target rule-set size was held constant. In exploratory analyses, each model exhibited greater mean lexical and semantic similarity to the preceding turn than matched human responses did. Instruction-tuned models additionally produced responses with greater mean semantic similarity than their pretrained counterparts in all eight architecture pairs, whereas the lexical similarity results were more heterogeneous.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01372

IMPACT: Image-Conditioned Motion with Physics-Aware Collision and Trajectory Guidance for Video Generation

Shiwei Yang, Yunlong Yu, Zhao Wang, Jungong Han

原文摘要

Visually realistic video generation does not guarantee physically consistent motion. Generated objects may exhibit implausible collision responses or rebounds without energy dissipation, while even physically valid motion predictions may not be faithfully realized during synthesis. We propose \textbf{IMPACT}, a physics-state-driven image-to-video framework that addresses these challenges by coupling explicit dynamics prediction with complementary sparse--dense physical guidance. A learnably calibrated Physics State Generator unifies continuous free-flight dynamics with discrete collision responses, linking impact timing, post-impact velocity, rebound attenuation, and eventual settling within a coherent physical-state sequence. To translate this evolution into effective generative constraints, IMPACT derives sparse trajectories and dense region-level motion priors from the same physical rollout. Sparse trajectories constrain global object displacement, while dense priors guide diffusion sampling to encourage coherent object-region motion and suppress unwanted background changes. Their shared physical basis coordinates global and local motion guidance to reduce prediction--generation mismatch. Experiments on 100 controlled sphere--plane collision scenes spanning different material combinations and visual environments demonstrate improved physical plausibility over representative general-purpose, physics-grounded, and motion-controllable baselines. The project repository is available at https://weiweiwiewei.github.io/impact

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01371

Token-as-a-Utility: A Model-Agnostic Architecture for Metering and Provisioning AI Inference Services

Yichiet Aun, Soung-Yue Liew, Yu Liang Lai, Jing Jie Tan, Dong Chen, Purnomo Husnul Khotimah

原文摘要

Token-based subscriptions are emerging as a commercial model for large language model inference, but extending them into interoperable utility services requires comparable consumption accounting. Raw token counts do not consistently measure inference resource use because demand varies with model architecture, context length, tokenisation, and concurrent serving conditions. This paper presents Token-as-a-Utility, a model-agnostic architecture integrating inference metering, service-level-aware provisioning, and inter-operator settlement. We prove that, under batched serving, no per-request meter can be additive, independent of co-resident traffic, and exactly cost-reflective at once. This motivates separating provisioned capacity, metered consumption, and contracted quality into distinct service products. Consumption is expressed in Reference Inference Units (RIUs) derived from prefill and decode demand, while occupancy-indexed operator ratings recover shared serving costs without altering the common unit. Versioned inference records support auditing and re-rating across operators; software-enforced capacity leases and quality-constrained routing enable provisioning on shared accelerators. The resource model is measured on three NVIDIA RTX 5000 Ada GPUs, and multi-tenant behaviour is evaluated with a trace-driven model calibrated to them. For the reference model, occupancy-indexed rating limits statement energy error to 9% under measured traffic, compared with up to 70.5% under fixed-occupancy rating. In calibrated multi-tenant experiments, tenant mispricing decreases from 7.36 times under flat token counting to 2.39 times with RIUs and 1.06 times after occupancy-based reconciliation. These findings demonstrate how portable inference accounting can be combined with load-dependent cost recovery and contract-based provisioning to support heterogeneous inference services across operators.

cs.DC · cs.NI · cs.PF

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01370

XDecideBench: Evaluating Typed Decision Models and Confidence Policies Across Languages

Marek Šuppa, Jaroslav Kopčan

原文摘要

Applications use Typed Decision Models to route and moderate text in many languages, and they often act only on decisions above a confidence threshold. We introduce XDecideBench, a benchmark of nine suites in 122 languages with 88,425 texts and 153,875 typed questions. All suites share one scoring contract, and we report aligned, locally labelled and native items separately. Model rankings change from suite to suite. The model that is best in English, chosen in hindsight, loses significantly in about a quarter of the suite-language cells, and on Burmese Belebele it falls far behind the best model. Three open models fine-tuned for typed decisions beat the Qwen models they were built from in all twelve development languages. When the Qwen models are run locally, a pre-registered held-out cohort confirms that the accuracy gain is larger in the four languages with the least web text than in the six with the most. In both sets of languages, however, fine-tuning fixes a similar share of the base model's errors, so the larger gain may reflect weaker base models. A confidence threshold set on English data to allow 5% errors exceeds that error rate on XNLI, even in German and French.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01369

Sharper Bounds for Graphical Two-Choice Allocation

Obinna Okechukwu

原文摘要

In graphical two-choice allocation, vertices are bins, and each arriving ball must be placed irrevocably at one endpoint of a uniformly random edge. The objective is to keep the maximum-minus-minimum load gap small at every time. On cycles, endpoint-local monotone rules incur polynomial gaps at long time horizons, whereas global rules can achieve polylogarithmic gaps. We prove a joint exponential-moment inequality for the orthogonal contrasts of a binary partition tree, controlling all contrasts along a root-to-leaf path simultaneously. Applied to the Bansal--Feldheim strategy, it improves the gap on every $κ$-edge-connected $d$-regular graph from $O((d/κ)\log^4 n\log\log n)$ to $O((d/κ)\log^3 n\log\log n)$. We give an explicit strategy on the $n$-cycle with expected gap $O(\log^2 n)$ uniformly over deterministic times and exponential tails at each such time. An Euler-tour projection yields $O(\bar d\log^2(2M))$ for every connected graph with $M$ edges and degree-proportional capacities. For lower bounds, we introduce a stochastic cut workload: the expected largest normalized overload forced by the requests, plus an indivisibility term. For every online integral strategy, the supremum over time of the expected gap is at least one sixth of this benchmark. Regular rings of cliques attain $Ω((d/κ)\log n)$ along an explicit family, improving the prior additive lower bound. With unequal capacities, the workload need not control the gap: one family has constant relative cut slack, bounded workload and gap $Ω(\log\log n)$; another has workload at most $20$ but forces gap $Ω(\log n)$ even for clairvoyant fractional allocations that remain irrevocable.

cs.DS · math.PR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01368

An $\mathsf{FPRAS}$ for Mixed Volumes

Xiaoyu Chen, Kuikui Liu

原文摘要

We design the first fully polynomial-time randomized approximation scheme ($\mathsf{FPRAS}$) to estimate the mixed volume of $n$ arbitrary compact convex sets in $\mathbb{R}^{n}$ specified by weak membership oracles. This disproves a longstanding conjecture of Gurvits (2009). $\textbf{AI Disclosure}$ The main ideas were generated entirely by GPT 6 Astra. The purpose of this paper is to provide a human-written exposition of the algorithm.

cs.DS · cs.CC · cs.CG · math.CO · math.PR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01364

Cross-Scale Spatial Reasoning: A Learning-Centered Framework for Designing Immersive Learning Environments

Dishita Turakhia

原文摘要

Understanding complex scientific and engineering systems often requires learners to connect structures, processes, and behaviors across different spatial scales and levels of organization. Although research on spatial cognition, scale, multiple representations, and systems thinking has examined aspects of this challenge, these perspectives do not always provide explicit guidance for designing learning activities that require learners to integrate information across levels. Immersive technologies offer opportunities to explore otherwise inaccessible structures, coordinate representations, and investigate system behavior, but their educational value depends on the reasoning they support. This paper proposes Cross-Scale Spatial Reasoning (CSSR) as an integrative framework for understanding how learners establish and use spatial and structural relationships across scales or organizational levels. We describe five interrelated processes: scale navigation, cross-scale relational mapping, representational coordination, dynamic and causal reasoning, and consequence-oriented reasoning. Building on these processes, we develop a learning-centered framework that connects reasoning objectives to immersive design mechanisms, instructional scaffolding, and assessment. Illustrative applications in biology, semiconductor design, manufacturing, and architecture show how the framework can inform domain-specific learning activities. We also propose testable research propositions and approaches for evaluating cross-scale understanding, instructional effectiveness, and transfer. Rather than treating immersion as an educational outcome in itself, CSSR provides a basis for designing and studying learning environments that help learners explain how complex systems work across levels.

cs.HC

查看论文
arXiv ↗PDF ↗