跳到正文
研踪PaperTrail

版本更新

查看已发布论文的最新修订,在详情页对照实际观测到的版本。

部分采集异常

全站更新概况

+1084新增论文
+883其中 AI 相关
+130已有论文修订
+59新增 AI 导读

arXiv 最近完成扫描:2026-11-18 04:28 · 全站最近入库:2026-11-18 19:45各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 00:00 — 2026-11-19 00:00(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:2026-11-18 04:28最近发现新增版本:2026-11-18 19:45库内论文最新更新时间:2026-11-18 08:00

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

26,870 已收录论文22,374 AI 相关8,156 有修订112 HF 社区发现

论文修订列表

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

找到 8,156 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
版本更新 · v3arXiv:2610.16822

DTA-GT: Direction- and Topology-Aware Graph Transformer for Neural Network Representation Learning

Yuxiang Zeng, Kun Xie, Yang Wang, Jigang Wen, Xiaocan Li, Guangxing Zhang, Gaogang Xie, Jiannong Cao

原文摘要

Architecture attribute predictors reduce the cost of neural architecture search by estimating accuracy or latency from a small set of evaluated candidates. Neural architectures are operation-labeled directed acyclic graphs (DAGs), where edge directions determine computational roles and execution dependencies. Existing graph Transformer predictors incorporate topological and directional information in different ways, but primarily focus on specific mechanisms rather than coordinated encoder-wide modeling of these semantics. We introduce encoder-wide directional consistency, a design principle that coordinates the modeling of directed computational semantics across node initialization, global spectral encoding, pairwise interaction, and feature updates. To implement this principle, we propose DTA-GT, a Direction- and Topology-Aware Graph Transformer that integrates direction- and topology-aware node initialization, magnetic Laplacian spectral encoding, direction-dual structural attention, and a Direction-Sensitive MoE-FFN. Across accuracy and latency prediction on NAS-Bench-101 and NAS-Bench-201, DTA-GT consistently outperforms representative RNN-, CNN-, GNN-, Transformer-, and hybrid predictors under limited-budget settings. Ablations and magnetic spectral controls support the contribution of the direction-aware stages and orientation-sensitive spectral information, while mechanistic diagnostics characterize module behavior. These results support encoder-wide directional consistency as an effective design principle for architecture DAG representation.

cs.LG · cs.AI · cs.NE

版本更新 · v4arXiv:2605.03749

FluxFlow: Conservative Flow-Matching for Astronomical Image Super-Resolution

Shuhong Liu, Xining Ge, Quanfeng Xu, Ziteng Cui, Liuzhuozheng Li, Gengjia Chang, Jun Liu, Ziying Gu 等 12 位作者

原文摘要

Ground-to-space astronomical super-resolution requires recovering space-quality images from ground-based observations that are simultaneously limited by pixel sampling resolution and atmospheric seeing, which imposes a stochastic, spatially varying PSF that cannot be resolved through upsampling alone. Existing methods rely on synthetic training pairs that fail to capture real atmospheric statistics and are prone to either over-smoothed reconstructions or hallucination sources with no physical counterpart in the observed sky. We propose FluxFlow, a conservative pixel-space flow-matching framework that incorporates observation uncertainty and source-region importance weights during training, and a training-free Wiener-regularized test-time correction to suppress hallucination sources while preserving recovered detail. We further construct the DESI--HST Dataset, the large-scale real-world benchmark comprising 19,500 real co-registered ground-to-space image pairs with real atmospheric PSF variation. Experiments demonstrate that FluxFlow consistently outperforms existing baseline methods in both photometric and scientific accuracy. Project webpage: https://i2wm.github.io/fluxflow/.

cs.CV

版本更新 · v2arXiv:2611.03721

Counterexample-driven autonomous research with application to excess radiated energy in a Z-pinch

Bowen Zhu, Jian Wu

原文摘要

Recent breakthroughs in artificial-intelligence-assisted mathematics show that open-ended machine search can outperform human mathematicians, yet transferring this paradigm to physics requires refactoring the research workflow. We introduce Simjecture, an open-source framework in which language-model agents pursue human-defined physical conjectures. The framework tackles two central challenges in this transfer: first, because physics is empirical and no model is final, it structures inquiry around counterexample-driven falsification and prospective hypothesis repair; second, because physical theories must interact with the real world, it uses computational physics as an executable testbed while separating the qualification of numerical instruments from scientific claim review so solvers and diagnostics can be adapted within a recorded investigation. We apply the framework in a 136.3 h investigation to tackle the long-standing problem of radiated energy exceeding the imploding-shell kinetic energy in a Z-pinch. The investigation reveals competing effects of energy conversion, retention, and release timing. Stronger coherent helical deformation increases resistive conversion while reducing radiation and increasing retained energy. In a matched fine-grid test, broadening the trailing-plasma profile delays the later radiation maximum by 1.80 ns and recovers an early 153 J bolometric deficit to within 0.08% by 44 ns, with a spectral response that shifts during the pulse. These results provide new insight into energy conversion in high-energy-density plasma physics and demonstrate a new paradigm for physics research.

cs.AI · physics.plasm-ph

版本更新 · v2arXiv:2609.30456

Spectral Feedback for Test-Time Alignment of Protein Diffusion Models

Shai Dickman, Mert Cemri, Landon Butler, Kannan Ramchandran

原文摘要

Discrete diffusion models have become leading architectures for inverse protein folding. Test-time alignment guides these models during inference to generate proteins with desirable attributes. Alignment methods for discrete diffusion models often treat inference as a unidirectional process, lacking effective mechanisms for revisiting undesirable token selections. We introduce Spectral Feedback, an algorithm that selects edit-positions in a feedback loop, allowing the model to iteratively correct its own generations. This approach leverages the masking structure of discrete diffusion models by re-masking and re-sampling tokens. While prior alignment methods focus on what token labels to assign to maximize a target reward, we instead treat which tokens to revisit as the central alignment problem. Selecting edit-positions is challenging because edit effects are interdependent: the impact of modifying one token depends on which others are edited simultaneously. We define an edit-set as a set of positions to edit by re-masking and re-sampling the corresponding tokens in a sequence. Motivated by prior work on sparse interactions in biological systems, we find empirically that edit-set value functions for protein inverse folding admit sparse Fourier representations. This structure enables Spectral Feedback to efficiently learn and optimize the value functions for edit-position selection. Spectral Feedback is model-agnostic and can be applied to pre-trained, test-time aligned, and fine-tuned diffusion models without modifying the underlying generative processes. Applied to inverse folding with a protein stability reward oracle, Spectral Feedback increases the proportion of stable proteins by 32.3 percentage points over a pre-trained model, 24.8 over Best-of-10, and 5.8 over a state-of-the-art RL fine-tuned diffusion model.

cs.AI

版本更新 · v2arXiv:2606.29073

From Tool Connection to Execution Control: Benchmarking Security Invariants in MCP-Style Agent Runtimes

Ting Liu

原文摘要

Tool-connected agents need execution-time invariants that hold even when a model follows an adversarial instruction. We formulate eight execution-layer invariants (I1-I8) covering structured authority, canonical resource resolution, principal and delegation binding, handle lifecycle, explicit source-to-target transfer, request-correlated denial evidence, and single-use approval state. To test whether these protections require a centralized runtime or follow from the invariants themselves, we compare HCP, an in-memory runtime with managed handles and tasks, against an independent gateway/server ACL (B3) enforcing the same I1-I8 contract over identical grants and labels. Both block 18 modeled violations and complete 25 workflows, while 16 source-code ablations pinpoint the checks responsible. Outside our scripted corpus, we test three boundaries. First, on 24 held-out AgentDojo tasks with live models, DeepSeek reaches attacker goals in 4 direct sessions while both controllers deny every attacker call; however, strict reference-derived grants also deny 40 non-attacker calls, and first-divergence replay under an approve-all control reaches 4 new attacker goals. Second, across 132 conditions on unmodified ChainCaps and Playwright MCP servers, per-call grants block ungranted writes but cannot stop a secret passed as an ordinary argument to an authorized sink; session source budgets block that copy but refuse unrelated actions; and explicit handle pipes or sealed reads block handle-mediated exfiltration while preserving unrelated workflows. Third, on a matched MCP backend, HCP adds 0.13 ms per workflow outside MCP calls while retaining 7.7 MB of state over one thousand workflows versus 0.7 MB for B3. Identical decisions across HCP and B3 show that enforcing explicit I1-I8 invariants at controlled entrances secures tool execution across centralized and gateway designs.

cs.CR · cs.AI

版本更新 · v2arXiv:2607.23182

Beyond ICA: Identifiability by Symmetry Breaking

Pengzhou Wu

原文摘要

We prove the population-level identifiability of deep generative models (DGMs) with piecewise-affine (PWA) decoders and Gaussian mixture model (GMM) priors, in a purely unsupervised setting. We introduce three algebraic contrast principles for symmetry breaking: *domain contrast*, which trivializes the mixture symmetry group, a label-free counterpart of the sufficient-variability assumption of nonlinear ICA; *mechanism contrast*, which ensures every decoder branch gets an observational boundary across which it toggles alone; and *interaction contrast*, which forbids parameter conspiracies between latent components and decoder branches. Together they exploit the interplay between the discrete combinatorics of the PWA map and the continuous symmetry structure of the latent GMM. Continuity is replaced by algebraic symmetry conditions; injectivity is decoupled from structural identification and required only for pointwise inversion. Our results form a hierarchy: from *law identifiability* (LID; latent distribution up to a global affine map) through *map identifiability* (MID; decoder up to the same map) to *posterior* and *pointwise identifiability*. The ICA-form ambiguity emerges under conditions on diagonal component covariances. The interaction contrast is the only one of our contrasts required on the estimator side. To our knowledge this is the first to develop algebraic symmetry-breaking into an identifiability engine for a concrete nonlinear model class, the first to admit discontinuous decoders, and the first to handle fully non-injective decoders, where every observation admits multiple latent codes.

stat.ML · cs.LG · math.ST

版本更新 · v2arXiv:2601.23180

TriSpec: Ternary Speculative Decoding via Lightweight Proxy Verification

Haoyun Jiang, Junqi He, Feng Hong, Xinlong Yang, Jianwei Zhang, Zhengyang Zhuge, Zheng Li, Xiaofeng Cao 等 12 位作者

原文摘要

Inference efficiency in Large Language Models (LLMs) is fundamentally limited by their serial, autoregressive generation, especially as reasoning becomes a key capability and response sequences grow longer. Speculative decoding (SD) offers a powerful solution, providing significant speed-ups through its lightweight drafting and parallel verification mechanism. While existing work has nearly saturated improvements in draft effectiveness and efficiency, this paper advances SD from a new yet critical perspective: the verification cost. We propose TriSpec, a novel ternary SD framework that, at its core, introduces a lightweight proxy to significantly reduce computational cost by approving easily verifiable draft sequences and engaging the full target model only when encountering uncertain tokens. TriSpec can be integrated with state-of-the-art SD methods like EAGLE-3 to further reduce verification costs, achieving greater acceleration. Extensive experiments on the Qwen3 and DeepSeek-R1-Distill-Qwen/LLaMA families show that TriSpec achieves up to 35% speedup over standard SD, with up to 50% fewer target model invocations while maintaining comparable accuracy.

cs.LG

版本更新 · v2arXiv:2608.12195

IF:CARGO: LLM-Based Semantic Compilation for Al-Native Rule Programming Games

Ting-Chen Hsu, Lianye Zhang, Jiangxu Lin, Zhaoyi Yu, Fei Qin, Zihao Chen

原文摘要

This case study presents IF: CARGO, an experimental puzzle game that uses a large language model as a semantic compiler rather than an autonomous game-playing agent. Players author IF/THEN rules in natural language, which the model translates into a constrained command schema for deterministic validation and execution by the game engine. This architecture creates a playable loop of expression, execution, observation, and revision, framing AI interaction as semantic debugging. A mixed-methods playtest with 24 participants across eight levels examined player attempts, thinking time, perceived controllability, adjustability, and interpretations of the AI's role. Results suggest that players generally understood the model as a translation intermediary and could revise their strategies through feedback, while periodic commands, multi-robot coordination, and rule-priority mechanics created greater cognitive and diagnostic demands. The study proposes a practical pattern for AI-native gameplay: constrain natural-language input, preserve player authorship, and ensure deterministic execution.

cs.HC

版本更新 · v2arXiv:2608.24845

LAION-BVD: A 13-Million-Hour Open Video Dataset for Multimodal Pre-training

Andreas Hochlehnert, Marianna Nezhurina, Mehdi Cherti, Andrej Radonjic, Thaddäus Wiedemer, Christoph Schuhmann, Romain Beaumont, Wieland Brendel 等 12 位作者

原文摘要

We present LAION-BVD (LAION - Big Video Dataset), a large-scale open video dataset for multimodal learning, which contains 1.3B platform-specific video URLs collected from CommonCrawl. From these, we download 80M videos with a total duration of 13.5 million hours. The dataset is designed for multimodal pre-training across the video, audio, and image modalities. Using content-aware scene detection, we extract clips for which we synthetically generate video and audio captions. Models trained on these data achieve competitive performance on standard video-text and audio-text benchmarks, with consistent improvements as training or model scale increases. Additionally, we explore video frames as an alternative source of image-text data by extracting scene-changing frames. These frames exhibit a visual distribution distinct from standard web image corpora, and models trained on this dataset achieve strong image-text retrieval performance. We release LAION-BVD to the research community. It significantly expands open access to multimodal videos at an unprecedented scale.

cs.CV · cs.AI · cs.LG

版本更新 · v3arXiv:2607.18642

Spaghetti Architect: A Controlled Code Benchmark Generator, and What Its Own Comments Do to Model Scores

Yuxiang Ji

原文摘要

Code corpora mined from the wild cannot change one thing at a time: a program's behaviour, messiness and size vary together, and nothing marks the correct answer. We present Spaghetti Architect, a generator that turns a small JSON description of a program into deliberately messy programs in five languages. It compiles and runs every program, checks the output against a reference computed from the description, and labels each program by problem size and by messiness. This control lets us change one property at a time and still know the correct answer. The generator writes comments into its own output, so we first re-render identical code without them. Removing the comments lowers the refactoring score of all four models we tested, and lowers the weakest model's about ten times as much as the strongest model's; a pre-registered replication confirms the difference at a smaller magnitude. The comments also hide an effect: messiness leaves scores flat while they are present and lowers them on both tasks once they are gone. We therefore recommend evaluating on the comment-free rendering. Changing only problem size drives direct-answer aggregation accuracy to zero for every model, and changing only literal values moves scores by less than 0.012. The generator, the dataset and the evaluation records are open source.

cs.LG · cs.SE

版本更新 · v2arXiv:2605.31522

Chem-PerturBridge: a harmonized compendium of small molecule perturbation transcriptomic effects

Artur Szałata, Olga Novitskaia, Maiia Shulman, Matthew Mella, Altynbek Zhubanchaliyev, Fabian J. Theis

原文摘要

Large perturbation models require training data encompassing chemical, cellular, and assay diversity. Current transcriptomic resources for small-molecule modeling, however, are fragmented across technologies, metadata conventions, controls, doses, and preprocessing pipelines. We introduce Chem-PerturBridge, a harmonized multi-dataset resource comprising over 37k compounds, 136 cellular contexts, and 1.25M transcriptomic samples across eight assay types, with standardized identifiers, metadata, and replicate-aware condition-level effects. We use the resource to evaluate matched-condition agreement across datasets and replicate agreement within datasets. Matched same-compound conditions show weak absolute agreement in fine-grained $\mathrm{logFC}$ rankings and magnitudes across most dataset pairs. However, they generally exceed individual same-context different-compound signatures, while often falling below the smoothed centroid of such signatures. Same-compound retrieval is above chance in all pairs. $\mathrm{LogFC}$ direction agreement is high in absolute terms, and exceeds both baselines in most cases. We further evaluate Chem-PerturBridge as a pretraining resource for compound representation learning. Under a compound-held-out OP3 evaluation split, embeddings pretrained on Chem-PerturBridge improve over L1000-only embeddings, Morgan fingerprints, chemical language model embeddings, and the descriptor-free OP3 baseline across metrics. An extensive molecule-holdout evaluation across 11 datasets further shows that models trained on Chem-PerturBridge outperform or match those that are not. Chem-PerturBridge therefore supports both diagnostic evaluation of cross-dataset signature agreement and model-oriented reuse of heterogeneous perturbation transcriptomic data.

cs.LG · q-bio.GN · q-bio.QM

版本更新 · v2arXiv:2609.14402

Neural Modal Decomposition: Architectural Priors from Observables

Juho Park, Kaushik Sengupta

原文摘要

Many engineering building blocks behave as multi-port linear time-invariant systems. RF cavities, photonic devices, and superconducting quantum chips, despite their different underlying physics, all share a common mathematical structure for their port-level response. Each entry of the response matrix is a sum of contributions from a small number of intrinsic resonant modes, the pole-residue form. A model capable of predicting such responses for arbitrary geometries and arbitrary port configurations, while simultaneously extracting the underlying eigenmode structure, could therefore offer a design principle potentially applicable across all these domains. We propose a neural framework that learns this modal decomposition end-to-end, supervised only by system-level observables and without supervising the modal parameters themselves. The architecture decomposes into a port-independent pole predictor and two port-dependent coupling predictors whose outputs are combined entry-wise, separating intrinsic from port-dependent features. This factorization yields a single trained model that generalizes to port counts unseen during training, whereas direct regression needs a separate model for each port count, with an output size that grows as $\mathcal{O}(N^2)$. Although the modal parameters are never supervised, the freely parameterized poles converge to the physical resonances, in agreement with poles extracted by the AAA rational approximation algorithm. We instantiate the framework in radio-frequency electromagnetic surrogate modeling. A model trained only on 2-port data accurately predicts $N$-port responses unseen during training.

physics.comp-ph · cs.LG

版本更新 · v2arXiv:2606.22142

RoboLineage: Agent-Native Data Lifecycle Governance Across Robot Policy Iterations

Qian Luo, Wentao Guo, Zhennan Qin, Nanchun Guo, Yunhan Zhao, Yi Ma, Yanchao Yang

原文摘要

We present RoboLineage, an agent-native data lifecycle governance system for robot policy iteration. Modern robot policies improve through repeated data collection, review, retraining, evaluation, and release decisions, but the evidence connecting these steps is often scattered across local tools, scripts, and expert memory. RoboLineage makes this lifecycle explicit by representing rollouts, reviews, dataset decisions, training runs, policy metadata, evaluations, deployment recommendations, and next-collection plans as typed lineage artifacts. Agents interpret embodied rollout evidence, adapt accepted data to existing training stacks, maintain data health, and summarize cross-iteration state under explicit artifact boundaries. In real-robot manipulation workflows, RoboLineage makes routine policy iteration faster and more auditable while maintaining downstream policy performance. We open source RoboLineage as a lightweight lifecycle layer for different robot embodiments and training families. Project page: https://robolineage.github.io/

cs.RO

版本更新 · v2arXiv:2610.31863

Machine-Readable Operator Manuals over the ISO 11783 Network for Offline, Multilingual LLM Assistance

Timo Oksanen, Julius Gun

原文摘要

If agricultural machinery is to support intelligent, offline assistance, then the system must access technical documentation dynamically. In this paper, the Semantic Synchronization of operator manuals over ISO 11783-based CAN buses is analyzed, defined as the process that brings the local knowledge base of a tractor-side assistant into agreement with the operator manual of the connected implement. Data transfer performance was benchmarked using Markdown, JSON, and XML; various open-weight Large Language Models (LLMs) were also evaluated in cross-lingual query tasks. The automatic evaluation of the answers was validated against four human raters. A complete manual was transferred over a physical ISO 11783 network in 31 to 89 s, depending on format and transport settings, which is comparable to the object pool upload that operators already wait for at the first coupling of an implement. Markdown produced the smallest files, while the question-answering performance was comparable across the three formats for most models. With retrieval-augmented generation, locally run models answered most questions on the English manual correctly, with no advantage of the largest model over 7B and 8B models, but performed worse on the five other language editions. Keyword retrieval failed across languages, whereas semantic retrieval provided the cross-lingual capability. The exchange requires only a new parameter group that uses the existing request and transport mechanisms of ISO 11783, which makes it a candidate for standardization. The study is a proof of concept with inference on PC-grade hardware; deployment on embedded agricultural hardware remains future work.

cs.CL · cs.AI · cs.IR

版本更新 · v2arXiv:2510.24282

TsetlinKWS: A 65nm 16.58uW, 0.63mm2 State-Driven Convolutional Tsetlin Machine-Based Accelerator For Keyword Spotting

Baizhou Lin, Yuetong Fang, Renjing Xu, Rishad Shafik, Jagmohan Chauhan

原文摘要

The Tsetlin Machine (TM) has recently attracted attention as a low-power alternative to neural networks due to its simple and interpretable inference mechanisms. However, its performance on speech-related tasks remains limited. This paper proposes TsetlinKWS, the first algorithm-hardware co-design framework for the Convolutional Tsetlin Machine (CTM) on the 12-keyword spotting task. Firstly, we introduce a novel Mel-Frequency Spectral Coefficient and Spectral Flux (MFSC-SF) feature extraction scheme together with spectral convolution, achieving a record-high accuracy of 87.35% for TM-based models on the 12-keyword spotting task. Secondly, we develop an Optimized Grouped Block-Compressed Sparse Row (OG-BCSR) algorithm that delivers a remarkable 9.84$\times$ reduction in model size, significantly improving the storage efficiency of CTMs. Finally, we propose a state-driven architecture tailored for CTMs, which simultaneously exploits data reuse and sparsity to attain high energy efficiency. The full system is evaluated in 65 nm process technology, consuming 16.58 $μ$W at 0.7 V with a compact 0.63 mm$^2$ core area. TsetlinKWS demonstrates a Power-Performance-Area (PPA) product of 60.2 and requires only 907k logic operations per inference, corresponding to 1.4$\times$ and 10$\times$ reductions, respectively, compared with state-of-the-art KWS accelerators. These results position the CTM as a highly efficient candidate for ultra-low-power speech applications.

cs.SD · cs.AR · eess.AS

版本更新 · v4arXiv:2605.09393

Motivators and Demotivators of Integrating Large Language Models in Software Engineering Education: An Exploratory Familiarity Allocation Framework

Maryam Khan, Jussi Kasurinen, Muhammad Azeem Akbar, Estefanía Martín-Barroso

原文摘要

Large Language Models (LLMs) are increasingly influencing software engineering practice and education, yet little research has examined their systematic integration using stakeholder evidence and quantitative decision-support models. This study presents an exploratory familiarity-allocation framework for analyzing motivating and demotivating factors in LLM integration in software engineering education. Building on our earlier literature-based taxonomy, we evaluated 19 factors (nine motivators and ten demotivators) through a survey of 126 stakeholders from multiple countries. Naive Bayes and Logistic Regression were used to examine associations between factor ratings and high self-reported LLM familiarity. Both models reached an accuracy of 0.461, below the majority-class baseline, so their probabilities were used as exploratory relative scoring functions rather than individual-level predictions. These estimates were fed into a Genetic Algorithm with a defined allocation score to support Global Factor Allocation (GC), Local Factor Allocation (LC), and category-level Delta-Fitness analyses. The most highly rated motivators were Programming Assistance and Debugging Support, Personalized and Adaptive Learning, and AI as a Learning Partner. The most highly rated demotivators were Plagiarism and Intellectual Property Concerns, Over-Reliance on AI in Learning, and Reduced Critical Thinking and Problem-Solving. Under the fitted models and allocation assumptions, GC assigned higher levels to integrity- and governance-related factors, while LC revealed further pedagogical and risk-related patterns within categories. These configurations are exploratory scenarios, not validated implementation priorities or evidence of educational effectiveness, and classroom and institutional validation is needed before the framework can guide practice.

cs.SE

版本更新 · v2arXiv:2608.02391

Cooperative Coevolution for Resource-Constrained Agentic LLM Post-Training

Zhiyuan Wang, Shengcai Liu, Jiahao Wu, Ning Lu, Hui Ouyang, Shaofeng Zhang, Haoze Lv, Ke Tang

原文摘要

Tool-using large language model (LLM) agents produce long, multi-turn trajectories, making gradient-based post-training memory-intensive. Evolution strategies (ES) enable memory-efficient full-parameter post-training without backpropagation and can eventually match the performance of gradient-based reinforcement learning (RL). However, resource-constrained settings typically offer only a few GPUs, so the high GPU-hour requirements of ES translate into prohibitively long training times. To address this, we introduce Cooperative Parameter-subspace Evolution Strategy (CoPES), a cooperative coevolutionary method that decomposes the full parameter space into lower-dimensional subspaces and searches over them cooperatively to improve optimization efficiency. On Qwen3.5-4B math, CoPES recovers 92% of full-parameter GRPO's validation-accuracy gain within the GPU-hour budget of GRPO's best validation checkpoint, versus 67% for standard ES. Its theoretical GPU memory requirement is less than one-eighth that of full-parameter GRPO. It consistently outperforms standard ES and LoRA-based GRPO on all evaluated pass@k metrics across five math benchmarks. CoPES's gains extend to Qwen3.5-9B with unchanged optimization hyperparameters and to multi-hop QA. These results demonstrate an improved trade-off between memory requirements and training time for agentic LLM post-training under resource constraints. The code is open-sourced in https://github.com/MetaronWang/CoPES

cs.AI · cs.LG

版本更新 · v2arXiv:2606.20871

Geometric Entropy: When Trajectory Diversity Helps and Hurts in Imitation Learning

Qian Luo, Ruizhe Liu, Pei Zhou, Xunzhe Zhou, Yanchao Yang

原文摘要

We study how trajectory-shape diversity in demonstrations affects imitation learning (IL) performance across models, tasks, and data scales. We introduce Geometric Entropy (H_G), a task-agnostic metric that quantifies the intrinsic diversity of transit trajectories after normalizing away extrinsic variation, such as goal pose and workspace scale, via target-frame alignment. Across multiple IL architectures and both simulated and real-robot contact-rich manipulation tasks, we observe a consistent inverted-U relationship between success and H_G: increasing geometric diversity improves robustness in low-diversity regimes but degrades performance once diversity induces strategy ambiguity. Moreover, the optimal entropy shifts toward lower values as task mastery increases through more data, easier tasks, or stronger priors, and for a pretrained vision-language-action model the trend becomes effectively monotonic decreasing. Practically, H_G enables fast pre-training auditing of demonstration datasets and offers a simple guideline for calibrating demonstrations toward the learnable regime.

cs.RO

版本更新 · v6arXiv:2506.23210

Effective Unbounded Drift Control in Heterogeneous Federated Learning: Bayesian Fine-Tuning Using a Reference Model

Taehwan Yoon, Wesley De Neve, Bongjun Choi

原文摘要

Federated learning (FL) enables collaborative model training across distributed clients while preserving data privacy. However, data and system heterogeneity often induce unbounded drift in model updates due to each clients' different multiple local steps, partial participation, and unbounded dynamics in model updates. These challenges severely degrade predictive performance, exacerbate catastrophic forgetting, and hinder global optimization forward to optimal updates. Related works (AdaBest, FedEve, A-FedPD) defined dual drift problems and proposed each regularization term to client optimization process. However, in aspect of temporal unbounded drift, they generally reflect last round temporal drift to client optimization while forgets prior temporal unbounded drift. To address these limitations, we propose FedRef, a robust optimization framework that leverages a reference model generalized from prior global models via Bayesian fine-tuning. FedRef integrates a Maximum A Posteriori (MAP)-based regularization mechanism that calibrates global updates toward a temporally aggregated reference model, thereby effectively controlling unbounded drift and maximizing empirical stability. Moreover, unlike prior approaches that rely on complex client-side optimization heuristics, FedRef achieves superior generalization to reflect recency weighting by seamlessly blending a robust probabilistic prior with global likelihood optimization. By maintaining a temporal moving average centered on previous global trajectories, the proposed framework provides a highly reliable optimization anchor.

cs.LG · cs.AI · cs.DC

版本更新 · v2arXiv:2606.09257

BSTabDiff: Block-Subunit Diffusion Priors for High-Dimensional Tabular Data Generation

Al Zadid Sultan Bin Habib, Md Younus Ahamed, Prashnna Gyawali, Gianfranco Doretto, Donald A. Adjeroh

原文摘要

High-Dimensional Low-Sample Size (HDLSS) tabular domains (e.g., omics) are characterized by $n \ll m$, where $n$ = number of samples, and $m$ = number of features. Such domains often exhibit strong local correlation groups, sparse cross-group dependencies, heavy-tailed non-Gaussian marginals, heteroscedastic noise, and structured missingness, making direct density learning in $\mathbb{R}^m$ ill-conditioned since $n \ll m$. We propose BSTabDiff, a block-subunit generative framework that partitions the $m$ observed features into $M$ latent blocks ($M \ll m$) and generates each block via a shared low-dimensional subunit variable, concentrating global dependence learning in the compact block-latent space $\mathbb{R}^M$ while decoding to the full feature space with copula-driven dependence, flexible per-feature marginals, and explicit missingness mechanisms. BSTabDiff can induce a data-driven feature ordering and block construction before latent partitioning, allowing the model to better align with local dependency structure when such organization is beneficial. BSTabDiff supports modern deep priors on block latents, including diffusion and normalizing flows, enabling stable synthesis and controllable benchmark generation in the HDLSS regime. Empirically, BSTabDiff produces more realistic and more stable high-dimensional synthetic data when compared with unstructured tabular generators on HDLSS data.

cs.LG · cs.AI · stat.ML

版本更新 · v2arXiv:2609.36637

Decompose Dynamics Before Learning Dependencies in Spatiotemporal Systems

Ziqi Wang, Daojiang Hu, Cheng Bao, Zhiwei Ling, Wenzhuo Qian, Jiahui Zhai, Hailiang Zhao

原文摘要

Relations in networked spatiotemporal systems are often learned from observations that entangle dynamics governed by different mechanisms, obscuring what evolves locally and how it propagates across nodes. We introduce Component-Aware Network Dynamics with Ordered Relations (CANDOR), which decomposes local dynamics before learning their dependencies. CANDOR represents each trajectory through a persistent background, gradual accumulation and release, and sparse shocks. Conditioned on these components, a delay-aware physical branch models edge and sample-dependent propagation over directed topology, while a topology-unconstrained functional branch discovers latent dependencies from background dynamics. Context-adaptive fusion combines functional, forward-propagation, and reverse-support forecasts, with training objectives encouraging specialized and semantically consistent representations. Experiments on two traffic benchmarks and three long-horizon water-quality datasets span two distinct spatiotemporal systems: human-driven urban traffic and naturally evolving river water quality. CANDOR achieves the lowest aggregate normalized error across five datasets, outperforming the overall runner-up by 7.25%. These results establish decomposition before dependency learning as an effective principle for spatiotemporal representation learning.

cs.CE

版本更新 · v3arXiv:2605.07964

Asymptotically Log-Optimal Bayes-Assisted Confidence Sequences for Bounded Means

Valentin Kilian, Stefano Cortinovis, François Caron

原文摘要

Confidence sequences based on test martingales provide time-uniform uncertainty quantification for the mean of bounded i.i.d. observations without parametric distributional assumptions. Their practical efficiency, however, depends strongly on the choice of martingale updates, and many existing constructions do not exploit prior information about plausible data-generating distributions or mean values. We propose a Bayes-assisted framework that uses a Bayesian working predictive model to adaptively construct confidence sequences. For each candidate mean and time point, the predictive distribution selects, among valid one-step martingale factors, the update maximising predictive expected log-growth; validity is therefore preserved even when the prior or working model is misspecified. We prove that if the predictive distribution is Wasserstein-consistent, the resulting procedure is asymptotically log-optimal, matching the per-sample log-growth of an oracle procedure with access to the true distribution. We instantiate the framework using robust predictives based on Dirichlet-process mixtures and Bayesian exponentially tilted empirical likelihood. Experiments on synthetic data, sequential best-arm identification for LLM evaluation, and prediction-powered inference show that informative priors can substantially reduce confidence-sequence width and sampling effort while retaining anytime-valid coverage.

stat.ML · cs.LG

版本更新 · v6arXiv:2608.15565

Admission Without Answers: Label-Free Certification and Experience Learning for LLM-Based Optimization Modeling

Junbo Jacob Lian, Huiling Chen, Hanzhang Qin, Chung-Piaw Teo

原文摘要

Agents that learn from experience improve at optimization modeling by storing solved trajectories and reusing them as skills. A wrong trajectory that enters the library can be retrieved for many later problems, and a stream of new problems carries no ground-truth answers that could keep it out. Existing learners admit trajectories by matching known optima, and label-free substitutes such as execution success or agreement at one instance admit wrong models. We introduce AdmitOR, a label-free admission gate. It generates models from three model families and solves each on the stated problem and on instances with resampled parameters. It keeps the largest group of models whose optimal values agree on every instance and that spans more than one family. A threshold fitted on solver-verified problems maps this agreement to acceptance, abstention, or escalation, with a finite-sample bound on the false-discovery rate of accepted values. Inside a recent skill learner, AdmitOR raises admission precision from 0.871 under majority vote to 0.927. Its library is the smallest of the four compared and has the highest macro accuracy on five benchmarks. An ablation traces the gain to an accepted value external to the learner. One program from the learner's own model already raises precision to 0.923, and agreement across families raises it further. With one candidate per family, resampling can withhold a certificate but cannot change its value, and the values it withholds are wrong far more often than those it keeps, on the stream and on the solver-verified calibration set. The false-discovery bound holds on the calibration set but not on the benchmark stream. An audit traces every false certificate to a benchmark text that omits or rounds the numbers needed to reproduce the labeled answer, or to a label error. A label-free check of the extracted numbers against the text flags most omitted-number cases.

cs.AI

版本更新 · v3arXiv:2503.03283

Exploring specialization and sensitivity of convolutional neural networks under simultaneous image augmentations

Pavel Kharyuk, Sergey Matveev, Ivan Oseledets

原文摘要

Drawing parallels with the way biological networks are studied, the authors adapt the treatment--control paradigm to explainable artificial intelligence research and enrich it through multi-parametric input alterations. A framework for investigating internal inference impacted by input data augmentations is proposed to address the real-world scenario with multiple simultaneously applied treatments instead of observing a single effect. The internal changes in network operation are reflected in activation changes measured by variance, which can be decomposed into components related to each augmentation by employing Sobol indices and Shapley values. To facilitate distinguishing model-related specifics from the self-interactions of augmentations, an auxiliary variable responsible for their permutations has been incorporated into the analysis. The resulting quantities enable one to visualize sensitivity to different variables and use them as features for further analysis and processing, including guided masking of activations. In addition, a method for single-class sensitivity analysis is introduced through a pipeline that involves class selection according to their match with the prediction bias generated by targeted damaging of the activations. Three convolutional networks, namely AlexNet, VGG11, and ResNet18, have been evaluated via the designed framework, with two vision transformers, ViT-b-16 and Swin-t, partially complementing the findings. Two sets of augmentations, consisting of five and seven distinct input transformations applied simultaneously, have been utilized as sources of variance in the image domain. Relying on the observed parallels, the authors assume that the developed framework can potentially be transferred to the study of biological neural networks in complex environments, as well as enhance the design of autonomous decision-making systems.

stat.ML · cs.AI · cs.LG · math.NA

版本更新 · v4arXiv:2505.23277

Sentinel: Decoding Context Utilization via Attention Probing for Efficient LLM Context Compression

Yong Zhang, Heng Li, Yanwen Huang, Ning Cheng, Yang Guo, Yun Zhu, Yanmeng Wang, Shaojun Wang 等 9 位作者

原文摘要

Retrieved contexts are often long, noisy, and redundant, motivating query-aware compression before answer generation. Native attention provides signals for context selection, but heterogeneous head behaviors complicate their direct aggregation into sentence-utility scores. We introduce Sentinel, a sentence-level compressor that learns to combine these signals through a signed linear readout across layers and heads. Only the readout is trained using existing QA evidence annotations, while the backbone remains frozen and sentence scoring requires no autoregressive generation. Across twelve LongBench tasks, Sentinel with a 0.5B backbone outperforms Full Context on multiple tasks under a 2,000-token budget with each of three readers: Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct, and DeepSeek V4.1 Flash. Despite English-only QA supervision, the same readout transfers to Chinese tasks without task-specific retraining. Length-stratified profiling further shows lower compression latency and GPU memory usage than LLMLingua-2 and CPC.

cs.CL · cs.AI

版本更新 · v3arXiv:2605.30876

dMoE: dLLMs with Learnable Block Experts

Sicheng Feng, Zigeng Chen, Gongfan Fang, Xinyin Ma, Xinchao Wang

原文摘要

Diffusion Large Language Models (dLLMs) have recently emerged as a promising alternative to autoregressive models, offering competitive performance while naturally supporting parallel decoding. However, as dLLMs are increasingly integrated with Mixture-of-Experts (MoE) architectures to scale model capacity, a fundamental mismatch arises between block parallel decoding and token-level expert selection. Specifically, each dLLM forward pass processes multiple tokens with bidirectional dependencies, whereas conventional MoE layers route each token independently. This mismatch substantially increases the number of uniquely activated experts, making inference increasingly memory-bound. To address this, we propose dMoE, a simple yet effective block-level MoE framework. The central idea of dMoE is to aggregate token-level expert distributions within each block into a unified block-level expert distribution, which is then used to guide block expert routing in a coherent manner. In this way, dMoE substantially reduces the number of uniquely activated experts during inference without sacrificing performance, thereby mitigating the memory-bound bottleneck. Extensive experiments across a variety of benchmarks demonstrate the effectiveness of dMoE. On average, dMoE reduces the number of uniquely activated experts from 69.5 to 16.6 while retaining 99.55% of the original performance. Meanwhile, it reduces memory usage by 74.36% to 76.78% and achieves $1.36\times$ to $2.04\times$ end-to-end latency speedup. Code is available at: https://github.com/fscdc/dMoE.

cs.CL

版本更新 · v4arXiv:2603.27397

Benchmarking Quantum Computers via Protocols, Comparing Superconducting and Ion-Trap Quantum Technology

Nitay Mayo, Tal Mor, Yossi Weinstein

原文摘要

Both Superconducting and Ion-Trap are leading quantum architectures common in the current landscape of the quantum computing field, each with distinct characteristics and operational constraints. Understanding and measuring the underlying $\underline{\text{quantumness}}$ of these devices is essential for assessing their readiness for practical applications and guiding future progress and research. Building on earlier work (Meirom, Mor and Weinstein Arxiv 2505.12441), we utilize a benchmarking strategy applicable for comparing these two architectures by measuring "quantumness" directly on optimal sub-chips. Distinct from existing metrics, our approach employs rigorous binary fidelity thresholds derived from the classical limits of state transfer. This enables us to definitively establish quantum advantage of a designated sub-region. Here we apply this quality assurance methodology to platforms from both technologies. This comparison provides a protocol-based evaluation of quantumness advantage, revealing not only the strengths and weaknesses of each tested chip and its sub-chips but also offering a common language for their assessment. By abstracting away technical differences in the final result, we demonstrate a benchmarking strategy that bridges the gap between disparate quantum-circuit technologies, enabling fair performance comparisons and establishing a critical foundation for evaluating future claims of quantum advantage. We encourage other companies to emulate the independent qubit availability and the fair pricing, as do IBM and AQT, which allow researchers to perform such assessments. In the discussion section, we consider an important future direction of using "benchmarking via protocols" also for fault-tolerant quantum computing with logical qubits.

quant-ph · cs.DC · cs.ET

版本更新 · v2arXiv:2610.37361

Online Interval Selection with Binary Predictions: Optimal Consistency and a Continuous Robustness Tradeoff

Zhong Han

原文摘要

We study online interval selection with binary predictions of membership in a final optimal solution. Requests arrive in arbitrary order; accepted requests may be revoked, but rejected or revoked requests cannot be recovered. With rewards proportional to interval length, the best consistency under finite strict robustness is $d=(3+\sqrt5)/2$ when both guarantees hold almost surely on each fixed input, including for randomized algorithms. A continuous lower bound forces consistency strictly above $d$ at every robustness budget below $4\varphi+3\approx9.472$, whereas our deterministic algorithm attains $d$ with exact robustness $\varphi^5\approx11.090$, where $\varphi=(1+\sqrt5)/2$. Each held interval inherits a ledger recording positive prediction mass lost through irrevocable decisions. Tuning the replacement costs and both special thresholds gives a continuous family with exact consistency throughout and exact robustness on two parameter intervals, including $(C,R)=(25/9,10)$ and $(4,7)$. Randomization permits expected consistency approaching one with finite expected robustness, whereas almost-sure robustness forces expected consistency strictly above two at every finite budget.

cs.DS · cs.LG

版本更新 · v2arXiv:2611.03601

DiabAgent: Toward Agentic Physiological Control

Chengxi Li, Shaoxuan Li, Deyao Hong, Qingle Liu, Yi Huang, Puheng Bian, Minzhi Xu, Lanyue Zhang 等 16 位作者

原文摘要

As pretraining scales, medical language models have advanced rapidly in clinical question answering. Their ability to achieve effective physiological control through sustained intervention still lacks systematic quantitative evaluation. Type 1 diabetes provides a concrete setting: impaired insulin secretion creates dependence on exogenous insulin, with dosing continually adjusted using information about meals, exercise, illness, and glucose measurements. We introduce DiabAgent, a research suite for agentic physiological control comprising the Agentic Physiological Control (APC) framework, the DiabetSim simulator, and the SweetBench benchmark. APC controls glucose through medical-device tools, using ongoing observations to infer individual states, accumulate personal experience, and choose treatment actions. We build DiabetSim to simulate different patients, events, and device conditions for scalable virtual testing and training. Using DiabetSim, we construct SweetBench by instantiating 32 scenario designs as 212 glucose-control tasks. With Claude Opus 5.5 and a fixed decision interval of one hour, APC achieves a COGI of 73.5, compared with 71.2 for the open-source closed-loop baseline OpenAPS. Ablations further show that individual adaptation and contextual information improve glucose control. Combining high-frequency rule-based control with lower-frequency agent decisions shows potential for balancing control performance and computational cost. Our work provides a framework, simulator, and evaluation foundation for agents to participate in human physiological control.

cs.AI · cs.CL

版本更新 · v2arXiv:2609.37675

LEMON-ZEST: Evolution-Informed Tokenization for Efficient Protein Language Modeling

Biswajit Banerjee, Claudia Alvarez Carreno, Anton S. Petrov

原文摘要

Protein Language Models (PLMs) have made remarkable progress following scaling laws established in natural language processing across sequence- and structure-based tasks, yet the potential of tokenization remains underexploited. Unlike human language, proteins preserve structure despite extensive sequence variation, a property standard tokenization strategies fundamentally fail to capture. We introduce ZEST (Zoned Encoding of Sequence Traits), an evolution-informed vocabulary derived from conserved regions of multiple sequence alignments. ZEST allows embedding domain-level biological priors directly at the tokenization stage rather than learning them implicitly through scale. ZEST natively compresses sequences to an average token length of 3.3 residues, enabling our model to process $\geq3380$ residues within a standard 1024-token context window. Building on this, we present LEMON (Layered Extraction of Molecular Ordering from Nature), a compact 200M-parameter sequence-based model for detection of remote homology between protein sequences trained on a single H100 GPU for one week. Despite its modest size, LEMON outperforms models of 600M to 3B parameters and is on-par with TM-Vec. Our results demonstrate that evolution-informed tokenization can substitute for massive parameter scaling, opening a new direction for efficient, biologically-grounded protein representation learning. All code and model weights are publicly available (at \href{https://github.com/LDWLab/ZEST}{github.com/LDWLab/ZEST}) under the MIT license.

cs.LG · q-bio.BM