跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+479新增论文
+361其中 AI 相关
+63已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 13:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 15:46 — 2026-11-16 15:46(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:2026-11-16 01:34最近发现新增版本:2026-11-16 13:44库内论文最新更新时间:2026-11-14 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。

23,827 已收录论文19,941 AI 相关6,921 有修订112 HF 社区发现

浏览论文库

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 23,827 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
版本更新 · v2arXiv:2610.28083

IECG: Weakly-Supervised Interpretability-Enhancing Foundation Model for Electrocardiogram

Huynh Dang Nguyen, Trong-Thang Pham, Anh-Thuan Do, Phuong-Nhi Dinh, Brijesh Patel, Ngan Le, Van Nguyen

原文摘要

Electrocardiography (ECG) is a cornerstone of cardiac diagnosis, yet most machine learning methods for ECG analysis lack interpretability, limiting their clinical adoption. We present IECG, a weakly-supervised ECG foundation model that jointly performs diagnostic classification and abnormality localization without requiring manual abnormal region annotations, overcoming a long-standing bottleneck in interpretable ECG learning. Central to IECG is a weakly-supervised attention strategy that explicitly incorporates clinical priors by deriving abnormality heatmap pseudo-labels from established ECG clinical knowledge. These pseudo-labels guide the model's CLS-token attention through a KL-divergence loss, encouraging it to focus on diagnostically relevant waveform regions. During pretraining, IECG is jointly optimized with clinically guided attention supervision, ECG-text contrastive alignment, and report captioning objectives, enabling it to learn rich multimodal representations while producing localized waveform evidence. By explicitly aggregating features from clinically guided attention regions, IECG grounds its diagnostic predictions in interpretable waveform evidence without sacrificing classification performance. Extensive experiments demonstrate that IECG achieves state-of-the-art abnormal region localization while maintaining strong classification performance, advancing trustworthy foundation models for ECG analysis.

cs.AI

新论文 · v1arXiv:2611.13765

Beyond Interaction Scores: Selecting Feature Interactions via Independent Replication

Jincheng Gao, Shuo Sun

原文摘要

Learning feature interactions is essential for accurate prediction and interpretable modeling, yet a high interaction score may reflect fitting noise rather than a reproducible pattern. Ranking methods score feature pairs but leave the cutoff to the user; testing methods set the cutoff but rely on repeated model refits or a model of the joint feature distribution. We present LENS, a model-agnostic framework for selecting feature interactions through independent replication. LENS trains two models with the same learning algorithm on disjoint data and accesses them only through predictions. For each feature pair, it removes main effects from the joint-effect surface to isolate an interaction pattern, ranks pairs by its strength, and tests whether the second model reproduces it at a meaningful strength. A single multiple-testing correction determines which pairs to retain, using only two model fits regardless of the number of features. We prove that a replication ratio alone can retain arbitrarily weak patterns shared by both fits, whereas a strength floor restores selection consistency, and we characterize when normalization in Friedman's $H^2$ reverses interaction rankings. On 16 synthetic designs, LENS matches leading model-specific ranking methods (e.g., TreeSHAP) and recovers 91% of material interactions, against 45% for the knockoff-based DIAMOND, without selecting false pairs; with 1,225 candidate pairs and no interactions, it makes substantially fewer false discoveries. On large-scale French motor insurance data, it identifies interactions documented in the actuarial literature and recovers 90% of the deviance gain obtained using all pairs. On two credit datasets, LENS selects few pairs while maintaining or slightly improving predictive performance over the additive baseline.

cs.LG · cs.DB · stat.ML

新论文 · v1arXiv:2611.13762

Exploiting What NVIDIA Profilers Hide: Fast and Accurate Analytical GPU Performance Modeling

Ziwen Wang, Qi Luo, Kunlin Li, Changxi Liu, Dongsheng Wang, Yun Chen

原文摘要

GPUs have become essential to many fields, including AI and scientific computing. As GPUs grow more complex, the design space of their hardware configurations becomes increasingly large, yet cycle-level simulators remain too slow to explore it. Analytical models make this exploration much faster. However, existing GPU analytical models fall short of accurately predicting performance across hardware configurations, because they re-estimate or scale every stall of a warp on the target configuration. We observe that fixed-latency stalls stay the same across configurations, whereas queueing stalls vary with the pressure on each hardware unit. Based on this observation, we propose ForeSight, a queueing analytical model that reuses the fixed-latency stalls measured on GPU hardware and recomputes the queueing stalls of each hardware unit from its pressure. To provide ForeSight with the counter values of each hardware unit, we build UnitSight, a profiler that recovers these values, which NVIDIA's official profilers hide by aggregating across units. Our evaluation on hardware configurations of nine NVIDIA GPUs shows that ForeSight predicts kernel execution time with a mean absolute percentage error (MAPE) of 8.3%, compared with 14.1% for the best baseline. ForeSight also predicts the end-to-end execution time of LLM inference on vLLM with a MAPE of 2.0%. It runs 49x faster than the cycle-level simulator Accel-Sim and faster than interval-based models such as GCoM. With the aid of ForeSight, we explore configurations derived from the H20 GPU for LLM inference and find one with 1.78x its performance/cost.

cs.AR · cs.PF

版本更新 · v2arXiv:2611.02472

MAGAR: Multimodal Agents for GUI-Based 3D Mechanical Assembly and Minimal Rework

Jingxuan Wei, Jiahao Fu, Fuqiang Wang, Xiaoming Wu, Yuwen Liu, Kaiwen Wei, Ming Yang, Junnan Zhu

原文摘要

A GUI command can be correct at the interface level yet still produce an incorrect assembly. An agent must identify the relevant components, respect their structural relationships, and determine which parts should move during recovery. We introduce MAGAR-Bench, a benchmark of 4,000 multimodal samples from 26 assembly families that separates Assembly Decision, Atomic Action, and Minimal Rework. For rework, the objective counts distinct moved parts within the validated recovery candidate set for each state, rather than the number of actions. We also introduce MAGAR, a selective correction framework built on a frozen policy obtained by supervised fine-tuning. Its key design matches correction granularity to output dependencies. Structured candidates revise assembly fields and rework scope, while complete action candidates keep native GUI primitives coupled with their parameters. A learned selector retains the original prediction unless a candidate passes a task-specific intervention threshold. On recorded states from held-out assembly families, MAGAR improves Overall, the task-balanced aggregate, from 37.50 to 41.39, with gains on all three tasks. Across 209 interventions, 70 correct an error and 22 introduce one. These results support task-specific correction while highlighting the remaining tradeoff between fixing errors and preserving reliable predictions.

cs.AI

新论文 · v1arXiv:2611.13760

Recursive memory for prediction and generation

Pengbin Feng, Chunlei Meng

原文摘要

Recurrent and state-space language models compress the past into a state of fixed size. The state must answer questions about the future now, and it must remain useful as new tokens arrive, including tokens the model samples itself. We show that the second requirement can cost far more memory than the first. For a known hidden Markov source with positive transition probabilities, a state of $O(\log(1/\varepsilon))$ bits answers every question about the future to accuracy $\varepsilon$, however far ahead it looks, because the Bayesian filter forgets its rounding errors. Generating the future is different. When a model feeds each sampled token back into its state, the small errors in its next-token distributions add up, and $T$ tokens can require a state of order $\log(T/\varepsilon)$ bits. The lower bound comes from the KL chain rule: at every step, a model with $K$ states pays for approximating the true next-token distribution by one of only $K$ distributions. The argument applies to any source, including a language model continuing a prompt, and a small-ball estimate makes it tight for two-state sources. The extra $\log T$ disappears if the model keeps private randomness, or if error is budgeted per token, as in perplexity. Statistics of the recent past show the same gap between describing and maintaining. The number of ones among the last $n$ bits takes $\log n$ bits to write down. But if each bit is a noisy copy of the one $n$ steps earlier, tracking that count to a mean-square error $E^2$ well below its variance costs order $n/(1+E^2)+\log n$ bits. Information about each bit must be kept until the bit leaves the window, and a queue holding the counts of recent blocks keeps just enough of it.

stat.AP · cs.IT

新论文 · v1arXiv:2611.13759

Exploring Synchrony for Communication in Modular Neural Networks

Nikolas Willems, Qiyang Sun, Björn W. Schuller

原文摘要

One motivation for modular neural networks is to divide computation across components that learn distinct, reusable functions, which could then be recombined to support compositional generalisation. In practice, modular structure alone does not guarantee that such roles develop, and unrestricted communication between modules can undermine any specialisation that does emerge. This raises the question of how modular communication should be organised. The problem can be viewed as an analogue of the perceptual binding problem, where synchrony has been proposed as a mechanism for coordinating distributed representations. We introduce SyncNet, a modular architecture that separates module content from a dynamical phase state: learnt Kuramoto dynamics evolve the phases, while phase alignment determines communication through a shared channel. We evaluate SyncNet on Sort-of-CLEVR for relational reasoning and on SQOOP for systematic generalisation, where lower pair variety demands more recombination at test time. SyncNet gives the best held-out accuracy of the models compared at the three lowest pair varieties, by 5.1 percentage points at the hardest, and is competitive on Sort-of-CLEVR though below the strongest attention baselines. Test-time overrides show that performance depends on phases that evolve: fixed phases cost as much as no addressing at all, and permuting which module holds which region is nearly as damaging. A content-addressed variant trained from scratch nonetheless matches it, so the benefit appears to come from the modular decomposition rather than synchrony itself.

cs.CV · cs.NI

新论文 · v1arXiv:2611.13758

Mixed Signals: Weight-Space Programming for EEG and ECG

Dara Varam, Taraneh Aminosharieh Najafi, David Atienza

原文摘要

Weight-space programming allows language models to read a trained neural network's weights and edit them. This opens the door to ``training'' by reasoning rather than through gradient descent. Prior work has demonstrated its functionality and promise for game-playing networks and fixing specific failures in language models, even extending to diffusion models. In this work, we present its applicability to models trained on biosignal data, specifically EEG and ECG data. We show that frontier models are not only able to debug specific faults planted in biosignal-based models without being told what these faults are, but are even capable of writing all the weights of a network from scratch, given only the architecture, the task, and a minimal set of training subjects. In particular, in one set of experiments, a language model was able to match standard gradient-descent training using $6\times$ fewer training subjects, through reasoning alone and without any gradient descent step. Networks written by Claude Opus 5.5 also scored higher than classic hand-crafted EEG pipelines (alpha band power, and common spatial patterns with linear discriminant analysis) when built from the same 5 subjects. We also highlight some of the limitations, which include the inability of language models to improve already well-trained classification models, and their incapacity to reliably recognize, from the weights alone, the task a network was trained on. Overall, our results indicate that weight-space programming can be useful for small networks, such as those deployed on edge devices and wearables, but the concept still requires further investigation before it can be used in practice.

cs.LG · cs.AI · eess.SP

版本更新 · v3arXiv:2610.29391

Nominate-then-Adjudicate: LLM-Assisted One-Pass and Per-Instance MIP Solver Tuning

Yifan Zhao, Qianyang Zhao, Xinyu Guan, Kai Wei, Yuming Deng

原文摘要

Parameter configurations control presolving, cut generation and branching strategies in mixed-integer programming (MIP) solvers, directly affecting solving efficiency. Effective configurations vary across instances, while searching for them online requires additional solver runs. We propose Nominate-then-Adjudicate: an empirical performance model (EPM) shortlists candidates from a fixed portfolio, and one large language model (LLM) call selects using static features, compressed formulation text and memory distilled from offline solver measurements. Text exposes distinctions omitted by the chosen aggregate features; selection requires no online candidate solves or foundation-model weight updates. Across sixteen synthetic families, adjudication improves on the EPM's top-ranked candidate (top-1), raising mean normalized performance score from 0.377 to 0.426 and the win rate against SCIP's default from 84.9% to 90.2%; all ten sequential batches show positive mean-score gains. On 400 Ecole instances, it outperforms the per-instance baseline ISAC+ in mean runtime-based score, with gains concentrated in facility location. Total solver time falls by 69.6% versus default, excluding LLM latency. Ablations support text and memory; a second LLM improves over top-1.

cs.LG

版本更新 · v4arXiv:2605.13282

Differentiable Learning of Lifted Action Schemas for Classical Planning

Jonas Reiter, Jakob Elias Gebler, Hector Geffner

原文摘要

Classical planners can effectively solve very large deterministic MDPs represented in STRIPS or PDDL where states are sets of atoms over objects and relations, and lifted action schemas add or delete these atoms. This compact representation yields strong search heuristics and provides an ideal setting for structural generalization, since lifted relations and action schemas give rise to infinitely many domain instances. A central challenge is to learn these relations and action schemas from data, and recent approaches have addressed this problem using different types of observations. In this work, we develop a novel neural network architecture for learning action schemas from traces where states are fully observed but action arguments are unobserved. The problem is a simplification but an important step towards learning planning domains from sequences of images and action labels, and we aim to solve this simplification in a nearly perfect manner. The challenge lies in learning the action schemas while simultaneously identifying the action arguments from observed state changes. Our approach yields a robust differentiable component that can then be integrated into larger neuro-symbolic models. We evaluate the architecture on various planning domains, where the learned lifted action schemas must recover the ground-truth structure. Additionally, we report experiments on robustness to observation noise, on component ablations, and on a variation related to slot-based dynamics models.

cs.AI · cs.LG

新论文 · v1arXiv:2611.13757

Stochastic Aggregation with Prescribed Resources and Additive Delay

Tianhang Lu, Runtian Ren, Shengcai Liu

原文摘要

We study online aggregation with prescribed resources and additive delay. In this problem, we are given a finite set of resources with purchase costs and a collection of request types, each specifying the resources it requires. Requests arrive over time, and each request can be served immediately or postponed to a later time. A service may serve several pending requests together by purchasing every resource required by at least one of them, paying for each purchased resource only once. These purchases serve only the current batch; resources needed in a later service must be purchased again. A request served $t$ units of time after its arrival incurs delay cost $t$. The objective is to serve all requests while minimizing the sum of resource purchase costs and individual delay costs. We consider a stochastic version of this problem in which requests of each type follow an independent Poisson process of known rate. An online algorithm knows these rates but observes requests only upon arrival. We compare its expected cost with that of an offline optimum that knows the entire realized input and may choose every batch freely. A resource--scale linear program supplies both an offline lower certificate and synchronized service periods. This yields a deterministic online algorithm with polynomial-time preprocessing on rational input and a long-run ratio of expectations below $2.113$. The guarantee applies in particular to rooted multi-level aggregation and prescribed-pair aggregation on trees. Besides, for Poisson TCP acknowledgment, we further characterize the optimal long-run ratio of expectations at every load, showing that its worst-case value is approximately 1.409 and is attained by a deterministic online policy.

cs.DS

版本更新 · v2arXiv:2610.06190

Bridging the Evidence-to-Execution Gap:A Reflective Agent for Multi-Objective Peptide Design

Haosen Zhang, Yang Yang

原文摘要

Large language models can reason over scientific literature, but textual plans do not reliably produce biological sequences with the intended properties. Sequence generators capture sequence patterns, yet they do not interpret evidence, choose interventions, or reflect on outcomes. This separation creates an evidence-to-execution gap between scientific reasoning and sequence-level control. We introduce EASER, a reflective agent that connects the two through a learned property interface. The interface consists of property-specific low-rank directions trained offline and fixed during search; an LLM controller (the controller) composes them to steer a frozen diffusion generator. From retrieved evidence, sequence context, and prior outcomes, it proposes intervention hypotheses that specify anchors, editable positions, and coefficients. Probe-and-Steer tests these hypotheses and allocates further samples from their joint predicted responses; reflection updates the agent's memory. On computational antimicrobial peptide design, EASER balances activity, non-hemolysis, and non-toxicity. Explicit hypothesis formulation yields larger multi-objective gains than direct action generation, and ablations support evidence retrieval, episodic history, reflection, and Probe-and-Steer. EASER achieves the highest mean hypervolume and lowest mean IGD+ among the evaluated search policies and generators on screened candidates. These results show that a learned property interface can make literature-grounded reasoning executable at the sequence level.

cs.AI

版本更新 · v3arXiv:2504.04404

fRAC: Remote Accelerator Calls on Hostless FPGAs

Ziyi Yang, Krishnan B. Iyer, Yixi Chen, Ran Shu, Zsolt István, Marco Canini, Suhaib A. Fahmy

原文摘要

Hardware accelerators are essential for meeting microsecond-scale demands in distributed applications, but invoking them over the network remains bottlenecked by host software. Host-mediated paths (RPC, RDMA) still rely on the CPU to reassemble requests and launch accelerators, which dominates end-to-end latency, while packet-level offload on SmartNICs lacks any notion of a complete request. We introduce the Remote Accelerator Call (RAC) paradigm, in which transport ingestion, request reassembly, dispatch, and accelerator invocation are handled entirely in hardware. We build fRAC, a hostless prototype that implements this network-to-accelerator interface as a lightweight shim on an FPGA hosting multiple virtualized accelerators, reconfigurable at runtime in a few milliseconds. Serverless functions backed by fine-grained accelerators are a natural fit, since host-mediated invocation overhead can match or exceed their short execution times. fRAC achieves under 7.8us end-to-end latency while sustaining application throughput of up to 90 Gbps. Compared to highly optimized DPDK-based CPU and DPU baselines, it achieves at least 80% lower latency under saturation, while consuming 85% less power.

cs.NI · cs.AR

版本更新 · v2arXiv:2604.23546

COMO: Closed-Loop Optical Molecule Recognition with Minimum Risk Training

Zhuoqi Lyu, Qing Ke

原文摘要

Optical chemical structure recognition (OCSR) translates molecular images into machine-readable representations such as SMILES strings or molecular graphs, but remains challenging in real-world documents due to wide variations in chemical structures, shorthand conventions, and scanning artifacts. Most existing deep learning approaches rely on teacher forcing with token-level Maximum Likelihood Estimation (MLE). This training paradigm suffers from exposure bias, as models are trained under ground-truth prefixes but must condition on their own previous predictions during inference. Moreover, token-level MLE objectives hinder the optimization towards molecular-level evaluation criteria such as chemical validity and structural similarity. Here we introduce Minimum Risk Training (MRT) to OCSR and propose COMO (Closed-loop Optical Molecule recOgnition), a framework that mitigates exposure bias by directly optimizing over molecule-level, non-differentiable objectives. Experiments on ten benchmarks, including synthetic and real-world chemical diagrams from patent and scientific literature, demonstrate that COMO substantially outperforms existing rule-based and learning-based methods with less training data, consistently achieving superior performance across both reproduced baselines and previously reported results. Ablation studies further show that MRT is architecture-agnostic, demonstrating its potential for broad application to end-to-end OCSR systems.

cs.CV · cs.AI · cs.LG

版本更新 · v5arXiv:2606.04993

Code Lifespan Survival Analysis (CLSA): Predicting the Survival of Source Code Lines Using AST-Aware Mining

Pavel Gurov

原文摘要

Superseded by arXiv:2611.10530. Context: Predicting which source lines will be deleted - and when - matters for maintenance and review prioritization. Existing MSR approaches work at file or method granularity, masking individual-statement risk. Objective: We introduce Code Lifespan Survival Analysis (CLSA), the first framework to model individual-line deletion risk from covariates - where prior line-granularity work estimated lifespans but found no significant predictors. CLSA treats each line as a right-censored subject and estimates deletion risk from structural, contextual, and temporal covariates; its strongest predictors are computable statically from one file (AST structure plus line token count), without version history or bug data. Method: We mine 32.5 million line birth events from 120 open-source TypeScript repositories. A 5-stage matching pipeline separates true deletions from refactoring noise, preventing 8.3 million false deaths. We fit a Cox Proportional Hazards model with 15 covariates and check robustness via Weibull/Log-Logistic AFT, gamma frailty, and time-stratified landmark models. Results: The Kaplan-Meier median survival time is 1,335-1,352 days (about 3.7 years), verified on the full 32.5-million-line population and an independent resample; among deleted lines the median lifespan is 95.7 days. Line token count is a steady protective factor (HR=0.87) that stays essentially flat with age (HR 0.89-0.91 across regimes). Lines in conditional branches show no detectable effect at birth (HR=0.98, 0-90 days, not significant) but become a risk factor after 90 days (HR=1.23). Repository identity is the largest factor: a gamma frailty model (variance theta=1.451) raises concordance from 0.587 to 0.676. Conclusion: Line-level survival modeling is tractable, yielding interpretable risk signals and a calibration recipe for time-conditional scoring in IDEs and code review.

cs.SE

新论文 · v1arXiv:2611.13752

Word-Level Alignment of OCR and Ground Truth under Zoning and Reading-Order Errors

Fonseca Cacho, Jorge Ramón

原文摘要

OCR post-processing needs OCR text aligned word by word with its ground truth. Data sets rarely provide that mapping, and a monotone aligner can lose its place when zoning errors permute the reading order. We revisit this problem, the Zoning Problem of our 2019 paper, with a protocol that tests correctness under such permutations. We apply OCR-side reading-order permutations with construction-time word-level gold and score correct-match F1, cascade length and recovery. We compare the 2019 location-aware aligner, a re-anchoring extension of it, a RETAS-style baseline (RETAS-lite), a multi-region aligner that combines unique-word and unique n-gram anchors with chunk-to-window assignment, genalog's RETAS and the original Java RETAS. Experiments use synthetic character noise with block moves, paragraph swaps and column interleaving, historical newspaper reading-order permutations, geometry-derived gold for Tesseract OCR, and a small word-box set. Synthetic tests show where local tracking fails after large displacements and where unique-anchor methods collapse when unique anchors are scarce. On our synthetic boilerplate page the 2019 method had the highest F1 among those tested. Historical newspaper and geometry-derived evaluations carry the limitations of approximate gold and the article-order convention. The first multi-region version has a quadratic scaling cost. Local tracking remains fragile under large reading-order changes; the tested anchor-based methods handle many of those cases but fail when unique anchors are scarce. Approximate gold, the article-order convention, missing residual annotation, and the lack of modern multi-column word-level ground truth remain limitations.

cs.CL · cs.CV

新论文 · v1arXiv:2611.13750

List Update with Per-Page Maximum Delay

Tianhang Lu, Runtian Ren, Shengcai Liu

原文摘要

We study list update with per-page maximum delay. Requests may wait, and one access clears all pending requests of a page at its current list rank, paying their maximum waiting penalty. Each service can change the permutation and therefore the cost of later accesses. We give a strictly $5$-competitive deterministic algorithm: serve a page when the oldest waiting time reaches two thirds of its current rank, then move it to the front. Our main tool is an asynchronous marked-rank coupling that compares different list orders and different service histories. A temporal transfer principle separates this permutation argument from two waiting-cost inequalities. It gives factor $5$ for page-specific superadditive penalties, common calendar rates, and additional hard deadlines; deadlines alone admit factor $3$. Two structural conditions on request-specific penalties give factor $3+2κ$. In particular, nonincreasing request severity retains factor $5$ even with unbounded weight ratios. For linear delay, offline optimization is NP-complete but fixed-parameter tractable in the number of pages. We characterize fixed-list batching, show an $Ω(m)$ gap between the best static order and dynamic reordering, and prove that the optimal deterministic factor for one page is exactly $2$. Counterexamples delineate the threshold rule's scope.

cs.DS

新论文 · v1arXiv:2611.13748

When Covariance Is Not Enough: Kernel-Based Regularization for Single-Cell Counterfactuals

Korbinian Traeuble, Edward de Brouwer, Archit Verma, Doron Haviv, Kipper Fletez-Brant

原文摘要

Counterfactual editing of single cells, predicting how an observed cell would look had one factor been different, enables in-silico screening where experiments are infeasible, but is useful only if the edit is faithful to the individual and not merely to the condition. Concept bottleneck generative models make the effects of interventions interpretable by decomposing a cell's representation into known and unknown factors. Previous work uses a linear cross-covariance penalty to disentangle known and unknown dimensions. We demonstrate that this first-order criterion does not fully separate information when non-linear interactions are present. We first demonstrate the inadequacy of linear cross-factor penalization with simulation experiments with controlled edits and known non-linear covariate effects. We then demonstrate that adding a nonlinear kernel criterion, the normalized Hilbert-Schmidt Independence Criterion, is able to recover the true intervention effects on simulation data. Finally, we apply the non-linear concept bottleneck model to a complex single-cell RNA-seq dataset and find that it improves the ability to generate counterfactual expression profiles of cells under different tissue environments.

cs.LG · q-bio.GN

版本更新 · v2arXiv:2509.09906

Towards using Large Language Models for Risk Negotiation and Consensus-building in One Health contexts

Alexandra Fetsch, Iurii Savvateev, Racem Ben Romdhane, Martin Wiedmann, Artemiy Dimov, Maciej Durkalec, Josef Teichmann, Jakob Zinsstag 等 15 位作者

原文摘要

Risk negotiation under the One Health framework requires balancing competing stakeholder interests across human, animal, and environmental health domains - a process constrained by information complexity and time pressure. This study presents and evaluates a multi-step pipeline that integrates large language model-based agents into a human-supervised negotiation process, specifically targeting risk assessment, valuation, and negotiation steps. Agent descriptions were generated from stakeholder-provided materials using retrieval-augmented generation methods. During preliminary multi-agent discussions, agents accessed domain-specific computational models and web-based sources before human participants refined proposed issues and options. A simulated negotiation game then produced distributions of candidate deals, characterised using Nash bargaining solution criteria and Pareto optimality metrics. The developed approach was evaluated in a workshop involving independent domain experts across two real-world scenarios: food safety criteria for Campylobacter in broiler meat and oak processionary moth management. In this feasibility evaluation, participants reached consensus with the allotted time after discussing and modifying the proposed deals. The framework offers an adaptable blueprint for AI-assisted risk negotiation; the specific contribution of LLM assistance, including gains in efficiency and decision quality, requires comparative evaluation.

cs.MA · cs.AI

版本更新 · v2arXiv:2605.10425

Epistemic Infrastructures of Science in AI Era Should Rebalance Costs of Generation and Verification

Jiaqi W. Ma

原文摘要

AI systems can now cheaply generate plausible scientific artifacts such as papers, reviews, and surveys. This creates a risk of \emph{epistemic pollution} in our scientific systems, where unreliable but plausible-looking artifacts can accumulate faster than the system can filter them out. The problem is structural: the epistemic infrastructure of science was calibrated to a world where producing a plausible artifact required substantial expertise, labor, and time, so generation cost itself served as a rough filter; AI weakens that filter without comparably lowering verification cost. This position paper argues that \textbf{AI-era science should rebalance the costs of generating and verifying scientific artifacts by redesigning epistemic infrastructure at the level of the artifact}. The current paper-centered system makes verification expensive: papers compress long-context scientific logic into prose, forcing reviewers, human or AI, to reconstruct underlying argument structure before they can evaluate it. As one step in this direction, we propose \textbf{blueprints}: structured, decomposed research artifacts that represent claims, evidence, assumptions, and definitions as typed graph components. Blueprints complement rather than replace papers---the paper remains the narrative interface, the blueprint becomes the verification interface---and are designed to trade an upfront generation cost for cheaper, more local, more distributed verification downstream. We also instantiate the proposal in a proof-of-concept prototype.

cs.CY · cs.AI

版本更新 · v2arXiv:2611.06447

$A^3$-VLA: Automatic Perception-Guided Attention Alignment for Robot Manipulation

Shengzhe Zhang, Qi Zhang, Dazhong Shen, Chao Wang, Shaopeng Zhai, Hui Xiong

原文摘要

Vision-Language-Action Models (VLAs) enable robots to perform manipulation tasks by leveraging Vision-Language Models (VLMs) to process visual observations and language instructions. However, the action prediction objective itself lacks fine-grained task-specific perceptual supervision, making it prone to relying on task-irrelevant visual shortcuts, leading attention away from target objects and key interaction areas, thereby limiting its operational performance and generalization ability. To address this, we propose Automatic Perception-Guided Attention Alignment for Robot Manipulation ($A^3$-VLA), a framework that derives task-specific visual guidance from the manipulation process itself. Specifically, $A^3$-VLA first generates heuristic candidate regions for target objects and the robot from interaction-induced visual changes, and refines them with a visual segmentation model offline. These regions serve as explicit perceptual guidance through two complementary objectives: an attention allocation loss that encourages sufficient focus on task-critical regions when language or robot state tokens query the visual input, and a contrastive learning loss that aligns the representations of candidate target regions with language instructions while separating them from task-irrelevant regions. Extensive experiments on simulated and real-world manipulation tasks demonstrate that $A^3$-VLA consistently improves multiple VLA backbones, with an average success rate gain of 6.5% - 25.2% across benchmarks.

cs.RO

版本更新 · v2arXiv:2609.36630

A Comprehensive Survey of Agent Distillation across Models, Artifacts, and Harnesses

Ziluowen Luo, Senzhang Wang, Chaozhuo Li, Jun Yin, Hao Yan, Ming Cheng, Chenxu Wang, Songyang Liu 等 13 位作者

原文摘要

Knowledge distillation provides a teacher-student framework for transferring capabilities at reduced cost and has been widely studied for large language models (LLMs). As LLM-based agents move from response generation to sustained, closed-loop task solving, distillation expands beyond model parameters to knowledge retained in reusable resources and execution workflows. This shift from model-level to agent-level knowledge transfer supports efficient deployment, broader capability access, and continual self-evolution. However, existing surveys largely examine model distillation and agent system design separately, limiting comparison of transfer strategies across agent components. To bridge this gap, we formalize Agent Distillation as persistent knowledge transfer between teacher and student agents and present its first unified survey. Distinguishing experience used for transfer from knowledge retained for reuse, we develop a knowledge-substrate taxonomy based on where knowledge persists: models, artifacts, or harnesses. Building on this taxonomy, we analyze cross-substrate transfer paths and hybrid strategies. To assess the resulting capabilities, we review benchmarks and evaluation protocols for retention, causal attribution, and deployed utility without further teacher support. This survey provides a unified basis for studying agent knowledge transfer and developing efficient, adaptable, and self-evolving agents.

cs.AI

新论文 · v1arXiv:2611.13744

Do Language Models Feel the Sentiment? Investigating Emotion Vectors

Ali Hassan Khan, Saad Bin Ather, Muhammad Saif, Maryam Bashir, Hajra Waheed

原文摘要

Emotion vectors are directions in a language model's internal representations that are associated with emotional concepts. Prior work shows that these vectors can influence model behavior, but their role in sentiment classification remains unclear. This study investigates emotion directions in Qwen2.5-0.5B-Instruct and Qwen2.5-3B-Instruct. Eight directions extracted from GoEmotions are evaluated through sentiment probing, activation interventions, and supervised correction. Emotion-only probes achieve 88.66% and 90.70% accuracy on binary TweetEval. In exploratory matched-ablation experiments, raw emotion-space removal causes 2.39 and 1.10 percentage points more accuracy loss than matched isotropic random-subspace removal for 0.5B and 3B, respectively. All four TweetEval raw and denoised effects are significant after Holm adjustment across eight comparisons. An exploratory SST-2 extension shows smaller raw excess losses of 0.66 and 0.57 points, with no effects surviving Holm adjustment. Frozen sentiment-correction classifiers are also tested on 20,000 Amazon Polarity reviews. Emotion-based correction improves accuracy over uncorrected Qwen, but does not consistently outperform margin-only baselines. These results distinguish sentiment information available in model representations, the effects of changing those representations, and their practical value for classification. They do not establish a uniquely emotional mechanism.

cs.CL

版本更新 · v2arXiv:2505.02853

A Computational Model of Teacher-Student Co-Adaptation

Francesco Balzan, Pedro P. Santos, Maurizio Gabbrielli, Mahault Albarracin, Manuel Lopes

原文摘要

Effective teaching involves mutual adaptation: teachers adjust instruction based on student responses, while students actively seek information to resolve uncertainty. Yet many computational models of teaching treat instruction as a one-way process. This paper presents a Bayesian computational framework for studying teacher-student co-adaptation under partial observability in a stylized concept-learning task. Students are organized in heterogeneous groups that differ in which features of a target concept they can observe, and the teacher infers these constraints from limited feedback. We compare five interaction modes (active teaching, active learning, turn-based interaction, adaptive teaching and full co-adaptation) and three teacher-led controls across 100 independent matched simulation runs. Learner-initiated queries resolve information gaps left by the baseline teachers' stopping rules, while teacher-led continuation also achieves complete identification in the observed episodes. Bayesian belief tracking reduces the mean interaction steps required by full co-adaptation as teacher experience accumulates. At experience level 40, full co-adaptation requires fewer interaction steps on average than active learning, turn-based interaction and all three teacher-led controls, with complete observed coverage shared by these policies. Analyses by group and student type, together with sensitivity analyses, clarify the conditions and distributional limits of these results. The framework is interpretable and modular. Its findings provide a computational proof of concept for investigating interaction structure in heterogeneous groups, rather than direct evidence about classroom practice.

cs.CY · cs.AI · cs.LG

版本更新 · v2arXiv:2610.36672

Learning Where to Trust: Reliability-Guided Expert Routing and Velocity Gating for 3D Deformable Registration

Chenyu Guo, Wenjie Dai, Yiqian Chang, Zhiyuan Zhang, Yunfan Wei, Shuhan Qi, Tianrui Xu, Dong Liu 等 9 位作者

原文摘要

Deformable image registration relies on accurate anatomical correspondences. However, explicitly coupling local matching reliability with spatial context selection and deformation update strength remains insufficiently explored in learning-based registration. This challenge is particularly pronounced in homogeneous, weakly textured, and severely deformed regions, where ambiguous matches may induce erroneous deformation updates. We propose ReliMorph, a reliability-routed symmetric framework for 3D deformable registration that couples correspondence assessment with spatial context selection and update strength.Local correlation distributions characterize correspondence ambiguity using shared anatomical features with modality-specific adaptation. These reliability cues guide spatial expert fusion and gate residual velocities during coarse-to-fine refinement. Updated inverse-inconsistency feedback guides routing and gating at finer pyramid levels. To our knowledge, ReliMorph is the first 3D deformable registration framework to jointly condition spatial expert routing and residual velocity gating on correspondence reliability. Extensive experiments demonstrate that ReliMorph consistently outperforms competing methods in anatomical overlap, highlighting its effectiveness across unimodal and multimodal registration tasks.

cs.AI · cs.CV

版本更新 · v2arXiv:2609.03472

Override and Update in Restriction Categories

Jean-Simon Pacaud Lemay, Chad Nester

原文摘要

We study the override and update operators on partial functions from the perspective of restriction categories. We propose a definition of override restriction categories, in which both of the operators in question exist. We prove a number of results concerning these operators and their relationship to the structure of the ambient restriction category, as well as relating them to the existing literature on the override and update operators. We provide various examples of override restriction categories and in particular show that every classical restriction category is an override restriction category.

math.CT · cs.LO

新论文 · v1arXiv:2611.13742

Plug-and-Play ADMM for Inverse Problems with Flow Matching Denoiser

Dibyanshu Kumar, Magda Gregorova

原文摘要

Plug-and-Play (PnP) methods with generative priors have achieved strong performance in inverse problems, with recent flow matching models enabling fast and scalable reconstruction. However, a key challenge in PnP methods is maintaining consistency between data fidelity updates and the learned generative prior, as data-consistency steps can move iterates away from the flow trajectory. We propose an ADMM-based PnP framework for flow matching priors that enforces stronger consistency between the measurement model and the prior through auxiliary variables and dual updates. In addition, we introduce a trajectory correction mechanism that restores consistency with the flow via a combination of deterministic and stochastic projections. Our method provides a more principled integration of flow priors within PnP frameworks, achieving high-quality reconstructions with reduced computational cost.

cs.LG

新论文 · v1arXiv:2611.13741

Retargetable Compilation for Tensor Kernels via a Unified Layout Abstraction

Likai Ma, Renze Chen, Tianqi Li, Yuhao Luo, Youwei Xiao, Size Zheng, Xiuhong Li, Yun Liang

原文摘要

Modern hardware accelerators achieve high performance through specialized instructions coupled with tightly managed memory hierarchies. These instructions impose strict layout requirements on their operands: where tensor fragments reside, how they are organized, and how parallel units access them. Such instruction-visible layout is critical to kernel performance, as it determines whether instructions execute correctly and how much data movement they incur. However, existing compilers either scatter layout requirements across handwritten programs and local scheduling rules, or provide layout representations and conversions specific to a single class of targets. Both approaches expose the same abstraction gap: the absence of a unified model for instruction layout requirements across backends. This paper presents Arknife, a retargetable compiler that treats instruction-visible layout as first-class instruction semantics. Its central idea is a constraint-based layout algebra: tensor layouts map logical axes to hardware axes spanning parallel levels and memory spaces. Instruction operands declare layout requirements, and target-provided repairs resolve conflicts. Layouts are then solved globally across the program. ISA-specific layout facts are supplied by target-side instruction descriptions rather than hardcoded in the compiler. Retargeting reuses the layout algebra and solver while defining the new target's instructions and their operand requirements. We evaluate Arknife across x86 CPU, Hexagon NPU, and NVIDIA A100 GPU. Arknife matches cuBLAS on A100, and on x86 and Hexagon outperforms vendor-optimized libraries by $2.17\times$ and $3.78\times$ and the retargetable compiler MISAAL by $5.08\times$ and $4.53\times$, respectively.

cs.PL

新论文 · v1arXiv:2611.13740

Multi-Objective Scheduling of LLM-Based Multi-Agent Workflows in Cloud Computing

Goshgar Can Ismayilov

原文摘要

Large language models (LLMs) have been increasingly composed into multi-agent workflows to accomplish complex and multi-step tasks. As the open-weight models continue to close the performance gap with the proprietary ones, model parameters are becoming a less significant source of competitive advantage in the artificial intelligence market. Yet how these models are efficiently scheduled onto distributed infrastructure such as the cloud, with respect to overall latency, monetary cost and resource utilization, remains largely unaddressed in the literature despite being an increasingly critical problem. Existing agentic workflow frameworks mostly focus on output quality and task success rates over popular benchmarks, rarely accounting for execution dynamics of LLM-based agents such as inference latency, computation power of heterogeneous resources, cloud-specific billing period and resource provisioning overheads. Therefore, this paper formulates multi-agent scheduling in cloud computing as a multi-objective optimization problem that jointly minimizes makespan and cost while maximizing resource utilization. Building on this formulation, we propose MO-SAIC (Multi-Objective Scheduling of Multi-Agent Workflows in Cloud Computing), a scheduling framework comprising four multi-objective schedulers with Non-Dominated Sorting Genetic Algorithm II (NSGA-II), Weighted-Sum Genetic Algorithm (W-GA), a multi-objective adaptation of Heterogeneous Earliest Finish Time (MO-HEFT) and a random baseline (RAND). We evaluate the schedulers from the workflow scheduling, multi-objective optimization and system perspectives to measure their overall performance, quality of their Pareto-optimal fronts and impacts of workflow topology, cloud resource composition and scalability parameters. We report the experimental results with their statistical significance via the Wilcoxon test.

cs.DC

新论文 · v1arXiv:2611.13739

Effects of Laser Beam Width and Measurement Noise on Tree Diameter Estimation in Laser Scanning

Jesse Muhojoki, Nuutti Ervasti, Eric Hyyppä, Aapo Erkkilä, Eppu Honkanen, Tuomas Yrttimaa, Mikko Vastaranta, Juha Hyyppä

原文摘要

Laser scanning has been utilized for decades to measure tree structure and geometry. Despite continuous advances in sensor technology, uncertainties arising from scanner characteristics and measurement conditions has remained relevant sources of error. In particular, factors such as laser beam diameter can introduce both systematic and random errors in the reconstructed tree geometry. This study investigates the main sources of these errors in mobile laser scanning (MLS) and quantifies their effects on stem curve (stem diameter) estimation. We discovered through simulations and experiments that the heteroscedasticity (difference in variance in ranging and scan angle) in the measurement noise is a key factor along with the beam width of the lidar, which cause the bias of the diameter estimates to depend not only on distance, but also on the tree diameter. We demonstrated that this bias can be reliably predicted and negated for trees with a diameter at the breast height greater than 10 cm using technical specifications of the sensor without any additional calibration. In experiments, the proposed bias compensation method reduced the root-mean-square error of stem diameter estimates to sub-centimeter level on boreal forest test sites. However, for small trees with diameter below 10 cm, the diameter bias becomes sensitive to the diameter of the tree$\unicode{x2013}$an unknown factor$\unicode{x2013}$and other factors, such as different bark and out-of-roundness of the stem, limiting the precision of lidar for measuring geometry of trees and applicability of the presented method.

cs.CV

版本更新 · v2arXiv:2610.35495

Query Complexity of Learning Axis-Aligned Partitions

Hadley Black, Arya Mazumdar, Barna Saha, Geelon So

原文摘要

This work establishes the query complexity of learning high-dimensional boxes in the exact query learning setting. Let $X \subset \mathbb{R}^d$ be a set of $n$ points, labeled by a collection of $k$ boxes: the label of each point in $X$ is determined by the unique box containing it. A learner aims to exactly recover the labels for every point in $X$ given access to a label oracle. We consider three increasingly-structured settings. In the most general setting, there are no conditions on the boxes, and they may overlap. We show that CAL (Cohn-Atlas-Ladner 1994), a classical active learning algorithm, is minimax-optimal with query complexity $Θ(kd \log (n/kd))$. When the boxes are disjoint, we examine two regimes. In the large-$k$ regime, CAL remains minimax-optimal. For the constant-$k$ regime, an optimized variant of the Halving algorithm (Hegedüs 1995) can beat CAL by a $\log(d)$ factor. Finally, in the most-structured settings, the boxes correspond to the leaves of a constant-sized decision tree. We prove a tight query complexity of $Θ(d + \log n)$ that is additive in $d$ and $\log n$, generalizing a recent result (Black-Larsen-Mazumdar-Saha-So 2026) that establishes the query complexity of learning decision stumps.

cs.DS · cs.CG · cs.LG