跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

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

部分采集异常
正在读取账号与研究记录…

全站更新概况

+367新增论文
+288其中 AI 相关
+33已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 10:18 · 全站最近入库：2026-11-09 10:17各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 10:33 — 2026-11-09 10:33（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-09 10:18最近发现新增版本：2026-11-09 10:17库内论文最新更新时间：2026-11-06 12:44

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

17,467 已收录论文14,949 AI 相关4,222 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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

找到 3,363 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 10:16（北京时间）
新论文 · v1arXiv:2611.08035

Should We Pay This Much for Robustness? Efficient Proxy Certificates with Marginal Guarantees

Soroush H. Zargarbashi, Mohammad Sadegh Akhondzadeh, Aleksandar Bojchevski

原文摘要

Modern classifiers remain sensitive to small input perturbations, while strong model-agnostic robustness certificates such as randomized smoothing are often too expensive for deployment, requiring an extensive number (e.g. 2000) of model forward passes per input. We propose a framework that delegates certification to a cheap proxy function while statistically controlling its deviation from the original sound certificate. Given an exchangeable unlabeled calibration set, we tune the proxy via robust conformal risk control to guarantee a bounded marginal (rather than pointwise) false-approval rate: the probability, over future inputs, that the proxy accepts an input whose prediction is flipped due to perturbation. The resulting proxy certificate can be used either as a standalone marginal certificate or as a fallback mechanism that invokes the expensive certificate only when the proxy rejects. We provide both single-sample and sample-heavy calibration recipes. Empirically, as a standalone certificate our method reduces the test-time certification cost to a single model forward while retaining much of the certified performance of randomized smoothing at small radii, and as a fallback it recovers the certified ratio of randomized smoothing at a more modest speedup. This enables cheap yet effective robustness guarantees for larger architectures such as vision transformers and language models.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08032

Reproducing Kernel (Quasi-)Banach Spaces with the $\ell^p$ Coefficient Norms

Tianfang Wang, Guohui Song, Haizhang Zhang

原文摘要

This paper advances the theory of reproducing kernel Banach spaces (RKBSs) by investigating the general $\ell^p$ regularization framework, with a particular focus on the non-convex regime $0<p<1$. While our preceding work established the foundation for RKBSs with the $\ell^1$ norm, the pursuit of stronger sparsity---closer to the $\ell^0$ pseudo-norm---naturally motivates this exploration into $\ell^p$ quasi-norms. For $0<p<1$, we construct reproducing kernel quasi-Banach spaces (RKQBSs) with $\ell^p$ quasi-norms and establish existence and sparsity results for interpolation and regularized learning under appropriate assumptions. We characterize the linear and relaxed representer theorems in terms of a generalized Lebesgue constant and derive bounds under kernel decay, sample spacing, and stability assumptions. For $p>1$, we construct RKBSs using a fixed countable dictionary, establish minimizer existence, and identify the optimal relaxed representer factor through an off-sample coefficient operator. These results reveal fundamental differences between the regimes $0<p<1$, $p=1$, and $p>1$. Numerical experiments compare the accuracy and sparsity of solutions for these three cases.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.10456

Integrating Background Knowledge for Scalable Causal Discovery

Mátyás Schubert, Theofanis Aslanidis, Tom Claassen, Sara Magliacane

原文摘要

Expert background knowledge is often available in practical applications of causal discovery. Such constraints on the true causal graph can help causal discovery in terms of identifiability of causal effects and accuracy of the learned structure, but also in reducing the space of candidate causal graphs. As causal discovery can become computationally expensive for large number of variables, it is crucial to utilize background knowledge effectively during the causal discovery process. However, most current methods only use background knowledge in a postprocessing step after causal discovery to refine the learned graph. In this work, we develop a framework for utilizing background knowledge during the causal discovery process, focusing especially on scalable causal discovery methods that recover only a subset of the whole graph. We implement our framework for multiple algorithms and empirically show that utilizing background knowledge can both reduce computational requirements and increase the quality of the learned structures.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08021

GTAFL: Addressing Test-Agnostic Long-Tailed Federated Learning in Medical Image

Guangyu Chen, Jingyun Zeng, Hui Jiang

原文摘要

In healthcare, protecting patient privacy is crucial due to the sensitivity of medical data and its extensive accessibility. Federated Learning (FL) offers a decentralized and privacy-preserving training paradigm, making it an ideal solution for healthcare applications. A critical challenge in healthcare is that real-world medical data often exhibits long-tailed distributions in local and global views. Existing methods addressing long-tailed FL problem typically assume that the model will be evaluated on uniform test data distribution. However, practical test data in healthcare systems is often agnostic and unpredictable, leading to potential model failures in real-world scenarios. In this paper, we introduce a novel task termed Test-Agnostic Long-Tailed Federated Learning and propose GTAFL, a comprehensive framework to address this challenge. During the training stage, GTAFL employs adaptive re-sampling, expert classifier retraining, and self-supervised learning to correct biased classifiers and distorted feature spaces caused by long-tailed training distributions. During the inference stage, an ensemble mechanism combines retrained expert classifiers to handle test data with unknown distributions. Extensive experiments on CIFAR10 and two medical datasets manifest that our framework outperforms other state-of-the-art methods. The code is available at https://github.com/cgy-lavine/GTAFL

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2508.05844

Online Budget Allocation with Censored Semi-Bandit Feedback

François Bachoc, Nicolò Cesa-Bianchi, Tommaso Cesari, Roberto Colomboni

原文摘要

We study a stochastic budget-allocation problem over $K$ tasks. At each round $t$, the learner chooses an allocation $X_t \in Δ_K$. Task $k$ succeeds with probability $F_k(X_{t,k})$, where $F_1,\dots,F_K$ are nondecreasing budget-to-success curves, and upon success yields a random reward with unknown mean $μ_k$. The learner observes which tasks succeed, and observes a task's reward only upon success (censored semi-bandit feedback). This model captures, for instance, splitting payments across crowdsourcing workers or distributing bids across simultaneous auctions, and subsumes stochastic multi-armed bandits and semi-bandits. We design an optimism-based algorithm that operates under censored semi-bandit feedback and assumes access to an exact maximization oracle. Our main result is an instance-dependent bound showing that in diminishing-returns regimes, the regret of this algorithm scales polylogarithmically with the horizon $T$ without any ad hoc tuning. For general nondecreasing curves, we prove that the same algorithm (with the same tuning) achieves a worst-case regret upper bound of $\tilde O(K\sqrt{T})$. Finally, we establish a matching worst-case regret lower bound of $Ω(K\sqrt{T})$ that holds even for full-feedback algorithms, highlighting the intrinsic hardness of our problem outside diminishing returns.

cs.GT · cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08016

Learning Dynamics of On-Policy Distillation

Guan Zhe Hong, Sumeet Ramesh Motwani, Liang Chen, Yangchen Pan, Junchi Yu, Jialin Yu, Philip Torr, Yi Ren

原文摘要

On-policy distillation (OPD) is emerging as an important paradigm for language-model post-training, combining dense teacher supervision with training on student-generated trajectories. This creates a feedback loop where each update changes the student and thereby the training distribution that generates subsequent updates. Yet, how this feedback shapes learning and generalization remains poorly understood. We conduct a mechanistic analysis of OPD's learning dynamics, distinguishing the two feedback loop stages: conversion of the distillation signal into parameter updates, and broadcast through which these updates change predictions across prefixes and reshape the rollout distribution. This framework helps us understand both limited student responsiveness despite substantial teacher-student disagreement, and degeneration when updates that improve local teacher agreement also increase the probability of unsuccessful continuations, exposing the student to unreliable supervision in subsequent rollouts. Finally, we show that offline distillation can prepare a student for OPD without significantly improving immediate held-out accuracy. While OPD alone may degrade generation, it can yield substantial accuracy gains after sufficient offline preparation. Together, our results connect teacher supervision, student geometry, and the evolving rollout distribution in determining the learning dynamics of OPD and its effects on downstream performance.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2607.04364

RL Forgets! Towards Continual Policy Optimization

Mao-Lin Luo, Zhe-Xu Wang, Zi-Hao Zhou, Bo Ye, Jian Zhao, Min-Ling Zhang, Tong Wei

原文摘要

Continual post-training is becoming a central paradigm for adapting vision-language models to evolving tasks. Recent studies report that reinforcement learning is less prone to forgetting than supervised fine-tuning, motivating the view that RL is inherently resistant to forgetting. However, this view remains insufficiently validated, as existing evidence is largely drawn from outdated or homogeneous benchmarks. We revisit this assumption by introducing MRCL, a Multimodal Reasoning Continual Learning benchmark built from recent and diverse multimodal reasoning tasks. Experiments on MRCL show that standard reinforcement learning still suffers from catastrophic forgetting during continual post-training. We trace the failure to an objective mismatch. The KL regularization used in common policy optimization methods is evaluated on current-task data, whereas forgetting is caused by behavioral drift on prior-task distributions. To address this problem, we propose Continual Policy Optimization (CPO), a replay-free method grounded in a prior-task behavioral KL objective. CPO derives a local Fisher surrogate from the historical KL objective and uses parameter movement as a gradient-free proxy for Fisher sensitivity, enabling sparse regularization with negligible additional overhead. Experiments on three model scales and comparisons with multiple RL baselines show that CPO consistently reduces forgetting while maintaining effective adaptation and preserving broader pretrained capabilities. The implementation code is available at https://github.com/MaolinLuo/CPO.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07998

Towards Multiscale Molecular Representation Learning through Geometry-Based Fragmentation for Polymer Property Prediction

Makoto Takamoto, Chaitanya Sampara, Viktor Zaverkin, Daniel Oñoro-Rubio, Mathias Niepert

原文摘要

It is well established that molecular substructures can contribute unequally to chemical and physical properties, with specific motifs or side chains often playing dominant roles. Fragment-based representations have therefore emerged as an effective strategy for incorporating chemically meaningful inductive biases, as exemplified by molecular fingerprints and fragment-based attention mechanisms. However, many existing fragmentation-based machine learning methods rely on predefined chemical rules, which may yield suboptimal fragmentation for previously unseen or chemically unfamiliar structures and often overlook the importance of multiscale molecular representations. To address these limitations, we formulate molecular fragmentation as a radius-constrained optimization problem inspired by the k-center formulation, where the number of clusters is not fixed a priori but emerges from the specified radius, and propose a geometry-based fragmentation method that partitions arbitrary molecular or material structures using largely geometric information, without relying on predefined chemical fragmentation rules. The method provides flexible control over fragment size, enabling the construction of multiscale fragment representations for scale-adaptive modeling. Building on this framework, we develop a geometric fragment-based attention mechanism that integrates multiscale structural information and incorporate it into a multimodal machine learning model combining p-SMILES representations with three-dimensional (3D) conformational information. Experiments on a benchmark polymer dataset show that incorporating 3D conformational information improves prediction accuracy for several properties over models based exclusively on p-SMILES representations. Explainable artificial intelligence analyses further provide insights into the physical relevance of the learned representations.

cs.LG · cond-mat.mtrl-sci · physics.chem-ph

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2511.08371

Multi-objective Hyperparameter Optimization with Expert Priors

Soham Basu, Nastaran Alipour, Frank Hutter, Danny Stoll

原文摘要

While Deep Learning (DL) experts often have prior knowledge about which hyperparameter settings yield strong performance, only few Hyperparameter Optimization (HPO) algorithms can leverage such prior knowledge and none incorporate priors over multiple objectives. As DL practitioners often need to optimize not just one but many objectives, this is a blind spot in the algorithmic landscape of HPO. To address this shortcoming, we propose the novel problem setting of multi-objective HPO with expert priors and introduce PriMO, the first HPO algorithm that can integrate user beliefs over multiple objectives. We show PriMO achieves state-of-the-art performance across 8 DL benchmarks in the multi-objective and single-objective setting. Further, we demonstrate that PriMO remains state-of-the-art at large scales by optimizing a vision-language model over three objectives.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2606.13657

Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation

Guo Yu, Wenlin Liu, Yulan Hu, Hao-Xuan Ma, Jun-Peng Jiang, Han-Jia Ye

原文摘要

On-policy distillation (OPD) has recently become a prominent post-training recipe by combining two desirable ingredients: on-policy student-generated trajectories and dense token-level teacher supervision. Yet how this hybrid training regime shapes a model remains poorly understood. We characterize the sparsity and geometry of OPD parameter updates across several language and vision-language model pairs and application settings. OPD updates are small and coordinate-sparse, while remaining distributed across layers and modules. This sparse support is operationally meaningful: masked training on the discovered subnetwork nearly recovers full-training performance. At the matrix level, the updates are numerically full-rank but spectrally concentrated. Their visible supports avoid coordinates emphasized by the source's principal structure and favor low-magnitude source coordinates, while the source singular-value spectra change little. Together, these findings show that OPD exhibits important weight-space signatures of on-policy post-training despite using dense teacher supervision.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08558

Minimum-Sufficient Knowledge and Computation for Wind Energy Predictive Analysis

Purbak Sengupta, Aparna S. varde, Emil Jørgensen Njor

原文摘要

Resource-constrained cyber-physical decision systems often apply fixed sensing, knowledge, and computational pipelines despite state-dependent information needs. We introduce Minimum-Sufficient Knowledge and Computation (MSKC), a resource-aware computing principle: select the least-costly route meeting decision-risk and deployment constraints, escalating only when cheaper routes are insufficient. As proof of concept, we isolate adaptive knowledge routing, the decision underlying Knowledge-Guided Machine Learning (KGML), which conventionally injects external knowledge unconditionally rather than only where needed. We instantiate this for wind ramp-event predictive analysis, an edge-oriented decision-support task, evaluating local, relational, and physics-informed routes with a state-aware gate on publicly available real data from two wind farms. We establish conditions for feasibility preservation, cost dominance, and strict expected savings over always-on routing. At a 35.9% relational-knowledge injection rate, adaptive routing is statistically indistinguishable from always-on injection on the reported metrics while reducing knowledge calls by 64%, supporting sustainable, Green-IT-aligned deployment. These results support MSKC's premise that uniformly maximal intelligence is unnecessary. This offers intelligent data analysis for big data streams: the analysis itself decides, per state, how much knowledge and computation the data warrant.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2608.08600

Population-Scalable Multi-Agent World Modeling across Scene Geometries

Renjie Zhao, Yuxiang Wu, Mingyu Zhang, Jiaxin Li, Sisi Li, He Li, Yimin Sheng, Tianxi Tan 等 12 位作者

原文摘要

World models have recently achieved impressive progress in visual prediction and interactive generation, but extending them to multi-agent environments introduces a fundamental scalability challenge. Existing methods generally assume a fixed number of agents during training and inference, which ties the model to a pre-determined agent population and limits inference-time scalability. Our key insight is that cross-view consistency should arise from a shared world state whose evolution does not assume a predefined number of agents, while agent-specific observations should be generated by querying this state through a unified rendering interface. Based on this insight, we propose Khora, a scalable multi-agent world model that supports inference-time expansion to arbitrary numbers of agents without retraining. Our framework decouples world-state evolution from visual rendering and introduces a population-agnostic rendering mechanism for incorporating other agent information. This design maintains cross-view consistency through the shared world state rather than through dense interactions among observation streams inside the expensive video generator, enabling approximately linear practical scaling with the number of queried views. Qualitative experiments demonstrate that our approach generalizes to unseen numbers of agents while maintaining visual quality and multi-agent consistency. We further implement a real-time interactive system to demonstrate scalable open-world simulation.

cs.CV · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07976

QRAE: Query-Relevant Attention Entropy for Context Compression in DeepSearch Agents

Yingjie Tan, Haiquan Qiu, Quanming Yao, Manyi Zhong, Xianzhi Yu, Yaqing Wang

原文摘要

DeepSearch LLM agents repeatedly search and carry retrieved sources into subsequent reasoning steps. This expanding context increases token consumption and latency, although many results do not contribute to later reasoning. We propose Query-Relevant Attention Entropy (QRAE), an online context compression method that uses sparse evidence-assessment heads to decide which intact retrieved chunks should persist across reasoning steps. It scores bounded candidate batches through paired prefills: a query-free control suppresses shared attention responses, while normalized entropy measures the breadth of the positive response within each chunk. High-scoring chunks enter a persistent evidence whitelist and are included in the reasoning context. Uncertain chunks remain outside the reasoning context but are retained in a candidate cache, where they can be retrieved for later reevaluation. QRAE requires neither an additional generative compression pass nor modification of the attention operator. Across multiple DeepSearch benchmarks and reasoning models, QRAE improves task success by an average of 2.35 percentage points and reduces end-to-end latency and reported token usage by an average of 30% and 45%, respectively. These benefits generalize to a model with nearly 100B parameters.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07973

Tight Asymptotic Bounds on the Maximum Number of Linear Regions of Piecewise-Linear Kolmogorov--Arnold networks

Ye Su, Yong Liu

原文摘要

Schoots et al.~\citep{schoots2025relating} (AISTATS 2025) established a generally loose upper bound on the number of linear regions of continuous piecewise-linear (CPWL) Kolmogorov--Arnold networks (KANs), without providing a lower bound. We consider a $T$-layer network with width vector $\mathbf n=(n_0,\ldots,n_T)$, input dimension $n_0=d$, output width $n_T=1$, and at most $k\geq2$ affine segments per edge. Our matching upper and lower bounds determine the tight growth order $Θ_{\mathbf n}(k^{\sum_{\ell=1}^{T}ρ_{\ell-1}})$ in $k$, where $ρ_{\ell-1}:=\min_{0\leq s\leq\ell-1}n_s$. When every hidden width is at least $d$, the tight order simplifies to $Θ_{\mathbf n}(k^{dT})$. The upper bound of \citep{schoots2025relating} is $k^{\sum_{\ell=1}^{T}n_{\ell-1}n_\ell}$. Our upper bound improves it by a factor of $Θ_{\mathbf n}\!\left(k^{\sum_{\ell=1}^{T}n_{\ell-1}n_\ell-\sum_{\ell=1}^{T}ρ_{\ell-1}} \right)$, with strict asymptotic improvement whenever a hidden layer has width greater than one. We further compare CPWL KANs with rectified linear unit (ReLU) networks using dense parameterizations with at most $Λ$ parameters per model and the same fixed nonlinear depth $T$. Counting trainable knot locations and optimizing the widths and $k$, we prove that the maximum region count of CPWL KANs divided by that of ReLU networks is $Θ_{d,T}(Λ^{d\lfloor T/2\rfloor})$ as $Λ\to\infty$, yielding a polynomial advantage for KANs when $T\geq2$. These tight bounds characterize the attainable geometric complexity of CPWL KANs, providing a foundation for understanding their expressive power and guiding architectural design.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.41697

TSBPO: Tree-Structured Branching for Policy Optimization in Interactive Language Agents

Rui Yu, Chong Mu, Jinchuan Zhang

原文摘要

Terminal feedback in multi-turn agent training leaves both rollout allocation and local credit underdetermined. Dynamics-Predictive Sampling (DPS) [9] provides a task-level predictive sampling reference, but interactive agents also need to choose which visited states merit further continuations. We introduce TSBPO with two method components. A lightweight, fine-grained Root/Branch budget allocator distributes factual rollouts across tasks and additional suffixes across replayable states using likelihood-fitted estimates of terminal-outcome contrast. On the resulting physical rollout trees, a tree-aware step-level credit assignment algorithm compares immediate sibling segments and assigns their local outcome contrasts to the turns they contain. Exact task/observation groups provide a complementary step term. The allocator selects what to sample; observed outcomes determine the subsequent credit. With a Qwen2.5-1.5B actor, fixed checkpoints attain 97.79% seen and 96.64% unseen stochastic success on ALFWorld, and an 81.07% per-episode success rate over six stochastic episodes for each of the 500 WebShop test goals. At the WebShop update-100 checkpoint, removing the observation-group step term yields 75.93% under the same evaluation. These results describe the evaluated training configurations on two interactive benchmarks.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.20687

Neuronal Self-Adaptation Enhances Capacity and Robustness of Representation in Spiking Neural Networks

Zhuobin Yang, Liao Yu, Yeyao Bao, Jian Zhang, Liangfu Lv, Daqing Guo, Xiaohong Li, Yunliang Zang

原文摘要

Spiking Neural Networks (SNNs) are promising for energy-efficient, real-time edge computing, yet their performance is often constrained by the limited adaptability of conventional leaky integrate-and-fire (LIF) neurons. Existing LIF models struggle with restricted information capacity and susceptibility to noise, leading to degraded accuracy and compromised robustness. Inspired by the dynamic self-regulation of biological potassium channels, we propose the Potassium-regulated LIF (KvLIF) neuron model. KvLIF introduces an auxiliary conductance state that integrates membrane potential and spiking history to adaptively modulate neuronal excitability and reset dynamics. This design extends the dynamic response range of neurons to varying input intensities and effectively suppresses noise-induced spikes. We extensively evaluate KvLIF on both static image and neuromorphic datasets, demonstrating consistent improvements in classification accuracy and superior robustness compared to existing LIF models. Our work bridges biological plausibility with computational efficiency, offering a neuron model that enhances SNN performance while maintaining suitability for low-power neuromorphic deployment.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07959

CoRD: Coupled Rollouts Fill the Blind Spot of On-Policy Distillation

Guhan Chen, Bohan Li, Jun Rao, Hejin Wang, Songtao Tian, Yexin Xie, Xiaojun Meng, Peng Yuan 等 11 位作者

原文摘要

On-policy distillation trains a student on its own rollouts, so states the teacher would reach but the student does not are seldom supervised. We introduce CoRD (coupled-rollout distillation), which keeps the on-policy loss and moves only the distribution of training states toward the teacher, drawing rollouts from a geometric interpolation of student and teacher through the maximal coupling of speculative decoding. The coupling keeps the student's token wherever the two distributions agree and otherwise substitutes a token from the part of the target the student underweights, so interventions are as rare as any exact sampler allows and recede as the student learns. Across six base students from two model families (Qwen3 and Qwen3.5, 0.6B to 4B), CoRD raises average pass@1 over on-policy distillation by 0.9 to 2.0 points and pass@8 by 1.2 to 3.4 points on five public math benchmarks at equal steps and data. On frozen teacher-reached states, a 4B student trained with CoRD reaches in 16 steps a gap closure that on-policy distillation does not reach in 80, and substitution rules intervening at least as often in other directions fall short of CoRD.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.14414

CytoBERT: A Foundation Model for Cytometry Data

Syed Abdul Haseeb Qadri, Bjarne C. Hiller, Felix Blanke, Vanja Sophie Cangalovic, Kutalmış Coşkun, Amin Mirzaei, Tom Siegl, Sebastian Bader 等 10 位作者

原文摘要

Cytometry measures the complex characteristics of single cells (e.g., counts and protein expression of immune cells) and is widely used across immunological research and clinical settings. However, cytometry data is highly heterogeneous and unstandardized due to experimental protocols and the choice of measured features. While machine learning methods hold the potential to gain deeper insights into cell biology, these challenges make them difficult to apply and transfer across studies. Recent advances in foundation models can alleviate these issues, but corresponding approaches are still scarce in this field. To address this, we provide CytoBERT, a publicly available, open-source, open-weight foundation model for single-cell cytometry data with variable marker panels. CytoBERT is pretrained in a self-supervised manner on a large-scale cytometry corpus (15 human datasets with heterogeneous marker panels and more than 50 million cells) curated through marker standardization, enabling it to learn transferable inter-marker relationships within cells. Fine-tuning CytoBERT for sample-level classification demonstrates that transfer learning across heterogeneous cytometry datasets is feasible, providing a starting point for scalable, generalizable cytometry analysis. Code is available at GitHub.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07953

A Behavioural Framework for Predicting and Understanding Loss of Control in Frontier Artificial Intelligence Systems

Yao Huang, Yichi Zhang, Yifan Wang, Yitong Sun, Haoyu Dong, Jifan Ma, Jinzhe Tu, Xiaojian Li 等 11 位作者

原文摘要

Frontier artificial intelligence (AI) systems are increasingly operating over longer horizons with diminishing human oversight, raising the risk of loss of control: systems acting beyond effective human control with potentially irreversible consequences. Because such failures may become observable only after containment is difficult, they must be assessed prospectively. We introduce a behavioural framework that decomposes loss-of-control risk into three factors: misaligned motive, harm-enabling capability, and monitoring evasion. We operationalise these factors through 13 measurable aspects and 29 evaluation tasks, whose scores are combined into a single loss-of-control (LoC) score. Across 13 frontier models, the LoC score shows strong prospective validity, correlating with failure rates in contained long-horizon risk scenarios (Pearson r = 0.84). Risk varies systematically across models and cannot be explained by capability alone. We further show that the framework can guide targeted mitigations: fine-tuning and monitoring directed at diagnosed vulnerabilities reduce failure rates while largely preserving general performance. These results provide a practical basis for predicting, understanding, and mitigating loss-of-control risk before it materialises.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07952

Invariance before structure: two modes of emergent compression in representation learning

Hardik Rajpal, Dan Goodman

原文摘要

Learned representations show striking invariance across biological and artificial neural networks, with different substrates and variations driven by drift, heterogeneity and initialisation. To understand this invariance, we propose Emergent Adaptive Representation Learning (EARL), a framework that distinguishes two modes of emergence in learned representations: state-space compression, where a learned representation gains predictive power over its own future beyond what the network's units can predict individually, and parameter-space compression, where networks with different micro-level parameters converge to the same representation. We formalise both as Fisher sensitivities and introduce ensemble-level information-theoretic measures for each. In a recurrent reservoir with a trained bottleneck, parameter-space compression rises within the first few epochs of training and partly independently of the task, whereas state-space compression rises about 30 epochs later and only when the network begins to learn the temporal structure of the task. These results suggest that invariance to the substrate and task-specific emergent structure are acquired in distinct phases of learning.

cs.LG · cs.NE · q-bio.NC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07950

Leakage- and Label-Aware Benchmarking of Class-Imbalance Strategies for Multimodal Chest X-Ray and EHR Classification

Dang-Khoa Bui, Quang-Huy Tran, Minh-Khoi Nguyen-Bui, Duc-Tuan Ngo, Thanh-Trong Tran, Tuan-Khoi Nguyen, Hoang-Anh Ngo

原文摘要

Benchmarks of class-imbalance strategies for multimodal chest X-ray (CXR) and electronic health record (EHR) prediction are often evaluated on record-level splits of cohorts in which one patient contributes several radiographs. We audit such a benchmark on 29,083 MIMIC-CXR radiographs of 10,479 patients with eight diagnosis targets. First, the record-split benchmark was misleading: a lookup table that copies the label of a development-set radiograph with the same EHR vector nearly matched the best model, and on unseen patients every model fell to the level of predicting every case positive. Second, tracing the labels back to MIMIC-IV explained why: each patient's labels are keyword matches on the diagnosis codes of a single admission, copied, with one EHR vector per patient, to all of the patient's radiographs, so about a third of the radiographs carry labels that differ from the codes of their own admission. Third, under patient-separated evaluation with admission-aligned and rule-refined labels, the initial conclusions do not hold: in the evaluated configurations no imbalance strategy raised the observed mean macro F2 over no augmentation by more than 0.01, tuned tree ensembles showed no consistent advantage over tuned logistic regression, and the released EHR variables stayed at the level of the all-positive baseline, whereas the diagnostic history available at imaging time and image embeddings exceeded it, including, with rule-refined labels, a CheXpert-trained encoder that never saw these radiographs; RAD-DINO had seen 96.6% of them during self-supervised pretraining. Adding either encoder to the diagnostic history gave no statistically significant F2 gain; exploratory AUROC gains were significant with RAD-DINO but not with DenseNet. We provide reusable diagnostics, a leakage-aware protocol and a checklist.

cs.LG · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.19969

Your Neighbors Know: Leveraging Local Neighborhoods for Backdoor Detection in Decentralized Learning

Sayan Biswas, Antoine Boutet, Davide Frey, Romaric Gaudel, Rachid Guerraoui, Maxime Jacovella, Anne-Marie Kermarrec, Dimitri Lerévérend 等 10 位作者

原文摘要

Decentralized learning (DL) is an emerging machine learning paradigm where nodes collaboratively train models without a central server. However, the collaborative nature of DL makes it vulnerable to backdoor attacks, where a model is taught to behave normally on standard inputs while executing hidden, malicious actions when encountering data with specific triggers. Backdoor attacks in DL remain understudied and existing defenses often overlook DL constraints. We introduce Argus, a novel backdoor detection framework native to DL that requires neither a central coordinator nor prior knowledge of the trigger. In Argus, honest nodes locally analyze received model updates to identify potential backdoor triggers. Nodes then collectively share their triggers with their neighbors and use a structural similarity metric to separate true backdoors from false alarms induced by data heterogeneity. A key insight is that false positive triggers exhibit inconsistencies across participants while true positive ones show consistent patterns. Model updates that fail this collaborative test are rejected, and persistently malicious senders are eventually evicted. We provide the first theoretical convergence guarantees for a DL-specific backdoor detection mechanism, showing that filtering out suspicious model updates with high probability preserves a convergence rate comparable to standard DL. We implement and evaluate Argus on three standard datasets and against three state-of-the-art baselines. Across settings, Argus reduces attack success rates by up to 90 points compared to no defense, while preserving model utility within 5 percentage points of an omniscient oracle. Furthermore, the effectiveness of Argus compared to baselines improves as data heterogeneity increases.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07937

Joint Modeling of Conditional Mean and Variability in Multilevel Functional Data: Application to Postprandial Glucose Trajectories in the AEGIS Study

Yang Xiao, Francisco Gude, Marcos Matabuena

原文摘要

Functional data analysis provides a framework for studying time-varying associations between covariates and high-frequency biological signals. In digital health, participants often contribute repeated functional trajectories, yet existing multilevel regression methods largely focus on the conditional mean, overlooking variability and its role in biological heterogeneity. We propose a heteroskedastic functional mixed-effects regression framework that jointly models the conditional mean and variance of repeated trajectories, with participant-specific random effects in both components. We also develop a participant-level bootstrap to quantify uncertainty in estimated functional parameters. We apply the method to postprandial glucose trajectories from the AEGIS study. Premeal glucose, carbohydrate intake, and meal type show distinct time-dependent associations with glucose variability, whereas HbA1c is more strongly associated with the conditional mean than with variability. Substantial between-participant differences in residual variability remain even after accounting for observed covariates. These findings show that modeling conditional variability alongside the mean provides insights into glucose regulation and individual heterogeneity that mean-focused analyses may miss. More broadly, the proposed framework enables joint characterization of average responses, variability, and participant-specific heterogeneity in repeated biological signals.

stat.ML · cs.LG · stat.AP · stat.ME

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2506.08911

Implementing Keyword Spotting on the MCXN947 Microcontroller with Integrated NPU

Petar Jakuš, Hrvoje Džapo

原文摘要

This paper presents a keyword spotting (KWS) system implemented on the NXP MCXN947 microcontroller with an integrated Neural Processing Unit (NPU), enabling real-time voice interaction on resource-constrained devices. The system combines MFCC feature extraction with a CNN classifier, optimized using Quantization Aware Training to reduce model size with minimal accuracy drop. Experimental results demonstrate a 59x speedup in inference time when leveraging the NPU compared to CPU-only execution, achieving 97.06% accuracy with a model size of 30.58 KB, demonstrating the feasibility of efficient, low-power voice interfaces on embedded platforms.

cs.HC · cs.AR · cs.LG · cs.PF · cs.SD

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07934

The Blindfolded Controller: Decision Model-Guided Training for Reinforcement Learning

Muhammad Ibrahim Khan, Aniket Dixit, Faizan Ahmed, James Brusey

原文摘要

Reinforcement learning (RL) provides a framework for continuous improvement through interaction with an environment. However, RL agents struggle against tasks that offer exploration challenges and sparse rewards, because learning efficient policies from scratch is slow and sample-inefficient. In contrast, decision models (DMs), given a description of the environment and task, can perform well in sparse-reward tasks, but, as they do not learn from reward, they are not able to improve towards the optimal solution. In this paper, we present Decision Model-Guided Training (DMGT), a technique that uses a DM with a description of the environment and task to initialise an RL policy, combining the DM's ability to act without training with RL's ability to improve from reward. Instead of exploring from scratch, the agent reaches the goal and receives reward from its first episodes, and RL then improves its policy beyond what the DM achieves. We demonstrate through experiments on seven tasks that our approach outperforms RL in all seven and DM in five. In addition, we provide comprehensive guidelines, derived from ablation studies, for describing an environment and task to a DM.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.03577

Sonar-MoE: In-Backward Expert Updates for Memory-Efficient Mixture-of-Experts Training

Avni Mittal, Avinash Anand, Ashutosh Kumar, Dikshant Kukreja, Kritarth Prasad, Chaitanya Lakhchaura, Rishitej Reddy Vyalla, Erik Cambria 等 10 位作者

原文摘要

Most parameters of a Mixture-of-Experts (MoE) model belong to its experts, and standard training keeps every expert gradient in GPU memory until the optimizer step. This memory grows with the number and size of the experts, so it rises as MoE models scale. We introduce Sonar-MoE, which updates each expert tensor during the backward pass and frees its gradient right away. It brings optimizer-in-backward from dense models to batched MoE expert tensors, so the GPU never holds more than one layer of expert gradients. When we fine-tune OLMoE-1B-7B and Granite-3.1-3B-A800M in bf16 with two expert-kernel backends, Sonar-MoE lowers peak memory by 19% to 22%. Its updates are bitwise identical to standard training without expert gradient clipping, and held-out loss stays within 0.003 of all baselines. Each step also takes 17% to 23% less time than standard training with global-norm clipping. Updating whole batched tensors rather than individual experts is what keeps Sonar-MoE fast, as it avoids a 20% to 72% slowdown while using the same memory. Sonar-MoE matches optimizer-in-backward over all parameters in memory and speed while still clipping the dense parameters.

cs.LG · cs.AI · cs.CL · cs.PF

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07932

AttnSR: Attention Step Reward for Long-Horizon Agentic RL

Mengsong Wu, Tianchen Zhou, Zhaochen Su, Zhenhua Liu, Zhe Cui, Aimin Zhou

原文摘要

Long-horizon LLM agents make multi-step decisions, yet outcome-reward-only reinforcement learning provides little direct supervision for individual steps. We introduce AttnSR, a step-level reward augmentation method that derives reward allocations from policy attention extracted during training replay, without a separately trained reward model or additional rollouts. AttnSR traces backward through the policy model attention graph to estimate the relevance of earlier steps to the final response. The terminal step, measured relative to a running baseline, determines whether these rewards reinforce or penalize the selected steps. In a controlled Qwen2.5-7B-Instruct study, AttnSR consistently outperforms the PPO baseline across all evaluated checkpoints on ALFWorld, raising final held-out success from 91.2% to 97.1%. The ablation experiment shows that the benefit depends on how intermediate rewards are assigned, rather than simple accumulation of step rewards over time. AttnSR also improves ScienceWorld at every checkpoint while cutting environment interactions by 29.9%. These results support policy attention as a practical prior for step-level reward allocation in long-horizon agentic RL. Code is available at https://github.com/fairyshine/AttnSR .

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07929

Flux as a Codec: Zero-Shot Lossy Compression with Flux

Fuma Kimishima, Jinjia Zhou

原文摘要

We propose FluxC, a zero-shot codec that uses Flux as a compression prior. Although DiffC has shown that pretrained diffusion models can serve as zero-shot codecs, we ask how the choice of coding path and reconstruction method affects rate--distortion--perception behavior. We analyze FluxC along three axes: coding cost and bit allocation, reconstruction method, and low rate distortion. At matched signal-to-noise ratio (SNR), we show that the path choice does not affect the ideal information rate, but changes how bits are allocated across time steps. For reconstruction, we compare ancestral sampling, one-step ODE reconstruction, and many-step ODE reconstruction. Our analysis shows that ODE-based reconstruction can achieve lower distortion than ancestral sampling, especially in the low rate regime. Experiments on Gaussian sources and natural images support this prediction. Moreover, FluxC performs competitively with, and in some cases outperforms, recent neural image compression methods, suggesting that Flux can serve as a principled zero-shot codec.

cs.LG · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2604.16565

Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models

Jiaoyang Ruan, Xin Gao, Yinda Chen, Hengyu Zeng, Liang Du, Guanghao Li, Jie Fu, Jian Pu

原文摘要

While Diffusion Large Language Models (dLLMs) offer structural advantages for global planning, efficiently verifying that they arrive at correct answers via valid reasoning traces remains a critical challenge. In this work, we propose a geometric perspective: Reasoning on the Manifold. We hypothesize that valid generation trajectories reside as stable attractors on the high-density manifold of the learned distribution, whereas invalid paths exhibit off-manifold drift. To operationalize this, we introduce Bidirectional Manifold Consistency (BMC), a training-free, unsupervised metric that quantifies the stability of the generated sequence through a forward-masking and backward-reconstruction cycle. Empirically, we demonstrate BMC's versatility across the full reasoning lifecycle: (1) in Diagnosis, it serves as a robust discriminator of solution validity without ground truth answer; (2) in Inference, it enables rejection resampling to effectively concentrate computational resources on complex reasoning tasks; and (3) in Alignment, it functions as a dense geometric reward that transforms sparse outcome supervision into fine-grained guidance, empowering models to self-evolve beyond standard baselines. Our results establish intrinsic geometric stability as a robust indicator of correctness for dLLMs.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07913

Same Answer, Different Future: Matched Predictions Do Not Imply Matched Belief Updating in Language Models

Weihan Li, Junhao Wu, Xinlei Chen, Tianshi Zheng

原文摘要

Language models can produce similar probabilistic predictions after observing outcomes, reading summaries, receiving instructions, or undergoing activation interventions. Whether these routes induce equivalent belief states remains unclear: agreement in current predictions does not establish how a model will respond to subsequent evidence. We investigate this distinction in a Bernoulli inference task with an analytic Bayesian reference. Across three open-weight language models, we prepare states through four textual routes and two activation-level interventions, measure both next-outcome continuations and explicit probabilistic estimates, and append identical new evidence from each prepared state. We quantify the persistence of the initial belief through its effective evidence weight, the number of new observations it is worth. We find that the format of evidence decides which readouts express its content: outcome sequences primarily affect continuations, whereas summaries and stated rates primarily affect explicit estimates. Moreover, effective weights differ substantially across routes, with summaries receiving weights that scale weakly with their stated observation counts and elicitation questions changing inferred weights by orders of magnitude. In a one-shot steering setting, an intervention that reproduces a natural record's immediate prediction loses most of its effect under subsequent evidence. These results show that agreement in current readouts is insufficient to establish equivalence in belief updating: how a belief is acquired and how it is read jointly determine its subsequent dynamics.

cs.LG

查看论文
arXiv ↗PDF ↗