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

+586新增论文
+453其中 AI 相关
+91已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-13 11:13 · 全站最近入库：2026-11-13 11:12各信源进度 →

统计口径与数据新鲜度

统计 2026-11-12 12:25 — 2026-11-13 12:25（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：2026-11-13 11:13最近发现新增版本：2026-11-13 11:12库内论文最新更新时间：2026-11-11 22:55

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。

22,261 已收录论文18,776 AI 相关6,286 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 5,087 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-13 11:11（北京时间）
新论文 · v1arXiv:2611.10247

Can Time Series Foundation Models Serve as Surrogates for Power Systems Dynamic Simulation?

Sandy Miguel, Bruno Paes Leao, Cheng Feng

原文摘要

High-fidelity dynamic simulation is essential for scientific and engineering applications, but its computational cost limits large-scale scenario screening. We investigate the use of pretrained time-series foundation models (TSFMs) as computationally efficient surrogates to address this limitation. In-context learning and post-training strategies, including retrieval-augmented reference sample selection and physics-informed regularization, are considered in the investigation. Results are benchmarked against a traditional AI model representative of the state-of-the-art in the domain. Experiments using an open-source TSFM and data from a simulated 9-bus power system indicate promising results. Retrieval augmentation improves in-context learning performance, and fine-tuning leads to superior results compared to the traditional AI model, especially when including physics-informed regularization. The fine-tuned TSFMs achieve lower errors and improved computational costs compared to the traditional AI model, and a 563$\times$ speedup compared to the original physics-based simulation.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2510.03224

Test-Time Defense Against Adversarial Attacks via Stochastic Resonance of Latent Ensembles

Dong Lao, Yuxiang Zhang, Haniyeh Ehsani Oskouie, Yangchao Wu, Alex Wong, Stefano Soatto

原文摘要

We propose a test-time defense mechanism against adversarial attacks: imperceptible image perturbations that significantly alter the predictions of a model. Unlike existing methods that rely on feature filtering or smoothing, which can lead to information loss, we propose to "combat noise with noise" by leveraging stochastic resonance to enhance robustness while minimizing information loss. Our approach introduces small translational perturbations to the input image, aligns the transformed feature embeddings, and aggregates them before mapping back to the original reference image. This can be expressed in a closed-form formula, which can be deployed on diverse existing network architectures without introducing additional network modules or fine-tuning for specific attack types. The resulting method is entirely training-free, architecture-agnostic, and attack-agnostic. Empirical results show state-of-the-art robustness on image classification and, for the first time, establish a generic test-time defense for dense prediction tasks, including stereo matching and optical flow, highlighting the method's versatility and practicality. Specifically, relative to clean (unperturbed) performance, our method recovers up to 68.1% of the accuracy loss on image classification, 71.9% on stereo matching, and 29.2% on optical flow under various types of adversarial attacks.

cs.CV · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.11289

Quotient-Categorical Representations for Bellman-Compatible Average-Reward Distributional Reinforcement Learning

Ege C. Kaya, Aliasghar Pourghani, Vijay Gupta, Abolfazl Hashemi

原文摘要

Average-reward reinforcement learning requires estimating the gain and a state-dependent bias, which solves the Poisson equation only up to an additive constant. Distributional analogues of the bias inherit this same ambiguity. We introduce a quotient-space formulation in which state-indexed laws are identified up to a common translation, together with a categorical parameterization that respects this symmetry. On this space, we define a projected average-reward distributional operator and show that it is well-defined, non-expansive in a coordinate Cramér metric, and admits fixed points. We interpret the projected fixed points through geometrically-stopped differential returns, whose categorical operators are contractive and whose fixed points converge in the Abel sense to a canonical fixed point of the projected undiscounted operator. We show that the means of the projected fixed points match the scalar bias up to an error caused by endpoint clipping of the categorical projections, and we bound this error. Finally, we establish almost-sure convergence and finite-iteration residual bounds for temporal-difference recursions with gain-centered rewards under i.i.d. and Markovian sampling. When the gain is unknown, we couple the recursion with an online gain estimator and prove the same guarantees under Markovian sampling, with a bound on the gain error.

cs.LG · math.OC

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2408.08812

TRAM: Test-Time Risk Adaptation with Mixture of Agents

Mohamad Chehade, Amrit Singh Bedi, Souradip Chakraborty, Amy Zhang, Hao Zhu

原文摘要

Deployed reinforcement learning agents often face safety requirements that are specified only after training: new hazard maps, revised risk thresholds, or behavioral alignment constraints. We study zero-update deployment-time adaptation in which a fixed library of risk-neutral source policies must be reused under a newly specified reward-risk tradeoff. We propose TRAM (Test-time Risk Adaptation with Mixture of Agents), a source-scored composition rule that evaluates each source under the target reward and an occupancy-based deployment risk, then selects actions using risk-adjusted source scores. Unlike training-time risk-sensitive methods tied to a fixed surrogate such as return variance, TRAM supports spatial barrier exposure, divergence to a reference behavior, and local volatility risks specified at test time. We make the surrogate nature of the method explicit: TRAM is not claimed to solve the full occupancy-control problem of the stitched policy, but it admits a measurable source-hull mismatch term connecting source-scored risk to realized risk. Experiments in gridworlds, MuJoCo Reacher, Safety-Gymnasium, and an inference-time LLM alignment setting show that TRAM improves deployment risk while preserving reward and requires no parameter updates at test time.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10240

PACE: Keeping the Right Tokens in the KV Cache Is Not Enough for Long-Horizon LLM Agents

Suman Chatterjee

原文摘要

Long-horizon LLM agents accumulate sessions of up to millions of tokens, far more key-value (KV) cache than one GPU holds, so serving systems keep a small budget of tokens and evict the rest. Eviction methods differ in which tokens they keep but share one goal: that the tokens a later step needs are still cached. We show this is not enough. In 100K-token coding sessions on Qwen3-8B with a 2,048-token budget, a planner-guided policy that keeps over 99% of the needed tokens resident still fails late steps increasingly often: its accuracy falls from 93% to 64% as the gap between a definition and its use grows from 2K to 90K tokens, at residency 0.996. The needed tokens are resident but unretrievable: what grows is their rotary-position distance to the query. We present PACE (Planner-Aware Context Engine), a KV-cache engine that couples plan-aware retention, in which the agent's planner tells the cache which context future steps will read, with bounded positions, which renumber kept tokens so their rotary distance to the query stays below 8K at any session length. In a pre-registered evaluation on fresh tasks, PACE passes 97% of hidden unit tests at 100K tokens, against 42% for H2O and 3% for SnapKV under the same budget, and needs both components: either alone reaches 63% (the combination beats each, p < 10^-4). The result holds with length: in 1M- and 2M-token sessions on one 24 GB GPU, with definitions written 0.9M and 1.8M tokens before use, PACE passes 99% and 100% of checks and recalls every session fact, while bounded positions without foresight falls from 33% to 13%; PACE holds under 0.7 GB of KV state where the full cache would need 147-295 GB. Renumbering is exact, costs no measurable perplexity, and adds 9% wall time. On Mistral-7B, whose coding ability caps it at 40% even with nothing evicted, PACE stays at that ceiling while retention alone falls below it.

cs.LG · cs.CL · cs.DC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10237

Implicit Bias in State Space Models and Linear Autoregressive Training

Gal Katzhendler, Gilad Yehudai, Gal Vardi

原文摘要

Linear State Space Models (SSMs) and linear autoregressive sequence models reuse the same parameters across a sample-dependent number of steps. As a result, different examples impose constraints through different predictors, even though all predictors share the same weights. We study this phenomenon through a general model of multiple non-homogeneous polynomial predictors with shared parameters, in a classification setting. Under standard interpolation and directional-convergence assumptions, together with a trajectory-dependent effective-degree condition, we show that gradient descent on the exponential loss converges in direction to a KKT point of an effective-degree max-margin problem. In this problem, only examples with minimal effective degree impose hard margin constraints; examples with faster-growing margins are asymptotically inactive except for feasibility. Our result provides a first-order characterization of the implicit bias in linear SSMs and linear autoregressive models. It exposes a mechanism of length bias: a longer input sequence or additional autoregressive steps may increase the example's effective degree, and the examples with the smallest effective degree dominate the limiting classifier. Our result highlights how non-homogeneity and parameter sharing alter classical homogeneous implicit-bias results.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10235

Agibot: An Open-Source Modular Swerve-Drive Robot Platform for Agricultural Robotics Research and Education

Moeen Ul Islam, Bishal Adhikari, Kori Edwards, Lorien Harvey, J. Alex Thomasson, Dong Chen

原文摘要

Agricultural production faces persistent labor shortages and increasing demand for automation, yet progress in agricultural robotics remains constrained by the limited availability of affordable, flexible, and accessible research platforms. This paper presents Agibot, an open-source, modular, low-cost agricultural robotics platform designed for autonomy research and experimentation, with potential applications in hands-on robotics education. The platform integrates four-wheel independent swerve drive, swappable computing, distributed embedded control, multimodal sensing, and configurable manipulation within a unified sense-plan-act-verify framework supporting perception, control, navigation, manipulation, and autonomous task verification. The platform was evaluated through representative row-crop navigation and manipulation tasks under varying lighting and soil conditions. Experiments demonstrated reliable lane following, autonomous row-to-row navigation, target identification, seed dispensing, plant manipulation, and closed-loop verification of task success. Its modular architecture supports independent testing, modification, and validation of autonomy components for rapid prototyping and experimentation. These proof-of-concept tasks, controller-tuning studies, and integrated trials demonstrate the platform's research capabilities, while its accessible and reconfigurable design supports its use for hands-on robotics education. By combining affordability, modularity, open-source accessibility, configurable manipulation, and end-to-end sense-plan-act-verify autonomy, Agibot provides a practical platform for agricultural robotics research, technology development, and workforce training.

cs.RO · cs.LG · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10230

RAD-TFM: Robust and Domain-Adapted Tabular Foundation Models

Matthew Peroni, Franck Le, Vadim Sheinin

原文摘要

The development of tabular foundation models (TFMs) has accelerated in recent years, outperforming traditional ML methods on many tabular benchmarks. A key finding is that TFMs can be pretrained entirely on synthetic datasets, opening opportunities to design data generators that encourage desirable model properties. Prior work has mainly focused on crafting high-quality priors over generators to improve overall pretraining performance. Our key insight is that parameterizing the generator distribution enables an adversarial, distributional robustness perspective: during training, we can adapt the generator to emphasize datasets that are particularly challenging for the model, which we formalize by introducing an optimality gap measure. Further, we develop a method to align the synthetic data generation with real-world datasets from a given domain, constraining the adversary to generate realistic data. Together, these algorithms comprise the Robust and Domain-Adapted Tabular Foundation Models (RAD-TFM) pipeline, a model-agnostic adversarial training framework. Applied to the TabPFN V2 classifier, RAD-TFM improves performance across 6 diverse tabular benchmarks, with up to a 10.8 percentage-point improvement in mean normalized AUC over the strongest baseline, using fewer than 100k additional synthetic training datasets, less than 0.1% of the original pretraining data. Applying the same pipeline to TabICL V2 also improves performance across three major benchmarks, demonstrating the generality of the framework. These results highlight a promising new direction for targeted adversarial continued training of TFMs using synthetic data alone.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.18164

A Continual Validation, Updating, and Decision-Making Framework for Self-Adaptive Digital Twins: A Case Study in Additive Manufacturing

Yi-Ping Chen, Ying-Kuan Tsai, Vispi Karkaria, Seul Lee, Daniel Apley, Wei Chen

原文摘要

Digital Twins support real-time decision-making through predictive models of physical systems, yet their reliability can deteriorate as operating conditions evolve. Maintaining predictive fidelity under such changes is challenging, particularly when model adaptation relies on limited streaming data, and updated models must be evaluated before deployment. Here, we present an online adaptation framework that integrates gradient-based drift detection, parameter-efficient fine-tuning, and statistical model validation within model predictive control. Changes in prediction-loss gradients trigger batch-wise model updates using Low-Rank Adaptation, while a paired moving-block bootstrap test evaluates predictive improvement before deploying the updated model. The framework is evaluated using a stochastic dynamical system with abrupt changes and a simulated directed energy deposition process with gradual changes in material properties. Results show improvements in predictive accuracy and uncertainty estimation during the evaluated post-adaptation intervals, alongside improved reference tracking and reduced constraint violations in the manufacturing case study compared with the investigated baselines. These findings demonstrate the potential of integrating continual validation with model adaptation while acknowledging the trade-off between responsiveness and predictive reliability in evolving Digital Twins.

cs.LG · cs.AI · math.ST

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10228

FAIR Universe Weak Lensing ML Uncertainty Challenge: Dataset and Cosmological Inference Competition

Biwei Dai, Po-Wen Chang, Erwan Allys, Wahid Bhimji, Boris Bolliet, Thomas Borrett, Paolo Calafiura, Ragansu Chakkappai 等 40 位作者

原文摘要

Weak gravitational lensing is a powerful cosmological probe that enables direct mapping of the matter distribution and precise constraints on the fundamental parameters governing structure formation in the universe. In recent years, machine learning has shown strong potential for extracting cosmological information from weak-lensing data beyond traditional summary statistics. However, progress has been limited by the lack of standardized benchmarks that capture the complexity of the dataset, simulator imperfections, and various systematic biases encountered in realistic analyses. To address this gap, we present the FAIR Universe Weak Lensing Machine Learning Uncertainty Challenge, one of the NeurIPS 2025 competitions, as a benchmark dataset and evaluation study. Our dataset reflects realistic weak-lensing observations, incorporating multiple systematic biases, and thereby providing a controlled testbed for robust cosmological inference under uncertainties. We summarize the main methodological advances developed by the winners of our challenge, including data augmentation with conditional optimal transport, an AI-agent-driven approach for parameter inference, ensemble learning, Vision Transformer-based architectures, and physics-informed feature integration. By unifying the benchmark dataset and the winning solutions, this work provides a community resource for developing and evaluating machine learning methods for weak lensing cosmology and, more broadly, for scientific inference under systematic uncertainties.

astro-ph.CO · cs.AI · cs.CV · cs.LG · physics.data-an

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2603.00326

Vectorized Dynamic Histograms for Sparse Oblique Forests

Ariel Lubonja, Jungsang Yoon, Haoyin Xu, Yue Wan, Yilin Xu, Richard Stotz, Mathieu Guillame-Bert, Joshua T. Vogelstein 等 9 位作者

原文摘要

Sparse oblique (SPO), part of the top-ranked configuration of Google's Yggdrasil Decision Forests (YDF), improve the accuracy while maintaining interpretability of Random Forests (RF) and Gradient Boosted Trees (GBT) by scanning a sparse linear combination of features instead of a single feature. Because projections are sampled at runtime, training is significantly slower, as pre-run optimizations such as presorting cannot be used. We overhaul SPO training in YDF, first by fixing inefficiencies in the released version, achieving 2-5x speedup, then by devising two novel methods, one aimed at GBTs and the other at RFs: (1) Hierarchical AVX2 and AVX-512-vectorized histogram filling speeds up typical GBT-depth trees by up to 1.6x in SPO-GBT and 2x for SPO-RF, and (2) runtime-dynamic histograms between vectorized histograms and exact splits, speeds up deeper, RF depth-typical trees (depths 16 to purity) by up to 1.6x with no detectable effect on accuracy. Our optimizations bring SPO-RF training time on par with YDF's axis-aligned RF. We extensively evaluate on 8 natural and 11 synthetic datasets of up to 10.5 million rows and 1.6 million features, from depth 6 to purity, and open-source the implementation.

cs.LG · cs.DC · cs.PF

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10223

Lower-Level Agnostic Bilevel Optimization

Peiwen Qiu, Prashant Khanduri, Jia Liu

原文摘要

Bilevel optimization is a fundamental framework for machine learning problems, where an upper-level (UL) objective depends on the solution of a nested lower-level (LL) problem. Existing bilevel algorithms typically assume that the LL objective is available for evaluation, differentiation, or unrolling. However, this assumption can fail when the LL response is produced by a black-box solver, simulator, adversary, or learned predictor. In this paper, we study LL agnostic bilevel optimization, where the UL learner has access only to an approximate LL solution $\bar{\mathbf{y}}(\mathbf{x})$ and cannot query the LL objective, its gradients, Hessian/Jacobian information, or the procedure that generates the LL response. We propose LeGo-BiO, a coordinate-wise pseudo-hypergradient method that estimates the missing Jacobian $\nabla _{\mathbf{x}}\bar{\mathbf{y}}(\mathbf{x})$ using finite differences of $\bar{\mathbf{y}}(\cdot)$. For each UL coordinate, LeGo-BiO constructs a decision vector subject to 1-sparse updates, thereby isolating the corresponding Jacobian column needed in the UL gradient computation. This avoids the directional-projection limitation of full-parameter response differences and, unlike derivative-free/zeroth-order approximations of the entire UL gradient, preserves the available first-order gradient information with respect to the UL variables for more accurate UL gradient evaluation. We establish convergence guarantees for LeGo-BiO in both deterministic and stochastic settings under an LL error-bound/Polyak-Lojasiewicz-type condition, without requiring LL strong convexity. Our bounds yield an $O(T^{-1})$ rate in the deterministic setting and an $O(T^{-1/2})$ rate in the stochastic setting when the LL approximation error decreases geometrically. Experiments demonstrate competitive performance of LeGo-BiO despite being agnostic to the LL objective.

cs.LG · math.OC · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.08007

Interpreting Reinforcement Learning Agents with Susceptibilities

Chris Elliott, Einar Urdshals, David Quarel, Daniel Murfet

原文摘要

Susceptibilities are a technique for neural network interpretability that studies the response of posterior expectation values of observables to perturbations of the loss. We generalize this construction to the setting of the regret in deep reinforcement learning and investigate the utility of susceptibilities in a simple gridworld model that nevertheless exhibits non-trivial stagewise development. We argue that susceptibilities reveal internal features of the development of the model in parameter space that one cannot detect purely by studying the development of the learned policy. We validate these results with activation-steering, and discuss the framework's extension to RLHF post-training.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2601.07524

Stagewise Reinforcement Learning and the Geometry of the Regret Landscape

Chris Elliott, Einar Urdshals, David Quarel, Matthew Farrugia-Roberts, Daniel Murfet

原文摘要

Singular learning theory characterizes Bayesian learning as an evolving tradeoff between accuracy and complexity, with transitions between qualitatively different solutions as sample size increases. We extend this theory to reinforcement learning, proving that the concentration of a generalized posterior over policies is governed by the local learning coefficient (LLC), an invariant of the geometry of the regret function. This theory predicts that deep reinforcement learning with SGD should proceed from simple policies with high regret to complex policies with low regret. We verify this prediction empirically in a gridworld environment exhibiting stagewise policy development: phase transitions over training manifest as "opposing staircases" where regret decreases sharply while the LLC increases.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10217

Rethinking How to Leverage Cheap Physics for Data-Efficient Neural Operators

Shuo Zhang, Senwei Liang

原文摘要

Neural operators learn mappings from PDE inputs, such as initial conditions and coefficient fields, to the corresponding solutions. Once trained, they can rapidly predict solutions for new inputs. However, obtaining input-solution pairs for supervised training often requires expensive numerical simulations, whereas PDE inputs and governing equations provide inexpensive physical information. This raises a question: how can cheap physical information reduce the need for labeled solutions? A natural approach is to use physics to select inputs for labeling, but our acquisition experiments show no consistent advantage over random sampling. This observation motivates exploring an alternative: using cheap physics to improve neural operator initialization before supervised training. We propose Physics-Informed Initialization (PI-Init), a simple yet effective method that pretrains neural operators on unlabeled inputs using physics-informed losses and retains the learned parameters for supervised fine-tuning on the labeled dataset. A linearized analysis shows that pretraining can improve downstream prediction accuracy by reducing initialization errors that limited labeled data cannot effectively correct. Experiments across diverse PDE benchmarks and neural operator architectures demonstrate improvements in predictive accuracy, out-of-distribution generalization, and label efficiency. Representative results show error reductions of up to 62.7% at the same label budget and comparable or better accuracy with 90% fewer labels, relative to supervised-only training.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10212

DisMUSE: An Efficient Distributed Singular-Spectrum-Based Optimization Approach with Theoretical Convergence Guarantee

Zhen Qin, Zhiyao Zhang, Yingbin Liang, Jia Liu

原文摘要

In recent years, singular-spectrum-based optimizers have attracted increasing attention due to their ability to preserve the matrix structure of neural network gradients, thereby enabling geometry-aware optimization. However, most singular-spectrum-based (SSB) approaches remain centralized, limiting their use in distributed learning infrastructures that exploit massive parallelism. Distributed SSB optimization is still at an early stage, with open questions about convergence guarantees and communication efficiency. To fill this gap, we propose the Distributed Momentum-based Spectral Estimator (DisMUSE), an efficient distributed SSB optimization framework for both data-center and federated settings. Using Muon-style exact orthogonalized momentum as the spectral update, DisMUSE integrates a recursive variance-reduced momentum estimator and achieves an $O((KT)^{-1/3})$ convergence rate, where $K$ and $T$ denote the number of nodes and local iterations per node, respectively. This rate matches the best-known rates for variance-reduced nonconvex distributed optimization. Building on this variance-reduced framework, we study two extensions. First, our DisMUSE method with finite Newton-Schulz (NS) iterations preserves the same convergence order under a uniform normalized support-spectrum condition, up to a multiplicative factor. Second, we develop a communication-efficient variant based on low-rank (LR) momentum transmission and quantify the error it introduces to the stationarity bound, characterizing the trade-off between accuracy and communication cost.

cs.LG · math.OC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.07502

Coverage Hides Churn: Auditing and Preserving Conformal Decisions as VLM Label Registries Grow

Jai Kumar Sharma, Peeyush Tapadiya

原文摘要

Vision-language classifiers can learn new labels from text alone, so the label lists they serve keep growing. We show that this growth silently changes conformal decisions about old labels. Common softmax-based conformal scores compare each label with an average over all labels; adding labels changes that average, and with it the score of every old label, even when the model, the image, and the old calibration data stay the same. Recalibrating after the update keeps the coverage guarantee, yet across eleven settings it changes at least one old decision on 53-90% of new images. Coverage cannot reveal this, because it checks only the true label: in five controlled settings that keep the old calibration, so that only the normalizer changes, old-class coverage moves by at most 0.01 while 60-67% of images change. We propose a lifecycle audit that measures these changes alongside coverage and set size, and a simple fix, PrefixCP: each class keeps the label registry that existed when it was added. Its old decisions then never change, each class keeps exact class-conditional coverage under exchangeability, and one prefix scan computes all historical normalizers at once. PrefixCP recovers 40.9-58.5% of the set-size gap between never updating the reference and recalibrating, which gives smaller sets but changes old decisions.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.05184

Rethinking On-Policy Self-Distillation for Thinking Models

Simran Kaur, Narutatsu Ri, Yinghui He, Liam Fowl, Sanjeev Arora

原文摘要

On-policy self-distillation (OPSD) is a promising approach to recursive self-improvement. In this setting, a model acts as its own teacher when augmented with privileged information, such as a solution to a math problem. Thinking models seem especially well positioned to teach themselves this way, since they can deliberate, verify, and self-correct. Surprisingly, we show that OPSD degrades thinking models on long reasoning traces: across five Qwen3 and OLMo thinking models evaluated on AIME24, AIME25, and HMMT25, privileged-context distillation causes a relative drop of up to 17\% in avg@16 accuracy. The degradation scales with the amount of privileged context withheld from the student and is most pronounced at long rollout budgets, where thinking models otherwise obtain their largest gains. This failure mode extends to distillation from a larger, privileged teacher: on-policy distillation (OPD) improves thinking models, but privileged OPD reverses these gains. Our diagnostics suggest that privileged teacher context reshapes learning at high-entropy forking positions, i.e., rollout positions where multiple continuations remain plausible and may lead to different reasoning paths. Privileged context lowers fork rates in thinking-model rollouts but not in instruction-tuned model rollouts, which may explain the observation that OPSD training helps instruct models more reliably than thinking models.At self-correction branches, privileged OPD penalizes sampled reconsideration tokens that vanilla OPD supports. Consistent with this, thinking models trained with a privileged teacher produce fewer verification, backtracking, and hedging markers, even after length normalization. These findings indicate that applying self-distillation methods to strong thinking models requires further consideration of token-level signal---especially around tokens related to correction and crucial reasoning steps.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2601.21636

Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation

Jan Schuchardt, Nikita Kalinin

原文摘要

We study privacy amplification for differentially private model training with matrix factorization under random allocation (also known as the balls-in-bins model). Recent work by Choquette-Choo et al. (2025) proposes a sampling-based Monte Carlo approach to compute amplification parameters in this setting. However, their guarantees either only hold with some high probability or require random abstention by the mechanism. Furthermore, the required number of samples for ensuring $(ε,δ)$-DP is inversely proportional to $δ$. In contrast, we develop sampling-free bounds based on Rényi divergence and conditional composition. The former is facilitated by a dynamic programming formulation to efficiently compute the bounds. The latter complements it by offering stronger privacy guarantees for small $ε$, where Rényi divergence bounds inherently lead to an over-approximation. Our framework applies to arbitrary banded and non-banded matrices. Through numerical comparisons, we demonstrate the efficacy of our approach across a broad range of matrix mechanisms used in research and practice.

cs.LG · cs.CR · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10202

Semiprime Factorization with Discrete Diffusion and Beam Search: Scaling Laws

Brendan O Donoghue, Nenad Tomasev, Volodymyr Mnih, Timothy Nguyen, Dalin Guo, Arun Nair, Kenneth Yang, Alexandre Frechette 等 15 位作者

原文摘要

We demonstrate that transformer architectures trained with discrete denoising diffusion and decoded via guided test-time beam search can learn to recover the prime factors of semiprime integers directly from data. Our approach establishes a new frontier for learning-based semiprime factorization, successfully factoring 68-bit integers-a substantial advance over the prior 56-bit state of the art. While computationally less efficient than classical factoring algorithms, our model requires no domain-specific number-theoretic priors and learns purely from training examples. In practice, the diffusion model acts as a generative prior, identifying promising factor candidates where exact verification or lattice-based post-processing can complete the factorization. Furthermore, we derive empirical scaling laws relating approximation quality to training data volume, model size, and test-time computation. In contrast to language, problem size is the key driver of scaling behavior. Achieving a fixed accuracy on a held-out test set requires compute that scales exponentially with bit length. Consequently, our findings pose no threat to security, as the projected compute cost required to factorize cryptographically relevant integers remains prohibitive.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.30667

StarWM: Self-Supervised Trained Attention Routing for Robust World Models

Zeqiang Zhang, Fabian Wurzberger, Maximilian Otte, Daniel Schmid, Sebastian Gottwald, Arne Peter Raulf, Daniel Alexander Braun

原文摘要

A robust world model must strike the balance between faithfully capturing environmental dynamics and abstracting away from irrelevant content. While reconstruction-based world models ensure faithful supervision, they misallocate representational capacity by pixel area rather than dynamics relevance for visual tasks, which can cause task-irrelevant content to dominate the learned representation. Alternatively, reconstruction-free methods avoid this bias but risk discarding possibly relevant information. We propose StarWM, which uses a cross-attention module trained on self-supervised dynamics to decide where reconstruction applies. A dual-stream decoder then restricts reconstruction to the attended regions, with stop-gradient barriers preventing interference between the two objectives. These components allows reconstruction to supervise the visual content of attended regions without contaminating the latent with non-predictive information. On DeepMind Control with dynamic video backgrounds, default (reward-free) StarWM achieves the strongest performance under random-frame distractors and substantially outperforms reconstruction-based baselines under sequential video. In addition, its reward-augmented variant matches or exceeds reconstruction-free methods on sequential video, achieving the highest overall return across all distractor regimes. Mechanistic probing confirms \starwm{} preserves state attributes with near-perfect fidelity through long-horizon imagination while systematically discarding distractors. Code is available on GitHub.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10198

BO-Arena: An Evolving Benchmark for High-Dimensional Bayesian Optimisation

Colin Doumont, Thomas Christie, Henry Moss, Philipp Hennig

原文摘要

High-dimensional Bayesian optimisation (HDBO) is an increasingly crowded field with new methods proposed at every major conference, making it ever harder to answer a deceptively simple question: "Which method is currently state-of-the-art?" In this paper, we question the efficacy of benchmarking practices in the field, and find them to be systematically ineffective: multiple published works fail to benchmark against the strongest available baselines, or even include incorrect implementations of key methods. Without a shared reference implementation, such errors are difficult to detect during peer review. We therefore introduce BO-Arena, an actively maintained and extensible package providing canonical implementations of state-of-the-art algorithms, which allows researchers to develop new methods and benchmark them rigorously. Using BO-Arena, we find that what currently drives performance in HDBO is even simpler than previously thought. We use these insights to propose a new algorithm which is competitive with the state of the art on problems with many observations, without resorting to the complex GP approximations used in recent methods. Finally, we question whether there is currently sufficient evidence that any more complex method outperforms a simple Gaussian process baseline for HDBO.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.25687

On Neural Scaling Laws for Weather Emulation through Continual Training

Shashank Subramanian, Alexander Kiefer, Arnur Nigmetov, Amir Gholami, Dmitriy Morozov, Michael W. Mahoney

原文摘要

Neural scaling laws, which in some domains can predict the performance of large neural networks as a function of model, data, and compute scale, are the cornerstone of building foundation models in Natural Language Processing and Computer Vision. We study neural scaling in Scientific Machine Learning, focusing on models for weather forecasting. To analyze scaling behavior in as simple a setting as possible, we adopt a minimal, scalable, general-purpose Swin Transformer architecture, and we use continual training with constant learning rates and periodic cooldowns as an efficient training strategy. We show that models trained in this minimalist way follow predictable scaling trends and can outperform standard cosine learning rate schedules. Cooldown phases can be repurposed to improve downstream performance, e.g., enabling accurate multi-step rollouts over longer forecast horizons or sharper predictions through spectral loss adjustments. We also systematically explore a wide range of model and dataset sizes under various compute budgets to construct IsoFLOP curves, and we identify compute-optimal training regimes. Extrapolating these trends to larger scales highlights potential performance limits, demonstrating that neural scaling can serve as an important diagnostic for efficient resource allocation. We open-source our code for reproducibility

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.00403

MXCode: Vector Quantization for MX-Native Inference at Scale

Gaurav Kolhe, Cansu Demirkiran, Shubhi Tyagi, Sulaiman Sadiq, Boyao Wang, Richard Wang, Maximiliana Behnke, Shreyas Labhsetwar 等 11 位作者

原文摘要

Memory capacity and bandwidth are major bottlenecks in LLM inference, motivating weight compression beyond conventional 4-bit quantization. Vector quantization (VQ) enables approximately 2-bit weight storage but often relies on codebooks incompatible with native FP4 computation. We introduce MXCode (MX-Native Codebook Quantization), a framework bridging ultra-low-bit VQ compression with MicroXcaling (MX)-native FP4 computation. MXCode proposes three strategies: PostScale, which quantizes learned codebooks to MXFP4; PreScale, which extracts MX scales before codebook learning; and PreScale+, which further compresses these scales using VQ. These strategies explore tradeoffs among quantization quality, scale overhead, and codebook granularity. All reconstruct MX-native W4A4 operands without materializing intermediate high-precision weights. We evaluate MXCode on Qwen3 (235B), DeepSeek-R1 (671B), and GLM-5.2 (753B) using the Microsoft MX Emulation Library. MXCode achieves approximately 2 bits per weight with competitive, workload-dependent model quality. On GB300 hardware, experiments with Qwen3 (235B) show approximately 50% lower model-load memory than Native FP4 while maintaining near-Native-FP4 serving throughput. Under memory-constrained prefix reuse, P90 TTFT improves by up to 94.5%. These results demonstrate software-based reconstruction on existing FP4 hardware and inform the development of future MX-native inference systems.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.07654

English Calibration Erodes Lithuanian in Expert-Pruned Mixture-of-Experts Language Models

Tomas Rasymas, Povilas Kvedaras

原文摘要

Expert pruning compresses Mixture-of-Experts (MoE) language models by removing the experts that a calibration set marks as unimportant. Studies of high-resource languages largely find that English calibration transfers well to other languages. We test this for Lithuanian: we pruned four MoE models with REAP, removing 25% or 50% of the experts with English, Lithuanian or mixed calibration, and evaluated both languages on reading comprehension, translation and language modelling. English calibration does not transfer to Lithuanian: at 25% pruning, English comprehension fell by a median of 1.7 points but Lithuanian by 21.4. The transfer is asymmetric. Lithuanian calibration removed most of the Lithuanian loss and never significantly hurt English comprehension, which was on average 2.5 points better than under English calibration; only English language modeling got slightly worse. Routing suggests why: in the last layers, Lithuanian sends 55-72% of its expert selections to just eight experts, against 19-39% for English, and English calibration removes some of these experts. Compressed models should be calibrated, and evaluated, in every language they must serve.

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10188

BiMuon: A Geometry-Aware Stochastic Bilevel Optimization Approach

Zhen Qin, Zhiyao Zhang, Yingbin Liang, Jia Liu

原文摘要

Stochastic bilevel optimization provides a general framework for many machine learning applications, such as hyperparameter learning, data reweighting, language model alignment, and actor-critic reinforcement learning. However, most existing bilevel optimization methods treat matrix-valued gradients as flattened vectors and perform optimization in the resulting vectorized space, ignoring the matrix structures common in modern neural networks. Moreover, the lower-level (LL) problem curvature can induce significant spectral imbalance in the upper-level (UL) geometry. Such limitations of existing bilevel optimization methods motivate us to develop BiMuon, a geometry-aware stochastic bilevel optimization method that integrates implicit hypergradient estimation in bilevel optimization with Muon-style orthogonalized updates at the UL. To our knowledge, BiMuon is the first stochastic BLO method with Muon-style orthogonalized matrix updates and an $O(ε^{-4})$ iteration-complexity guarantee, matching the best-known rates achieved by Muon-type methods based on matrix parameterizations. To improve computational and parallel efficiency for models with multiple matrix parameters, we further study BiMuon for blockwise diagonal matrix approximation and derive a relative stepsize allocation rule based on UL progress and blockwise LL sensitivity. We evaluate BiMuon on representation learning and blockwise bilevel optimization, providing empirical support for our methods.

cs.LG · math.OC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10187

Fast Accurate Quantum Monte Carlo without Metropolis Adjustment

Reuben Cohn-Gordon, Gabriel Pescia, Sumner N. Hearth, Jakob Robnik, Uroš Seljak, Peter Lunts

原文摘要

In quantum systems, physical quantities of interest can be expressed as expectation values of a probability distribution, which allows their estimation by Markov Chain Monte Carlo (MCMC) methods. This approach, an instance of Quantum Monte Carlo (QMC), plays a central role in obtaining predictions of system properties relevant to condensed matter and high energy physics. The use of Hamiltonian dynamics to design a Markov kernel, known as Hybrid or Hamiltonian Monte Carlo (HMC), is widespread in quantum applications. In this context, it is standard to use an HMC kernel that is ``adjusted'' with the Metropolis-Hastings (MH) criterion, so that estimates of expectations converge to their true value in the limit of infinite sample size. However, recent work in computational statistics suggests that an \emph{unadjusted} HMC kernel can be significantly more efficient, while safely maintaining an asymptotic bias which is small relative to the error arising from the variance of the finite sample size. We adapt this approach to the QMC setting, focusing on a challenging and high-dimensional \emph{spin-fermion} model of a quantum phase transition. We find that unadjusted methods outperform adjusted HMC in terms of effective sample size per gradient call, while retaining accurate results.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10186

Projected Neural Additive Models as Universal Approximators

Nhon N. Phan, Qiang Du, John D. Clayton, WaiChing Sun

原文摘要

Neural additive models (NAMs) offer interpretability but lack expressivity due to their rigid additive structure, whereas multi-layer perceptrons (MLPs) achieve universal approximation at the cost of transparency. We establish the first theoretical foundation for projected neural additive models (PNAMs), which augment NAMs with a learnable linear transformation $\boldsymbol{T}$ to capture cross-variable interactions. While standard NAMs cannot approximate even the simplest interaction term $χ_1 χ_2$ because their cross-derivatives are identically zero, we prove that PNAMs are universal approximators and characterize the minimum number of projections required for exact polynomial representation. Furthermore, we derive an approximation rate of $\mathcal{O}(M^{-s / (N - 1)})$ for $\mathcal{C}^s$ functions (i.e., functions with $s$ continuous derivatives), where $M$ denotes the number of projections and $N$ the input dimension; this rate is known to be optimal for ridge function approximation. To recover interpretability from the projected inputs, we introduce structured sparsity regularizers and post-hoc symbolic regression techniques that enable global input ranking, parameter pruning, and the conversion of learned bases into compact analytical expressions. Experiments on knot theory invariants, MNIST, and phase field fracture mechanics demonstrate that PNAMs match or surpass similar architectures in accuracy while discovering salient features and yielding symbolic models with orders of magnitude fewer parameters.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.31351

Progressive Memory Transformer: Memory-Aware Attention for Time-Series

Tord Sture Stangeland, Andreas Köhler, Steffen Mæland, Adín Ramírez Rivera

原文摘要

Time-series carry structure simultaneously at multiple scales (fine-grained variation, mid-range motifs, and global properties) and downstream tasks operate at correspondingly different scales. Most existing self-supervised learning approaches supervise representations globally via instance-level contrastive losses and limited temporal neighborhood supervision, but do not explicitly exploit the structural hierarchy. We propose a learning framework that explicitly enforces a structural hierarchy across three scales independently: a local objective for token alignment, a mid-range objective for window-level motifs, and a global objective for sequence-level agreement. Realizing this framework requires the backbone to expose a representation at each scale; we introduce \textbf{Progressive Memory Transformer} (PMT), which augments a transformer with writable, window-aligned memory that exposes the mid-range scale alongside the token and sequence-level representations conventional transformers already provide. Across eight UCR/UEA/UCI classification benchmarks, a cue-retention probe, and forecasting benchmarks, PMT learns representations that probe well at the global, mid-range, and local scales---strong low-label classification (1--5\% labels), competitive forecasting performance across multiple horizons, and quantitative and qualitative evidence that memory states capture mid-range motifs.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10176

AVCORP: Identifying and Resisting Deception via Communication Theory and Theory of Mind

Fardin Saad, Zhe Zhang, Sanjana Cheerla, Amanul Haque, Munindar P. Singh

原文摘要

Today's LLM-based agents are vulnerable to deception by users and other agents. Defending against deception requires Theory of Mind (ToM) reasoning to infer the beliefs and goals of others as well as modeling tactics based on communication theory. To enable training models to detect deception, we adopt the well-known deception game, Avalon. We present a corpus, AVCORP, of 5,000 annotated utterances from 250 games of Avalon. AVCORP includes (1) 37 tactics mapped to a 4x4 behavior matrix, and (2) reasoning traces capturing abductive hypotheses, suspicion levels, and nested ToM beliefs. We train Qwen3-8B on AVCORP and evaluate it on 25 held-out games and 20 games played by humans. On held-out games, our best trained detector outperforms its untrained baseline and frontier models (GPT-5.6 Sol, Gemini 3.1 Pro, DeepSeek-V4-Pro), matching Claude Opus 5.5. On human games, every trained detector exceeds the untrained model in F1 score across all rounds.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗