跳到正文
研踪PaperTrail

版本更新

查看已发布论文的最新修订,在详情页对照实际观测到的版本。

部分采集异常

全站更新概况

+1084新增论文
+883其中 AI 相关
+130已有论文修订
+94新增 AI 导读

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

统计口径与数据新鲜度

统计 2026-11-18 02:26 — 2026-11-19 02:26(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-18 04:28最近发现新增版本:2026-11-18 19:45库内论文最新更新时间:2026-11-18 08:00

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

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

论文修订列表

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

找到 8,156 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
版本更新 · v2arXiv:2609.11431

LLMs as Post-hoc Auditors of Physiological Plausibility in Symbolic Regression: A Clinician-Evaluated Case Study

Jorge López-Varela, J. Ignacio Hidalgo, José-Manuel Muñoz, Omar Costilla-Reyes, Esther Maqueda, Jesus Moreno-Fernandez, Tomás González-Vidal, J. Manuel Velasco 等 9 位作者

原文摘要

Genetic programming and its variants, such as grammatical evolution, are widely used in symbolic regression to derive mathematical expressions from multivariate data. In addition to predictive accuracy, models are appreciated for their potential to provide interpretability, offering explicit equations that relate input variables to outcomes. However, achieving interpretability and plausibility remains challenging, as evolved models may be complex or scientifically inconsistent. In this study, we explore whether large language models (LLMs) can assist in improving the interpretability of symbolic regression models generated by evolutionary computation methods. Building on our previous work on estimating body fat percentage using grammar-based genetic programming, we investigate LLMs as post-processing tools to analyze and rank evolved expressions by interpretability and physiological plausibility. Four symbolic expressions are analyzed by three LLMs over three repeated runs, and the resulting interpretations and rankings are assessed by a panel of three clinicians. Across the three LLMs, comparative model-ranking outputs received more favorable clinician assessments than isolated term-level interpretations. However, the LLMs also produced physiologically and mathematically questionable explanations, indicating that they are better suited to comparative auditing under expert oversight than to autonomous validation.

cs.AI

版本更新 · v2arXiv:2610.36727

Finite Fields: Root Sets, Frobenius, and Algebraic Structure

Hongfeng Wu, Li Zhu

原文摘要

This monograph develops finite field theory through root sets, Frobenius orbits, trace duality, and cyclic modules, with applications to polynomial constructions and algebraic coding theory. Root-set descent and linearized polynomials connect field extensions, normal bases, invariant subspaces, and linear recurrences. Cyclotomic cosets link additive symmetries and local phase data with polynomial composition, factorization, and compatible lifting. Low-degree subfield representations and relative traces lead to root-block recovery, while return maps on root fibers organize constructions of irreducible polynomials. Coding applications include duality, distance bounds, Fourier support, and syndrome decoding. Character sums yield trace-norm distributions, the primitive normal basis theorem, and recurrences for extension-field sums and curve point counts. The final chapter constructs finite fields as residue fields of unramified p-adic extensions and relates Teichmuller representatives and Hensel lifting to cyclotomic orbits, periodic digit expansions, Witt carries, coefficient valuations, and Newton slopes. The emphasis throughout is on explicit proofs and reusable connections between field structure, orbit structure, and linear dependence.

math.NT · cs.IT

版本更新 · v2arXiv:2611.07165

Structural Conditional Independence Test via Neural Quantile Resolution

Khoa Nguyen, Bao Duong, Thin Nguyen

原文摘要

Conditional independence testing is difficult when dependence is weak, localized, or expressed through distributional changes rather than a global mean shift. Existing tests usually return a scalar statistic or p-value, which can detect rejection but gives limited resolution about where the conditional law changes. We propose QRCIT, a quantile-resolution conditional independence test that compares P(X | Z) and P(X | Y, Z) through an amortized quantile deformation. A lightweight residual quantile-flow model first learns the baseline conditional quantile law and then learns the additional deformation induced by Y, yielding both a calibrated global test statistic and an inspectable deformation field over context and quantile level. We also introduce the Structural Dependency Benchmark (SDB), which evaluates real-world-inspired dependence structures, such as context-local, tail-only, sign-reversing, moving-ridge, and mean-neutral patterns. Across synthetic PNL and SDB benchmarks, QRCIT improves detection of structured alternatives while maintaining empirical Type-I control. Increasing quantile resolution consistently improves merged-SDB power, and the local-rescue strategy sharpens detection when dependence is concentrated in structural regions. On Sachs, METABRIC breast cancer, and CCLE/PLX4720, QRCIT provides competitive real-data performance and interpretable deformation patterns. These results support quantile-resolved conditional-law deformation as a practical framework for testing and diagnosing structured conditional dependence.

cs.LG

版本更新 · v3arXiv:2608.13545

LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure

Fanfei Li, Jana Zeller, Manuel Prada-Corral, Thaddäus Wiedemer, Prasanna Mayilvahanan, Ryan Cotterell, Wieland Brendel

原文摘要

Modern language models are trained on heterogeneous web-scale text corpora. Consequently, studying knowledge and skill acquisition is difficult, as prior exposure to related content is hard to characterize. To address this challenge, we introduce LittleCurriculum, a curated 88B-token pretraining corpus tailored to U.S. elementary school material, explicitly excluding concepts, facts, and vocabulary taught above Grade 5. Training a 5B-parameter LLM from scratch on LittleCurriculum yields LittleLearner, a model with sufficient language competence for open-ended evaluation, yet with clear knowledge and capability boundaries mapped to interpretable curriculum guidelines. We release LittleCurriculum and LittleLearner as a developmentally restricted sandbox to study how models acquire, represent, and use data under a well-defined training scope. We illustrate the sandbox's utility in a first suite of experiments on injecting new knowledge through post-training and in-context learning. These methods let LittleLearner better utilize existing knowledge, but do not raise out-of-scope capabilities. Our findings underscore the value of this controlled environment for future investigations.

cs.CL · cs.AI · cs.LG

版本更新 · v2arXiv:2511.08326

A Two-Term Ziv-Zakai Bound for Multitarget DoA Estimation in MIMO Radar

Mohammadreza Bakhshizadeh Mohajer, Daniela Tuninetti, Luca Barletta

原文摘要

Multitarget direction of arrival (DoA) estimation is challenging when fluctuating targets are closely spaced: local Cramér--Rao bounds (CRBs) miss global errors, while direct vector Ziv--Zakai bound (ZZB) evaluation is computationally demanding. For colocated multiple-input multiple-output (MIMO) radar with Swerling-II fluctuations and an ordered angular prior, we derive a rigorous two-term Bayesian mean squared error lower bound. A finite separation contribution addresses nonlocal discrimination, while a correction based on the prior averaged Fisher information matrix (FIM) retains target coupling and virtual array geometry. We show that the prior averaged pointwise CRB diverges under unrestricted target spacing when the FIM is nonsingular almost everywhere, although the proposed bound remains finite. Once the averaged FIM is obtained, evaluation avoids displacement optimization and multidimensional binary error integration. The bound supports analysis of snapshot diversity, target spacing, and transmit and receive allocation. Numerical comparison with the vector ZZB shows close agreement at low SNR but greater conservatism at high SNR, quantifying the tradeoff in tightness.

cs.IT

版本更新 · v2arXiv:2609.04874

A Wavelength Borrowing Architecture for Optical Data Center Networks - Extended Version

Andrea Detti, Chiara Lodovisi, Silvello Betti

原文摘要

The growth of east-west traffic, along with the cost and power consumption of electronic switching, is motivating the integration of a low-power, high-rate, all-optical layer within the data center network. This paper presents a spine-leaf all-optical architecture in which the default wavelength configuration, one wavelength per source--destination leaf pair, can be reconfigured to accommodate unbalanced traffic demand: wavelengths that are unused or lightly loaded at one leaf are borrowed by another leaf with higher demand. This topology-engineering capability is combined with a traffic-engineering scheme, based on two-hop detouring, enabling the control of wavelength load while limiting the amount of detoured traffic. A key feature of the architecture is that its degree of wavelength reconfigurability is set by a single tunable parameter, the borrowing degree $B$, ranging from none to full; performance evaluation shows that performance nearly equal to that of a fully reconfigurable architecture is achieved well below the maximum $B$, saving the complexity of a fully reconfigurable solutions. The optical fabric relies on mature, data-center-grade components, namely AWGs, AWGRs, colorless OXCs, and combiners. The reconfiguration speed and the adopted dynamic control policy make the architecture suitable for network tiers where the traffic varies on timescales of tens of minutes or more, e.g., among groups of racks (pods).

cs.NI

版本更新 · v2arXiv:2608.01855

RADAR Perception for Dynamic Obstacle Avoidance onboard small-scale Quadrotor UAVs

Dnyandeep Mandaokar, Bernhard Rinner

原文摘要

Fast dynamic obstacle avoidance (DOA) on uncrewed aerial vehicles (UAVs) demands not only low-latency control and actuation but also reliable, long-range perception to detect obstacles and estimate their motion in time to maneuver. We present, to the best of our knowledge, the first mmWave RADAR-based perception-and-control system for fast onboard DOA. We derive and analyze latency and spatial bounds that relate sensing range, relative speed, and control delay, yielding sufficient conditions for successful avoidance. We further extend prior latency analyses to include the decision latency of the tracker and trigger to evaluate them per trial. Our computationally efficient system combines a lightweight interacting multiple models (IMM) tracker with a control-barrier functions (CBF) controller that directly outputs evasive accelerations. In 300 throw experiments spanning three object sizes and varying visibility (light and dark), it achieves mean position errors of at most 0.15 m, 0.93m, and 0.87m in the x, y, and z directions, with a similar spread in 90 experiments in smoke. An onboard implementation on a Raspberry Pi 4B demonstrates real-time feasibility with an end-to-end processing latency of approximately 14ms per RADAR frame and a system latency of 75ms from first detection to the avoidance command. The UAV successfully avoided obstacles in all 20 tethered indoor flights and all 39 untethered outdoor avoidance maneuvers across three ball sizes, during both hover and forward flights at up to 5m/s with measured closing speeds up to 14.6m/s.

cs.RO · eess.SY

版本更新 · v2arXiv:2606.06333

Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability

Seyed Arshan Dalili, Mehrdad Mahdavi

原文摘要

Sparse Autoencoders (SAEs) are widely used for mechanistic interpretability in large language models, yet their standard formulation assigns each latent feature a single decoder direction, implicitly assuming features to be one-dimensional. We show that this assumption can induce feature splitting when model features are multi-dimensional. Geometrically, accurately reconstructing a feature under a fixed co-activation budget can require exponentially many decoder directions as its dimension grows. From an optimization perspective, adding decoder directions can strictly lower the $\ell_1$-regularized population risk, even when a basis can already reconstruct the feature exactly. Motivated by these results, we introduce Subspace-Aware Sparse Autoencoders (SASA), which replace single-vector decoders with learned subspaces, enforce sparsity through Top-$s$ group gating, and adapt group rank with nuclear-norm regularization. Under an idealized single-feature model, we prove that the SASA objective is minimized by a single group whose reconstruction map recovers the feature subspace. We also derive polynomial sample complexity bounds for subspace estimation within a group and a lower bound on the samples needed to observe every atom in a fixed fragmented dictionary. Experiments on GPT-2 and Mistral-7B show reduced absorption compared with SAEs. Matched-budget GPT-2 comparisons show lower absorption for concept families and more accurate prediction of their members using a small number of latent coordinates, at a reconstruction cost. The code is available at https://github.com/arshandalili/sasa.

cs.LG · cs.AI

版本更新 · v2arXiv:2605.06916

Tyche: One Step Flow for Efficient Probabilistic Weather Forecasting

Fan Xu, Yuan Gao, Kun Wang, Rui Su, Fenghua Ling, Hao Wu, Wanli Ouyang

原文摘要

Probabilistic weather forecasting requires not only accurate trajectories, but calibrated distributions over plausible atmospheric futures. Recent data-driven systems have achieved remarkable deterministic skill, and diffusion-based ensemble forecasters have substantially improved sample realism and uncertainty quantification. However, their inference cost scales with forecast horizon, ensemble size, and the number of denoising steps required for each transition, making large operational ensembles expensive. To address this, we present Tyche, a one-step conditional flow model for efficient probabilistic weather forecasting. Tyche models the conditional forecast distribution with a destination-aware average-velocity flow that maps Gaussian noise directly to future weather states in a single function evaluation (1-NFE). To make this one-step transport learnable in high-dimensional geophysical fields, we derive a JVP-regularized rectification objective that enforces temporal self-consistency across source and destination flow timesteps without explicitly forming Jacobians. The transport field is parameterized by an isotropic Swin-style transformer that preserves fine-scale spatial structure while remaining scalable on global grids. To improve ensemble reliability under autoregressive forecasting, we further introduce a rollout-based finetuning stage with curriculum CRPS calibration supervision. Experiments on ERA5 at 1.5$^\circ$ and 6-hour resolution show that our Tyche, using merely a single NFE, matches or exceeds the forecast skill and calibration of state-of-the-art multi-step generative baselines and the operational ECMWF IFS ensemble.

cs.LG

版本更新 · v2arXiv:2610.13799

Adaptive Variance Reduction across Smoothness and Noise Conditions

Wei Jiang, Yibo Wang, Sifan Yang, Lijun Zhang, Zechao Li

原文摘要

In this paper, we study adaptive stochastic non-convex optimization under unknown smoothness and noise conditions. Our algorithms require no smoothness constant, noise bound, initial function gap, or oracle-regime label. We first propose a fixed-budget method that combines normalized momentum, recursive variance reduction, and a fresh gradient stage, followed by fresh validation of the candidates. We prove that the same output has expected gradient norm $O(T^{-1/4})$ under objective smoothness and bounded noise variance, $O(T^{-1/3})$ under average smoothness, and $O(T^{-1/2})$ for noiseless gradients, where $T$ counts individual gradient evaluations. We then develop an anytime algorithm whose three optimization paths preserve their endpoints across reporting and budget-extension boundaries. The same three rates hold at every deterministic query budget, although the algorithm receives no information about the budget $T$. The analysis combines a scale potential, a uniform second-moment bound, and accounting for candidates retained through unfinished blocks. An optional sample-mean selector further reduces cumulative validation work from $O(T)$ to $O(T^{2/3})$ while preserving these rates.

math.OC · cs.LG

版本更新 · v2arXiv:2605.28137

No Safe Dose: How Training Data Drives Unsafe Image Generation

Felix Friedrich, Lukas Helff, Niharika Hegde, Patrick Schramowski, Kristian Kersting

原文摘要

Text-to-image models are trained on web-scale data that inevitably contains unsafe images, yet whether this contamination directly drives unsafe generation has not been tested under controlled conditions. We train the same text-to-image model on corpora that differ only in their fraction of unsafe images (0% to 9.6%) and in size (100K to 8M), and evaluate 10,000 generations per model with four independent safety classifiers. Output unsafety rises monotonically and saturates, from 16.6% at 0% to 26.4% at 9.6% contamination, and the effect appears only under adversarial prompts. At a fixed training budget, the level is set by the proportion of unsafe images rather than their absolute count or cumulative exposure, so filtering a fixed fraction is equally effective at 1M and 8M images, at no measurable cost in FID, CLIPScore, or ImageReward. Filtering alone, however, does not eliminate unsafe generation: a floor persists when every image flagged by any of four judges is removed (13.6%) and rises when training on real instead of synthetic images (23.1%). A safety-aligned text encoder lowers the floor to 9.6%, but it is not carried by a removable encoder direction, which implicates the generative backbone. Finally, fine-tuning on entirely safe data erodes the benefit of curation (+8.7pp). Data curation and encoder choice are complementary and effective, but neither makes a model safe on its own.

cs.CV · cs.LG

版本更新 · v2arXiv:2606.15104

Text-Driven Fusion for Infrared and Visible Images: Achieving Image Scene Adaptation on Hyperbolic Space

Huan Kang, Hui Li, Tianyang Xu, Tao Zhou, Xiao-Jun Wu, Josef Kittler

原文摘要

Infrared and visible image fusion aims to integrate complementary modalities, while existing Euclidean methods impose rigid distance metrics that distort multi-modal interactions and parent-to-child semantic hierarchies. To overcome these limitations, we introduce a text-driven fusion framework empowered by hyperbolic manifold learning. During training, BLIP-extracted text prompts serve as topological anchors within the hyperbolic space, guiding vision-attribute alignment through hyperbolic embeddings that naturally accommodate varying semantic granularities. By exploiting the exponential volume growth dictated by the Poincaré ball's negative curvature, this approach seamlessly embeds hierarchical trees to encode coarse-to-fine semantics without metric saturation, while the vast peripheral space prevents texture distortion during cross-modal fusion. At inference, the fusion process autonomously adapts to input content using the learned text-attribute priors, completely eliminating the need for textual input. Experimental results show our method outperforms state-of-the-art approaches on benchmark datasets, with code available at https://github.com/Shaoyun2023/TEDFusion.

cs.CV

版本更新 · v2arXiv:2603.18205

Tackling the Sign Problem in the Doped Hubbard Model with Normalizing Flows

Dominic Schuh, Lena Funcke, Janik Kreit, Thomas Luu, Simran Singh

原文摘要

The Hubbard model at finite chemical potential is a cornerstone for understanding doped correlated systems, but simulations are severely limited by the sign problem. In the auxiliary-field formulation, the spin basis mitigates the sign problem, yet severe ergodicity issues have limited its use. We extend recent advances with normalizing flows at half-filling to finite chemical potential by introducing an annealing scheme enabling ergodic sampling. Compared to state-of-the-art hybrid Monte Carlo in the charge basis, our approach accurately reproduces exact diagonalization results while reducing statistical uncertainties by an order of magnitude, opening a new path for simulations of doped correlated systems.

cond-mat.str-el · cs.LG · hep-lat

版本更新 · v3arXiv:2605.08956

Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery

Harshit Bisht, Vinay Kumar, Kevin Maik Jablonka, Mausam, N. M. Anoop Krishnan

原文摘要

A growing body of work pursues AI scientists capable of end-to-end autonomous scientific discovery. This position paper argues that although they already function as co-scientists, agentic AI scientists are not built for autonomous scientific discovery. We identify the following challenges in building and deploying autonomous AI scientists: (1) Problem selection is influenced by the McNamara fallacy; (2) Agents are built on large language models (LLMs) whose training corpora omit tacit procedural and failure knowledge of laboratory practice; (3) Preference optimisation during post-training compresses output diversity toward consensus; and (4) Most scientific benchmarks measure single-turn prediction accuracy and lack feedback from physical experiments back to the computational model. These challenges are not just questions of scale and scaffolding; they require revisiting fundamental design choices. To build truly autonomous AI scientists, we recommend scientific simulations as verifiers for training, a persistent, mutable epistemic state that carries beliefs and shifting objectives across an investigation, the establishment of a centralized preregistration repository for all AI-generated hypotheses, and application driven by scientific need rather than tool affordance.

cs.AI

版本更新 · v3arXiv:2602.16503

Interpretability-by-Design with Accurate Locally Additive Models and Conditional Feature Effects

Vasilis Gkolemis, Loukas Kavouras, Dimitrios Kyriakopoulos, Konstantinos Tsopelas, Dimitrios Rontogiannis, Giuseppe Casalicchio, Theodore Dalamagas, Christos Diou

原文摘要

Generalized additive models (GAMs) offer high interpretability through independent univariate feature effects but underfit when interactions are present in data. GA$^2$Ms add selected pairwise interactions, which improves accuracy, but sacrifices interpretability. We propose Conditionally Additive Local Models (CALMs), a new model class that narrows this trade-off: it stays close to GAMs in interpretability and close to GA$^2$Ms in accuracy. CALMs allow multiple univariate shape functions per feature, each active in different regions of the input space. These regions are defined independently for each feature as simple logical conditions (thresholds) on the features it interacts with. As a result, effects remain locally additive while varying across subregions to capture interactions. We further propose a principled distillation-based training pipeline that identifies homogeneous regions with limited interactions and fits interpretable shape functions via region-aware backfitting. Experiments on diverse classification and regression tasks show that CALMs never underperform GAMs, often beat them and achieve accuracy broadly comparable to GA$^2$Ms, while preserving the univariate auditability that GA$^2$Ms forfeit.

cs.LG · cs.AI

版本更新 · v2arXiv:2603.02865

Signals Are Present, Predictions Fail: Probing Diagram Representations in Large Vision-Language Models

Haruto Yoshida, Keito Kudo, Yoichi Aoki, Ryota Tanaka, Itsumi Saito, Keisuke Sakaguchi, Kentaro Inui

原文摘要

Large vision-language models (LVLMs) demonstrate strong performance on diagram understanding benchmarks, yet they still struggle to understand relationships between elements, particularly those represented by directed edges between nodes. To investigate the causes of this limitation, we probe the internal representations of LVLMs using a synthetic diagram dataset based on directed graphs. Our linear probing experiments reveal that signals about nodes and edges are linearly decodable from the hidden states of LVLMs, even for aspects that LVLMs struggle with in VQA, such as edge direction and connectivity between nodes. These results reveal a gap between internal signals and model outputs. We further perform causal interventions on the model's hidden states, showing that, for some aspects, the signals identified through probing causally contribute to the model's final predictions. These findings also hold on flowcharts, not only on synthetic diagrams.

cs.CL · cs.CV

版本更新 · v3arXiv:2606.25478

TACO: Towards Task-Consistent Open-Vocabulary Adaptation in Video Recognition

Minghao Zhu, Xiao Lin, Mengxian Hu, Xun Zhou, Liuyi Wang, Xiaoyan Qi, Chengju Liu, Qijun Chen

原文摘要

Adapting CLIP for open-vocabulary video recognition necessitates a delicate balance between newly acquired video knowledge and the pretrained generalization. While existing studies pursue this generalization-specialization trade-off with additional regularizations or constraints, we argue that they overlook the deviation of representations beyond the fine-tuning data distribution, resulting in suboptimal adaptation effects. We believe such deviation is inherited from the inconsistency between the fine-tuning and evaluation objectives, where model optimization is restricted to the known training distribution but evaluated on unseen ones. In this paper, we introduce \emph{TACO}, a simple yet effective framework to mitigate the potential negative effects induced by this inconsistency. Our key insight is that adaptation should preserve OOD-relevant alignment beyond the training distribution. To this end, we propose \emph{Relative Structure Distillation}, which regularizes the relative geometry of the representation space and suppresses harmful alignment shift during training. We further decouple the representation space from the optimization space with a lightweight specialization projection, allowing task-specific adaptation without directly overspecializing the representations used at test time. \emph{TACO} establishes state-of-the-art performance on diverse benchmarks under cross-dataset and base-to-novel settings. Code will be released at https://github.com/ZMHH-H/TACO.

cs.CV

版本更新 · v2arXiv:2611.08335

Discovering Update Rules for Opponent Shaping in General-Sum Games

Hong Jun Lee, Ziyan Wang, Jun Wang, Stefanos Leonardos, Yali Du

原文摘要

In general-sum games, self-interested learners can reach outcomes that are poor for everyone, which has motivated methods that shape the opponent's learning. Methods like Learning with Opponent-Learning Awareness (LOLA), which differentiates through the opponent's learning process, and Model-Free Opponent Shaping (M-FOS), which uses model-free optimisation methods for long-horizon opponent shaping, have enabled mutual cooperation and exploitation of learners. However, these methods require access to the opponent's parameters, policy, rewards or learning rule during deployment. In single-agent reinforcement learning, update rules discovered by meta-learning have achieved state-of-the-art results (e.g. DiscoRL). These rules are separate from the policy they train and read only the agent's own experience. We hereby extend this framework to general-sum settings by introducing Discovered Update Rule for Opponent Shaping (DUOS). To the best of our knowledge, this is the first method to discover an update rule for an agent in general-sum games. DUOS meta-trains the rule to maximise the agent's expected return over its lifetime, and updates an inner network using the agent's own experience. We show that our discovered rule exhibits behaviour consistent with opponent shaping without reading opponent policies or parameters, and ranks 1st in normalised mean score and 1st in self-play among tournament entrants.

cs.LG

版本更新 · v3arXiv:2610.07910

Revisiting Temporal Regularization for Smooth Control in Deep Reinforcement Learning

SungJae Ahn, Jeong Woon Lee, Kyoleen Kwak, Hyoseok Hwang

原文摘要

Deep Reinforcement Learning policies can produce nonsmooth action oscillations that hinder deployment on physical robots. Existing architectural and penalty-based approaches seek spatial smoothness by directly reducing sensitivity to changes in state inputs, but their broad constraints can degrade task performance as stronger smoothing is pursued. Temporal regularization instead constrains action differences along observed transitions, but has been considered unable to provide the spatial smoothness needed under observation noise. We revisit this assumption by proving that the temporal penalty bounds the expected action differences between current states sharing a next state, revealing a spatial effect that empirically extends to spatial smoothness. Building on this finding, we propose Conditioning for Action using only Temporal Smoothness (CATS), which combines a temporal penalty with linear ramp-up. We highlight temporal regularization's ability to provide spatial smoothness while better preserving task performance than explicit spatial regularization. Through linear ramp-up, CATS allows the policy to learn rewarding behavior before progressively smoothing its actions, improving return preservation and both temporal and spatial smoothness. Experiments in both simulation and the real world show that CATS substantially reduces action oscillation without degrading task performance, with little computational overhead.

cs.LG · cs.RO

版本更新 · v3arXiv:2604.27927

Taming the Centaur(s) with LAPITHS: a framework for a theoretically grounded interpretation of AI performances

Matteo Da Pelo, Alessio Donvito, Claudio Frongia, Pietro Salis, Antonio Lieto

原文摘要

We introduce a framework called LAPITHS (Language model Analysis through Paradigm grounded Interpretations of Theses about Human likenesS) and use it to show that several major claims advanced by models such as CENTAUR, proposed as an artificial Unified Model of Cognition, are not theoretically or empirically justified. LAPITHS provides a principled reference point for counteracting the current behaviouristic tendency in AI research to interpret the human level performances of transformer based language models as evidence of human like underlying computation and, by extension, as signs of cognitive abilities. The novelty of LAPITHS lies in making explicit the arguments grounded in two quantitative assessments: (i) the Minimal Cognitive Grid, a theoretically motivated method for estimating the cognitive plausibility of artificial systems, and (ii) a behavioural comparison showing that results similar to those reported for CENTAUR like models can be reproduced by other systems that do not satisfy the structural constraints typically associated with cognitive plausibility, and whose outputs do not provide independent explanatory insight into human cognition.

cs.AI

版本更新 · v2arXiv:2608.07224

Stochastic Autoregressive Learning

Ilan Doron-Arad, Idan Mehalel, Elchanan Mossel

原文摘要

Motivated by LLMs, which generate outputs by iteratively sampling from next-token distributions, we introduce a PAC-learning model for binary stochastic autoregressive learning. This generalizes the deterministic autoregressive learning framework of Joshi et al., COLT 2025. In our model, one fixed generator assigns a Bernoulli next-token distribution to every prompt string. Starting from an input prompt, a token is sampled and appended to the prompt; the same generator is then applied again to this expanded prompt; this procedure is repeated for $M$ steps. Three forms of supervision are considered: base one-step samples, chain-of-thought (CoT) samples that reveal full random trajectories of length $M$, and end-to-end (e2e) samples that reveal only the final token of length $M$ trajectories. For a generator class, we study the minimum number of samples $m_{base}(\varepsilon),m_{CoT}(\varepsilon), m_{e2e}(\varepsilon)$, resp., required to learn the one-step probabilities in the base model, and the final-token probability in the CoT and e2e models, under KL divergence. We show that stochastic autoregressive learning fundamentally differs from the deterministic theory. At scale $\varepsilon$, there is no universal comparison between the three learning tasks: both $m_{CoT}/m_{base}$ and $m_{e2e}/m_{CoT}$ can be made simultaneously arbitrarily larger than $M/\varepsilon$, the natural analogue for the existing deterministic results. Nevertheless, after altering scales, for every class, CoT learning at scale $\varepsilon$ is upper-bounded by base learning at scale $\varepsilon/M^2$, whereas e2e learning at scale $\varepsilon$ is upper-bounded, up to logarithmic factors, by $(M/\varepsilon) m_{CoT}(Θ(\varepsilon))$. These dependencies and scales are essentially tight. We complement these bounds by studying dimension $d$ logistic functions in our model.

cs.LG

版本更新 · v3arXiv:2611.06782

Target PageRank: Matching Prescribed PageRank Scores via Budgeted Edge Additions

Parth Gupta, Abhinav Jain, Avishek Mukhopadhyay, Amitabha Bagchi, Sayan Ranu, Abhijnan Chakraborty

原文摘要

PageRank is widely used to quantify the importance of nodes in directed networks. In applications such as recommendation systems, it is increasingly important that the PageRank distribution provides a fair representation of node exposure. This motivates the problem of making minimal changes to a graph so that the PageRank values of a given set of target nodes $T$ match a desired vector $\boldsymbol{t}$. In this paper, we study this problem under an edge-addition budget $B$, where exactly $B$ edges may be added to the graph. We show that deciding whether a multiset of exactly $B$ added edges can make the target nodes attain their desired absolute PageRank scores is NP-complete. After this, we define the $\ell_1$ Target PageRank problem in which we seek to minimize the $\ell_1$ distance between the target vector and resultant vector. We show that this optimization problem admits no polynomial-time multiplicative constant-factor approximation unless $P=NP$. Motivated by these hardness results, we propose two greedy heuristics for approaching the target PageRank vector. We additionally propose a Random Walk Hungarian (RWH) heuristic that addresses the addition of edges between dissimilar nodes by incorporating a penalty for such edges. Finally, we evaluate the proposed heuristics on several real-world and synthetic datasets and compare their performance in terms of PageRank accuracy, computational efficiency, and the relevance of the added edges.

cs.SI

版本更新 · v2arXiv:2602.17310

Attachment Anchors: A Novel Framework for Laparoscopic Grasping Point Prediction in Colorectal Surgery

Dennis N. Schneider, Lars Wagner, Daniel Rueckert, Dirk Wilhelm

原文摘要

Accurate grasping point prediction is a key challenge for autonomous tissue manipulation in minimally invasive surgery, particularly in complex and variable procedures such as colorectal interventions. Due to their complexity and prolonged duration, colorectal procedures have been underrepresented in current research. At the same time, they pose a particularly interesting learning environment due to repetitive tissue manipulation, making them a promising entry point for autonomous, machine learning-driven support. Therefore, in this work, we introduce attachment anchors, a structured representation that encodes the local geometric and mechanical relationships between tissue and its anatomical attachments in colorectal surgery. This representation reduces uncertainty in grasping point prediction by normalizing surgical scenes into a consistent local reference frame. We demonstrate that attachment anchors can be predicted from laparoscopic images and incorporated into a grasping framework based on machine learning. Experiments on a dataset of 90 colorectal surgeries demonstrate that attachment anchors improve grasping point prediction compared to image-only baselines. There are particularly strong gains in out-of-distribution settings, including unseen procedures and operating surgeons. These results suggest that attachment anchors are an effective intermediate representation for learning-based tissue manipulation in colorectal surgery.

cs.CV

版本更新 · v2arXiv:2611.06346

Today's Work, Tomorrow's Workforce: Incentivizing Learning in AI-Assisted Work

Moritz Diener, Daniel Hendriks, Philipp Spitzer, Gerhard Satzger, Joshua Holstein, Wei Sun

原文摘要

At work, people develop skills through experience: novices acquire skills by completing tasks, while experts retain theirs through continued practice. AI assistance changes this process by offering workers a choice between solving tasks independently and accepting the AI's answers. While relying on AI saves immediate effort, it can also displace the practice needed to acquire and retain skills, including those required to oversee the AI. We extend an existing accept-or-solve model to a sequence of tasks in which workers' skills evolve through independent practice and reliance on AI. We compare myopic workers, who maximize immediate utility, with strategic workers, who also value their future skills. We show that novices can become trapped at low skill levels, while experts may lose skill, even as AI-assisted outcome accuracy remains high. Strategic workers, by contrast, may choose to solve independently even when AI is more accurate, recognizing the future value of acquiring and retaining their skills. We then study incentives that reward correct independent work and characterize the payments needed to encourage skill acquisition and retention. We show that independent work can become self-sustaining once workers acquire sufficient skill, eliminating the need for continued incentives. Counterintuitively, supporting a higher skill target can sometimes reduce long-run incentive costs, either by enabling self-sustaining independent work or by lowering the payments needed to maintain proficiency. Our findings thereby shift the focus from whether workers should rely on AI on individual tasks to how organizations can sustain human expertise over time, and which skills are worth investing in.

cs.HC · cs.AI · cs.CY

版本更新 · v2arXiv:2610.08272

Performative Prediction with Selective Labels

Giovani Valdrighi, Isabel Valera, Marcos Medeiros Raimundo

原文摘要

Many social applications of machine learning exhibit performative effects: population behavior changes in response to deployed models. Performative prediction studies this interaction through a distribution map that relates each model to the population distribution it induces. One of the main results in this framework showed that repeated risk minimization (RRM), which updates models by retraining on the most recent data, can converge to a stable model that minimizes risk on its own induced distribution. However, existing analyses typically assume access to the complete distributions of features and labels after model deployment, ignoring the possibility of selective labels: observing labels only for the accepted subset of the population. In this work, we formalize performative prediction with selective labels and show that retraining only on observed data can misguide the retraining procedure and undermine the guarantees of convergence to a stable solution. We then propose a worst-case objective based on knowledge of a confidence interval on the probability of a positive label. Applying RRM to this objective permits us to remain within a bounded distance to the true stable point. Under a sensitivity assumption on the conditional label distribution, we further show how previously accepted data can tighten these confidence intervals over time. Experiments in a lending application with fairness regularization show that our robust optimization approach closely matches the performance of RRM with complete label access.

cs.LG

版本更新 · v3arXiv:2605.24584

LAPLEX: The FFT of Learnable Laplace Kernels

Łukasz Struski, Hanna Blazhko, Piotr Kubaty, Jacek Tabor

原文摘要

Fast matrix--vector multiplication in deep learning usually comes with a choice: fixed geometry and exact computation, as in the fast Fourier transform (FFT), or adaptive geometry paid for by dense parameters, random features, or low-rank surrogates. To move beyond this trade-off, we introduce LAPLEX, a class of exact, trainable (phased) Laplace-kernel operators. A LAPLEX layer is a typically full-rank dense matrix, implicitly defined by learnable coordinate anchors, with FFT-like scaling. Consequently, it supports trainable matrix-vector operations at vector dimensions up to $10^9$ on modern GPUs. As a neural layer, it yields compact projections and classification heads interpretable as soft, trainable routing models. The same primitive also serves as an efficient Gram operator, enabling high-dimensional covariance models on flattened images of dimension $3 \cdot 10^6$ that preserve visible spatial structure without imposing convolutional bias. These applications reflect a single principle: dense geometry can be learned without storing a dense matrix, which enables data-adaptive global interactions in regimes where ordinary dense layers are out of reach. In this sense, LAPLEX separates expressivity from storage cost: it behaves like a dense trainable matrix, but is represented and applied through a small structured set of parameters. Our code is available at: https://github.com/gmum/laplex.

cs.LG · cs.AI

版本更新 · v2arXiv:2502.01197

Evolving Drone Morphologies for Agile Flight

Elijah H. W. Ang, Robin Ferede, Christophe De Wagter, Guido C. H. E. de Croon

原文摘要

The design of multicopter drones has remained almost the same since their inception. While conventional designs work well in many cases, they may not be optimal in specific tasks. This paper revisits rotary drone design by exploring which body morphologies are best suited for different objectives and constraints. An evolutionary algorithm is used to produce drone morphologies that performs better than standard configurations at thrust-to-weight ratio, maneuverability and size. To generate a range of drones with performance trade-offs between them, the non-dominated sorting genetic algorithm II is used. The evolved drone bodies outperform a standard multicopters in at least one of the three objectives. The Pareto front extrema show improvement of 489.2%, 23% and 4.8% in maneuverability, thrust-to-weight ratio and size, respectively, when compared to a standard quadcopter. The improvement in maneuverability is attributed to the tilt angles of the motors, while the increase in thrust-to-weight ratio is due to the higher number of propellers. Experiments show that the performance improvement transfers to a real world drone racing task, where the evolved drone outperforms the standard drone in terms of number of gates passed,flight speed and lap times.

cs.RO

版本更新 · v2arXiv:2606.30118

Effective Horizons for Prophet Inequalities with Discounted I.I.D. Rewards

Jung-hun Kim, Vianney Perchet

原文摘要

We study prophet inequalities for $n$ i.i.d. base rewards subject to multiplicative discounts across $S$ phases. For equal-length phases and a common discount factor $\widetildeγ$, we characterize the optimal competitive ratio of single-quantile policies as $n\to\infty$ with $S$ and $\widetildeγ$ fixed. The resulting sharp guarantee describes the dependence on the phase parameters: it recovers $1-1/e$ without discounting and approaches $1/2$ in the worst-case regime. We also establish a distribution-free comparison that bounds the discounted prophet by a fractional i.i.d. maximum with effective horizon $B$, the sum of the discount weights across all observations. The comparison yields acceptance probability $1/B$, determined only by the phase profile. This calibration attains the canonical optimum even among single-quantile policies that may choose their acceptance probability using the known base distribution. The comparison also gives guarantees for heterogeneous discounts and unequal phase lengths. A complementary optimal-stopping upper bound establishes the same limiting optimum of $1/2$ for arbitrary stopping rules in the canonical model. Finally, the same effective-horizon calibration sets acceptance probability $1-\widetildeγ$ under infinite-horizon geometric discounting. This explicit quantile rule attains Boshuizen's (1994) known optimal worst-case ratio $1/(1+\widetildeγ)$ without solving a Bellman equation.

cs.GT · cs.DM · cs.DS · econ.TH · math.OC

版本更新 · v2arXiv:2611.06891

Prophet Secretary for Matroids and XOS Valuations: A Separation at 1-1/e and a 0.6767 Guarantee for I.I.D. Weights

Hossein Esfandiari, MohammadTaghi Hajiaghayi

原文摘要

Ehsani, Hajiaghayi, Kesselheim, and Singla (SODA 2018) give $(1-1/e)$-competitive algorithms for matroid prophet-secretary and prophet-secretary with XOS valuation functions. In this work we show that these two guarantees have different limits. For every matroid, we give a randomized $(1-1/e+\varepsilon_0)$-competitive algorithm, where $\varepsilon_0=10^{-6}$. The guarantee holds for independent nonnegative values with finite expected optimum. For explicitly given finite distributions with rational values and probabilities, the algorithm has polynomial worst-case running time in the matroid independence-oracle model. The oracle tests whether a queried set is independent. The algorithm makes $O(N^4)$ such queries in expectation and $O(N^4\log(N+2))$ in the worst case, where $N$ is the number of elements. We further consider the i.i.d. version of this problem and provide a $0.6767$ competitive ratio for every matroid with i.i.d.\ nonnegative weights from a known distribution. This guarantee even holds in fixed arrival order (a.k.a. i.i.d. matriod prophet inequalities), even when the algorithm learns the order only as the elements arrive. For combinatorial auctions with XOS valuations, however, we show that $1-1/e$ is the optimal competitive ratio. We give an explicit family of finite instances showing that no online algorithm can guarantee a larger competitive ratio than $1-1/e$, even when the buyers' valuations are i.i.d., every additive clause has coefficients in $\{0,1\}$, and computation is unrestricted. Thus the matroid improvement exploits structure absent from general allocation with XOS valuations.

cs.DS · cs.GT

版本更新 · v2arXiv:2606.23662

Action-BED: Task-Driven Bayesian Experimental Design with Singly Intractable Objectives

Tom Rossa, Angus Phillips, Tom Rainforth

原文摘要

Bayesian experimental design (BED) has traditionally been based on maximising expected uncertainty reductions from prior to posterior. A major shortfall of this approach is that it leads to doubly intractable objectives that are difficult to optimise, while customising them to particular downstream tasks of interest can also be difficult. Following first principles decision theory, we demonstrate that BED can alternatively be formulated in terms of an expected future loss (EFL) on downstream actions, providing a simple and naturally task-driven framework. Critically, we then show that all such EFLs can be rearranged into singly intractable objectives that can be jointly optimised with respect to both the design policy and a downstream action policy using stochastic gradients, an approach we refer to as ACTION-BED. This formulation further sidesteps the need for any explicit posterior or marginal likelihood estimation and is naturally implicit, requiring only the ability to sample from the joint model over model parameters and data, and evaluate the downstream loss function. It thus allows design policies to be learned more effectively, efficiently, and simply than existing methods, while providing easy customisation to different downstream tasks and losses.

stat.ML · cs.LG