Peer Revenue Publish or profit

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Machine Learning

cs.LG Watch Machine Learning

Saturday 27 June

Machine Learning · Cross-listed from stat.ML

Variance Reduction for Stochastic Gradient Generalized Non-reversible Langevin Monte Carlo Algorithms

Bingye Ni, Xiaoyu Wang, Yingli Wang et al. (+1 more)

We study the leading-order fluctuation of stochastic gradient Euler-Maruyama estimators for generalized non-reversible Langevin dynamics. Under structural assumptions tailored to the small-stepsize central limit theorem and under an unbiased stochastic gradient oracle, we prove that the empirical average over a horizon of order the inverse squared stepsize satisfies a central limit theorem in the vanishing-stepsize regime. The limiting variance is characterized through the Poisson equation of the limiting full-gradient diffusion. We then rewrite this constant in an operator form that links it to the continuous-time asymptotic variance and, under standard operator-theoretic assumptions, derive a sufficient condition under which an anti-symmetric perturbation strictly reduces the leading-order fluctuation constant relative to the reversible baseline. We also identify bounded smooth predictive observables that re directly covered by the main theorem. As a separate Gaussian calculation beyond the bounded-test-function regime, we obtain closed-form formulas for quadratic Hamiltonians and linear observables. The framework covers non-reversible Langevin dynamics and augmented-state examples including Hessian-free high-resolution dynamics and a positive-definite subclass of gradient-adjusted underdamped Langevin dynamics that allow stochastic gradients. Numerical experiments on basic examples and Bayesian linear regression using synthetic data, and Bayesian logistic regression using real data support the predicted Gaussian fluctuations and show that the non-reversible schemes consistently reduce the root mean squared error (RMSE) relative to their reversible baselines.
Read the full abstract

All authors Bingye Ni, Xiaoyu Wang, Yingli Wang, Lingjiong Zhu

Machine Learning · Cross-listed from cs.CL

Structure-Preserving Document Translation via Multi-Stage LLM Pipeline: A Case Study in Marathi

Manasi Waghe, Danish Chandargi, Mohammad Aamir Rayyan et al. (+2 more)

Government documents in India are predominantly issued in regional languages such as Marathi, creating substantial accessibility barriers for non-native readers, interstate administrative bodies, and policy analysts. Although recent advances in neural machine translation have improved sentence-level translation quality, existing systems largely neglect document structure, formatting integrity, and domain-specific terminology, thereby limiting their applicability to official documentation. This paper presents a structure-preserving Marathi-to-English government document translation framework capable of performing end-to-end document transformation while maintaining layout fidelity. The proposed system integrates layout-aware optical character recognition, coordinate-based text extraction, large language model based translation, and structured document reconstruction through HTML representations. By enforcing spatial alignment constraints and preserving hierarchical document elements, the framework ensures structural consistency between the source and translated documents. Experimental evaluation on real-world Marathi government PDFs demonstrates improved structural preservation, translation coherence, and terminological consistency compared to conventional text-only translation pipelines. The proposed framework contributes toward scalable multilingual accessibility solutions for e-governance and administrative document processing.
Read the full abstract

All authors Manasi Waghe, Danish Chandargi, Mohammad Aamir Rayyan, Raviraj Joshi, A.R. Deshpande

Machine Learning

On design-unbiased algorithmic Machine Learning

Li-Chun Zhang, Siu-Ming Tam, Luis Sanguiao-Sande et al. (+2 more)

Machine Learning (ML) algorithms, such as k-Nearest Neighbours (kNN) or random forest, eschew the ideal of true data models in favour of predictive performance. However, minimising the MSE or F-score cannot lead to unbiasedness directly, which is important in many situations such as official statistics. We study the conditions of algorithmic ML, other than the existence and knowledge of true data models, which lead to unbiased prediction or classification for a given finite population, including how the training data may be sampled from the population, how a trained prediction algorithm can be tuned to achieve unbiased prediction or classification for that population, and how the performance of out-of-sample prediction or classification can be assessed unbiasedly. The inference is based on the known probability design of samples and training sets, rather than any assumed distributions or models.
Read the full abstract

All authors Li-Chun Zhang, Siu-Ming Tam, Luis Sanguiao-Sande, Wesley Yung, Anders Holmberg

Machine Learning

Generative Learning as a Tool to Improve Perception of Emotional Body Motion Expressions

Huakun Liu, Miao Cheng, Xin Wei et al. (+6 more)

Emotional body motion expressions are an essential element of non-verbal communication. Effectively conveying these expressions through technology is of utmost importance, for example, with virtual reality avatars and in social robotics. Recent advances in generative models have opened new opportunities for advancing research on emotional body motion learning. However, generating accurate emotional expression representations is challenging, given the subtlety of emotional cues, individual variability, and cultural differences. We investigate whether a generative model can implicitly learn emotional body motions directly from culturally grounded motion-capture data, without explicit emotion-motion guidance. Using a dataset of emotional performances by 49 Japanese actors, we trained a Transformer-based generative model to generate expressive motions conditioned on 13 discrete emotion labels. We evaluate the generated motions from two perspectives: (1) an LSTM-based classifier to assess recognizability by machine observers, achieving a recognition accuracy of 22.80%, and (2) a human perception study with Japanese raters to assess alignment with human affective interpretations, yielding a recognition accuracy of 24.91%. Beyond these, we evaluate the utility of generative modeling for three practical tasks: augmenting emotion recognition models, extracting representative emotion-specific motion patterns, and synthesizing smooth transitions between emotion intensities. Our findings highlight the potential of implicit, data-driven generative modeling to enhance affective computing applications and our understanding of emotion expressions.
Read the full abstract

All authors Huakun Liu, Miao Cheng, Xin Wei, Felix Dollack, Victor Schneider, Hideaki Uchiyama, Chia-huei Tseng, Yoshifumi Kitamura, Monica Perusquia-Hernandez

Machine Learning

Hierarchical Decision Making with Structured Policies: A Principled Design via Inverse Optimization

Yuexuan Wang, Jingyuan Zhou and Kaidi Yang

Hierarchical decision-making frameworks are pivotal for addressing complex control tasks, enabling agents to decompose intricate problems into manageable subgoals. Despite their promise, existing hierarchical policies face critical limitations: (i) reinforcement learning (RL)-based methods struggle to guarantee strict constraint satisfaction, and (ii) optimal control (OC)-based approaches often rely on myopic and computationally prohibitive formulations. To reconcile these trade-offs, hierarchical RL-OC architectures have emerged as a promising paradigm. However, the formulation of the lower-level optimization within these frameworks remains underexplored, often relying on heuristic or myopic objectives. In this work, we propose a principled framework that systematically integrates upper-level goal abstraction with structured lower-level decision making. We adopt an inverse optimization approach to inform the structure of the lower-level problem from expert demonstrations, ensuring that the objective of the lower-level policy remains aligned with the overall long-term task goal. To validate the approach, our framework is evaluated on distinct decision making tasks: network-based resource allocation and continuous collision avoidance. Empirical results demonstrate that our method consistently outperforms strong baselines based on end-to-end RL, learning-augmented optimal control, and existing hierarchical RL approaches in both efficiency and decision quality.
Read the full abstract

Machine Learning

A Path-Space Formulation of Prediction in World Models: From a Single Action to Prediction, Planning, and Irreversibility

Gunn Kim

We propose a path-space formulation of prediction in AI world models. Rather than sequences of one-step conditional distributions, we argue that a world model implicitly defines a probability measure over future trajectories. In the local regime where latent dynamics admit an effective Markovian description, this path measure takes the Onsager-Machlup form. Within this framework, prediction (most probable trajectory), planning (constrained optimization), and uncertainty (fluctuations) emerge as operations on a single action functional. We decompose the latent dynamics into reversible and irreversible components and introduce operational measures of entropy production from model rollouts. In controlled small-scale attention-based models, we find that attention asymmetry is acquired during training in proportion to the irreversibility of the data. Symmetrizing the learned attention suppresses entropy production and selectively degrades long-horizon prediction of irreversible dynamics while preserving relaxational prediction. These results suggest that irreversibility may serve as a computational resource for predictive world models. More generally, the fundamental predictive object is a distribution over future paths rather than states.
Read the full abstract

Machine Learning · Cross-listed from cs.AI

Self-Supervised Theorem Discovery in a Formal Axiomatic System

Kazuki Ota, Takayuki Osa and Tatsuya Harada

Recent artificial intelligence (AI) systems have shown remarkable progress in mathematical reasoning. Many existing approaches, including large language models (LLMs), draw on human prior knowledge in the form of mathematical text, code, or theorem libraries. Although these approaches are highly effective in practice, it remains an open question whether an agent can autonomously discover useful theorems without such human priors. We study this question in a formal axiomatic system by developing an agent that starts from axioms and inference rules alone and gradually grows a library of useful theorems. Concretely, we propose a self-supervised theorem-discovery algorithm that alternates between proof search and useful-theorem extraction, building a theorem library whose entries are reused as lemmas for subsequent proof search. Experiments show that the agent discovers tens of thousands of theorems and finds proofs for human-written benchmark problems, suggesting that its discoveries include theorems meaningful from a human mathematical perspective. Furthermore, the discovered theorems improve LLM proof performance when provided as prompt lemmas, indicating that they can serve as external knowledge for LLM reasoning. Our results provide evidence that useful theorems can emerge from proof search without relying on human-provided theorem libraries. More broadly, they suggest a path toward self-evolving AI systems for mathematics whose discoveries remain formally verifiable.
Read the full abstract

Machine Learning · Cross-listed from cs.RO

J-LAW: Joint Localization and Action-Conditioned World Modeling via Coupled Latent Factor Graphs

Guanqun Cao and Liang Chen

Classical simultaneous localization and mapping (SLAM) estimates metric poses and a geometric map but does not provide an action-conditioned predictive state. Action-conditioned world models learn compact latent dynamics but ignore global metric consistency and accumulate drift under open-loop rollout. We introduce J-LAW (Joint Localization and Action-Conditioned World Modeling), a unified factor-graph formulation that connects metric pose variables, predictive latent states, and persistent latent landmarks in this letter.J-LAW represents each image as a compact predictive state and combines it with pose or motion measurements through a separately learned mapping. Its maximum a posteriori (MAP) factor graph enforces consistency between these complementary sources of information over time. Experiments on PushT and WildGS show that J-LAW's factor-graph representation can improve long-horizon latent consistency and recover more reliable predictive states under partial observations, forming a foundation for future integrated localization and planning systems.
Read the full abstract

Machine Learning · Cross-listed from cs.CL

AnTenA: Actionable and Explainable Tensor Analysis System with Large Language Models

Dawon Ahn, Auder Der and Evangelos E. Papalexakis

Accurately explaining hidden patterns in multi-aspect data has typically been done by leveraging labels and/or accompanying auxiliary metadata. However, labels and auxiliary data may be inaccurate (e.g. nonstandard, inconsistent), insufficient (e.g. static tabular metadata for time-dependent recordings), or unavailable. % We propose \fullmethod (\method), which leverages the knowledge of large language models (LLMs) to explain the hidden patterns in human narratives. \method uses task-agnostic and task-specific prompts to explain extracted co-clustered latent patterns from tensor decomposition. To evaluate these explanations, we test the LLMs on forward and backward inference tasks. % Our demo system is available at https://github.com/dawonahn/ECML_PKDD_AnTenA.
Read the full abstract

Machine Learning · Cross-listed from eess.IV

A Neuroimaging Simulation Framework for Developing and Evaluating Causal AI

Eryn Libert-Scott, Emma A.M. Stanley, Vibujithan Vigneshwaran et al. (+3 more)

Causally linking disease-related factors to image-derived biomarkers provides a powerful pathway to understanding disease mechanisms. Despite growing interest in applying causal artificial intelligence (AI) approaches for this task, these methods still need to be adapted for complex medical images, and especially, neuroimaging. However, the lack of ground-truth data presents a barrier to development. To bridge this gap, we developed and tested a method for generating synthetic neuroimages, which adhere to a user-specified causal structure describing the non-image to image variable relationships, permitting the creation of ground-truth neuroimaging datasets. In the simulated T1-weighted magnetic resonance images, anatomical variability is modeled by sampling from a subspace estimated from real data and deforming a template image to create unique simulated subjects. Causal relationships are encoded via precise volumetric changes of any region-of-interest without unwanted global artifacts. We achieved relative volume errors of 0.3-2.66% for the targeted regions-of-interest and demonstrate their statistically significant causal relationships, while maintaining mean absolute errors for non-target brain regions between 0.034-0.397ml. An initial evaluation of causal discovery methods exposes their limited ability to suppress spurious connections, highlighting the need for image-appropriate methods. Our framework is the first to enable the generation of realistic synthetic 3D neuroimages with explicit causal control that can serve as the missing ground-truth data necessary for the objective benchmarking and development of causal AI methods.
Read the full abstract

All authors Eryn Libert-Scott, Emma A.M. Stanley, Vibujithan Vigneshwaran, Matthias Wilms, Erik Y. Ohara, Nils D. Forkert

Machine Learning

Constrained Tabular Diffusion for Finance

Michael Cardei, Jose M Munoz, Oscar Barrera et al. (+2 more)

Generative models in finance face the dual challenge of producing realistic data while satisfying strict regulatory and economic objectives, a requirement that standard tabular diffusion models cannot provide. To address this difficulty, we introduce Constrained Tabular Diffusion for Finance (CTDF), a novel integration of sampling-time feasibility operations with mixed-type tabular diffusion in financial applications. By incorporating a training-free feasibility operator into the reverse-diffusion sampling loop, CTDF enforces hard constraints for applications such as simulation, legal compliance, and extrapolation. Extensive experiments on large-scale financial datasets demonstrate zero constraint violations and improvement in scarce data utility. CTDF establishes a robust method for generating trustworthy and compliant synthetic data, opening new avenues for rigorous generative modeling and analysis in the financial domain.
Read the full abstract

All authors Michael Cardei, Jose M Munoz, Oscar Barrera, Shreyas K Chandrahas, Partha Saha

Machine Learning

Entropy-Regularized Reinforcement Learning for Linear-Quadratic Stackelberg Differential Games in Regime-Switching Diffusion Models

Congde Hu, Danping Li, Lin Xu et al. (+1 more)

Stackelberg differential games (SDGs) provide a powerful framework for hierarchical decision-making in stochastic and continuous-time environments, yet their solution remains computationally challenging due to the complexity of traditional dynamic programming and Hamilton-Jacobi-Bellman-Isaacs (HJBI) methods, especially in high-dimensional systems. This paper proposes an entropy-regularized reinforcement learning (ERRL) approach for linear-quadratic SDGs (LQ-SDGs) within a continuous-time diffusion framework governed by Markovian regime switching. The key innovation lies in deriving exploratory weakly-coupled HJBI equations with entropy regularization, which promotes stochastic policies that actively avoid suboptimal equilibria – a limitation of classical SDG methods. Neural networks are integrated to approximate regime-dependent value functions and solve high-dimensional partial differential equations (PDEs) efficiently, while a novel sampling technique enhances computational tractability. Numerical results demonstrate the effectiveness of the framework compared to conventional approaches, particularly in escaping suboptimal traps through exploratory policies. The study highlights the critical role of entropy regularization and neural network approximations in achieving robust solutions for hierarchical decision-making problems under abrupt environmental shifts.
Read the full abstract

All authors Congde Hu, Danping Li, Lin Xu, Wenying Xu

Machine Learning · Cross-listed from econ.EM

MACROCAST: A Vintage-Consistent Time Series Foundation Model for Real-Time Macroeconomic Forecasting

Andrea Carriero, Davide Pettenuzzo and Shubhranshu Shekhar

We introduce MACROCAST, a lightweight Time Series Foundation Model (TSFM) for real-time macroeconomic forecasting. Existing TSFMs suffer from data leakage in two forms: temporal contamination, as the model may have seen the realized values of the series it forecasts, and revision bias, as training on fully revised data diverges from the preliminary, vintage-specific releases available to real-time forecasters. MACROCAST is, to our knowledge, the first TSFM that rules out both forms of leakage entirely: at no stage of training is the model exposed to information that would not have been available to a forecaster in real time. We train MACROCAST first on purely synthetic time series in approximately one GPU-day and then fine-tune it on synthetic time series drawn from Bayesian VARs, dynamic factor models, and ARIMA specifications estimated on vintage-specific ALFRED data. Because pretraining uses only simulated data and fine-tuning uses only real-time vintages, no observed future or revised value ever enters the model; each fine-tuning run takes nine minutes. Evaluated on the FRED-MD database in a genuine real-time out-of-sample exercise, MACROCAST improves on the AR(1) benchmark for roughly 80% of series-horizon pairs, matches or surpasses Chronos-2 – the strongest currently available TSFM – and outperforms the Bayesian VAR and dynamic factor model benchmarks, all in a data-leakage-free manner.
Read the full abstract

Machine Learning

Entropy Regularized Reinforcement Learning for Zero-Sum Stochastic Differential Games in a Regime-Switching Jump-Diffusion Process

Congde Hu, Zhuo Jin, Danping Li et al. (+1 more)

To address parameter misspecification and sudden structural environmental changes in conventional stochastic differential game (SDG) frameworks, this paper introduces a distributional control approach that characterizes optimal strategies as probability distributions over actions, conditioned on the continuous state, the discrete regime state, and parameters. This forms a reinforcement learning framework for entropy-regularized zero-sum stochastic differential games (ERRL-ZSSDGs) in a regime-switching jump-diffusion process. Using the dynamic programming principle (DPP), we derive the associated coupled systems of Hamilton-Jacobi-Bellman-Isaacs (HJBI) equations, from which equilibrium strategies are expressed via gradients of the value function. For linear-quadratic problems, semi-analytical solutions for both value function and equilibrium strategies are obtained by solving a system of coupled ordinary differential equations (ODEs). In more general settings, an Actor-Critic policy improvement algorithm is developed to approximate the value functions and equilibrium policies across different regimes. The method is applied to an investment game, and numerical examples illustrate the effect of the temperature parameter and regime transitions on optimal policies and values.
Read the full abstract

All authors Congde Hu, Zhuo Jin, Danping Li, Lin Xu

Machine Learning

Closed-Form Steepest Descent Direction toward Flat Minima: Reducing Upper Bounds on the Loss Hessian Eigenspectrum in Neural Networks

Yuto Omae, Kazuki Sakai, Yohei Kakimoto et al. (+3 more)

The flatness hypothesis suggests that flatness of the loss landscape, as measured by the eigenvalues of the loss Hessian, correlates with better neural network generalization. While various algorithms reduce these eigenvalues, most focus on procedural design, leaving it unclear how data distributions and NN parameters structurally determine directions toward flat minima. Characterizing these directions analytically is generally intractable. To overcome this mathematical difficulty, recent studies derived the Wolkowicz-Styan (WS) upper bound on the maximum eigenvalue of the cross-entropy loss Hessian in three-layer NNs. Although this upper bound is differentiable, its gradient was not derived. Therefore, we analytically derive the gradient of the WS upper bound to characterize directions leading to flat minima. Based on this, we propose Hessian Spectral Range (HSR) Regularization, which updates parameters along the steepest descent direction of the WS bound. Experiments demonstrate that HSR Regularization narrows the Hessian eigenvalue spectrum, avoids sharp minima and saddle points, and promotes convergence to flat minima. Although the applicability of this method is currently limited to cross-entropy loss and three-layer architectures, to the best of the authors' knowledge, this is the first study to report a closed-form gradient that promotes convergence to flat minima without numerical approximations. Therefore, the theoretical analysis of this gradient is expected to contribute to the further development of NNs.
Read the full abstract

All authors Yuto Omae, Kazuki Sakai, Yohei Kakimoto, Makoto Sasaki, Yusuke Sakai, Hirotaka Takahashi

Machine Learning

When More Sampling Hurts: The Modal Ceiling and Correlation Ceiling of Test-Time Scaling

Yong Yi Bay and Kathleen A. Yearick

People overthink; language models over-sample, and the extra effort can talk both into a worse answer. Reasoning systems answer a hard question by sampling it many times (test-time scaling), and the more they draw, the more often a correct answer turns up somewhere, so coverage, the fraction of problems with at least one correct try, climbs and appears to be progress. But a deployed system must return one answer, and choosing it, not knowing which try is right, is selection; selection is capped, and past a point extra samples only make the model surer of a confident mistake, even as every draw adds cost. The gap between climbing coverage and stalled selection, the identifiability gap, is the answer a model can produce but not pick. So the real question is not whether to sample but how far, and the answer is: not far. For picking an answer, the vote has already settled within a few dozen draws, the modal ceiling; for scoring a benchmark, sooner still, the correlation ceiling. Beyond that, extra draws cost compute and add nothing, and can even make the answer worse. This paper turns the cutoff into a single number, the effective number of samples, that any sampling run already reveals. The bottleneck is recognizing a right answer, not generating one.
Read the full abstract

Machine Learning · Cross-listed from q-bio.BM

Transformer-Based Active Learning for Data-Efficient Vaccine Epitope Selection in PRRS

Aspen Erlandsson Brisebois, Zahed Khatooni, Connor Burbridge et al. (+5 more)

High-fidelity molecular docking simulations can produce biologically relevant estimates of epitope-receptor binding affinity but are computationally expensive and therefore limit the number of candidates that can be screened for vaccine design. In this work, we evaluate machine learning (ML) approaches where variants of active learning are used to classify instances of high binding affinity between 9-mer epitopes and a well-conserved swine leukocyte antigen (SLA) receptor in the context of Porcine Reproductive and Respiratory Syndrome (PRRS). We use an internally generated dataset of 80 epitope-SLA docking affinities, each requiring more than 48 hours of high-performance computing (HPC). Multiple model families (linear, MLP, CNN, and a small transformer) are trained under strict low-data conditions within a pool-based active learning loop. In each case, optimal model configurations are identified by conducting large-scale hyperparameter optimization over the combined space of model architecture, training configuration, acquisition policy, and ensemble decision rules. To mitigate the effects of data subsample selection, each candidate configuration is evaluated by averaging performance over many randomized and balanced training and validation data subsets. Across experiments, transformer-based sequence models consistently emerged as the best-performing architecture, with active incremental learning yielding significant improvement over a baseline random sample acquisition strategy. Under moderate training data availability (N=30), the optimized ML-model configuration outperforms a standard baseline trained on twice the amount of data. Under higher training data availability (N=60), the same configuration achieves a peak accuracy of 86.8%, consistent with an upper bound of 85% classification accuracy based on two independent estimates of conformational noise.
Read the full abstract

All authors Aspen Erlandsson Brisebois, Zahed Khatooni, Connor Burbridge, Brook Byrns, Heather L. Wilson, Sureesh Tikoo, Steven Rayan, Gordon Broderick

Machine Learning · Cross-listed from quant-ph

Exploring the Effects of Entanglement on Quantum Machine Learning of Pathogen Epitope-Receptor Binding

Aspen Erlandsson Brisebois, Luis Pablo Gonzalez Dominguez, Shivansi Prajapati et al. (+8 more)

Parameterized quantum circuits (PQCs) provide a flexible substrate for hybrid quantum machine learning (QML), but their practical value on Noisy Intermediate-Scale Quantum (NISQ) devices remains an empirical question, especially because training depth and scale can introduce optimization challenges such as barren plateaus. Here we study how the number and topology of two-qubit entangling gates in the feature-map stage influence a fixed hybrid QNN workflow for classifying strong versus weak epitope-receptor binding in Porcine Reproductive and Respiratory Syndrome (PRRS) vaccine design. The dataset consists of docking-derived binding affinities for N=80 9-mer epitopes, labeled as Strong or Weak binding, and partitioned into training, validation, and test subsets using a 40:30:30 split. We compare a classical CNN benchmark with a hybrid Embedding-QNN architecture under four feature-map configurations: a non-entangling Z feature map, an all-to-all high-entanglement ZZ feature map, and two interleaved nearest-neighbour entanglement patterns of low and high depth. Among the configurations tested, the high-entanglement ZZ feature map is seen to provide the strongest evidence of reduced training-set overfit, with a lower training area under the accuracy curve (AUAC) and the highest test/training AUAC ratio, while preserving competitive test-set accuracy. These results do not establish a general QML advantage, but they suggest that feature-map entanglement topology is a meaningful design variable for sparse biological screening tasks and warrants further evaluation with additional metrics, larger datasets, and noise-aware or hardware-based experiments.
Read the full abstract

All authors Aspen Erlandsson Brisebois, Luis Pablo Gonzalez Dominguez, Shivansi Prajapati, Zahed Khatooni, Heather L. Wilson, Connor Burbridge, Brook Byrns, Sureesh Tikoo, Christophe Pere, Steven Rayan, Gordon Broderick

Friday 26 June

Machine Learning · Cross-listed from cs.CL

H2DF: Calibrated Target Bands for Controllable Language-Model Unlearning

Jupiter Yao

Gradient ascent (GA) is a simple language-model unlearning baseline, but it continues increasing forget loss after useful forgetting has occurred. This unbounded pressure can damage retained utility and make forgotten examples abnormally high-loss. We introduce H2DF, a calibrated target-band objective that applies GA-like pressure below a data-dependent lower target and suppresses, or reverses, that pressure after the target region is reached. The targets are estimated from matched non-member examples before training, so the base objective requires one forget-batch forward/backward pass per optimization step; our reported TOFU variant adds sparse retain replay every tenth step. We instantiate a one-sided objective for TOFU question answering and a two-sided objective for MUSE-News language modeling. Across three TOFU seeds, H2DF obtains a forget NLL of 1.528 with margin 0.049 and retain NLL of 1.165 with margin 0.047, matching GradDiff while using retain replay only every tenth step and showing substantially lower variability than GA. On MUSE-News, H2DF improves retention over GA and NPO and is competitive with SimNPO, but does not dominate it. Ablations show that the upper target reduces overshoot and that validation-based checkpoint selection is important. These results support calibrated target bands as a practical mechanism for controlling forgetting strength, while also exposing sensitivity to random seed and calibration quality.
Read the full abstract

Machine Learning

Physics-Informed Conformal Prediction: Embedding PDE Consistency into Distribution-Free Uncertainty Quantification for Neural Operators

Michael Chin

Neural operators such as the Fourier Neural Operator (FNO) achieve remarkable accuracy in approximating solutions to partial differential equations (PDEs). However, providing rigorous uncertainty estimates remains an open challenge. We propose Physics-Informed Conformal Prediction (PI-CP), a framework that embeds PDE residuals into the nonconformity score of split conformal prediction, producing prediction intervals that are (i) distribution-free with provable coverage guarantees, and (ii) spatially adaptive when the PDE residual correlates with prediction error – tighter where physics is well-satisfied, wider where it is violated. Additionally, we prove that FNO's translation equivariance creates a fundamental approximation barrier for PDEs with Dirichlet boundary conditions, and show that coordinate channels resolve this with up to 63x error reduction. We validate PI-CP across six physics scenarios – heat conduction (2D/3D), structural mechanics (2D/3D), Darcy flow, and Navier-Stokes – demonstrating consistent 89-91% coverage for all four Conformal methods, while MC Dropout and Deep Ensembles are unstable (82-100%). FNO outperforms CNN and DeepONet by 10-12x.
Read the full abstract

Machine Learning · Cross-listed from cs.CL

AdaThinking-E: One-Token Entropy Regulation for Adaptive Thinking

Zining Wang, Tongkun Guan, Boming Chen et al. (+8 more)

Multimodal large language models have demonstrated strong document reasoning capabilities by incorporating explicit thinking processes. While this capability significantly improves performance on challenging tasks, current models apply such deep reasoning uniformly to all questions, resulting in unnecessary computational overhead for simple task. This not only degrades user experience but also negatively impact accuracy on benchmark datasets. We identify the critical need for adaptive thinking mechanisms that can intelligently determine when to engage reasoning based on question complexity. To address this, we propose AdaThinking-E, a novel reinforcement learning framework that learns adaptive thinking through one-token entropy regulation. Our key insight is that model confidence in the decision to engage thinking (or not) can be quantified through entropy analysis of the predicted probability distribution at critical decision tokens. This observation motivates our entropy-governed reward mechanism: the training process naturally transitions from high-entropy exploration, where the model experiments with different thinking strategies, to low-entropy convergence with confident, generalizable decision-making policies. Crucially, this approach enables models to intrinsically discover when to think without requiring manual intervention or external difficulty labels. Extensive experiments demonstrate that our approach enables models to be both accurate on complex problems and efficient on simple ones across diverse document tasks.
Read the full abstract

All authors Zining Wang, Tongkun Guan, Boming Chen, Zhentao Guo, Jianqiang Liu, Chao Jin, Chen Duan, Kai Zhou, Pengfei Yan, Wei Shen, Xiaokang Yang

Machine Learning · Cross-listed from cs.CL

Affix Cache for Diffusion Large Language Models

Kaihua Liang, An Zhong, Xin Tan et al. (+4 more)

Diffusion Large Language Models (DLLMs) enable non-autoregressive decoding, but efficient inference support remains immature: unlike autoregressive models, whose requests reuse a shared prefix key-value (KV) cache, DLLMs use bidirectional attention, so a shared context's KV states depend on the tokens still being decoded, leaving directly reused caches stale and full recomputation necessary. We present ACache, a cross-request cache reuse mechanism for shared spans, or affixes, at any position: prefix, infix, or suffix. ACache measures the influence of affix tokens on the masked generation region to identify a small request-specific subset as Anchor Tokens, and recomputes only their KV states while reusing the remaining affix cache. Built on state-of-the-art intra-request caching mechanisms, ACache recovers most of the accuracy lost to direct affix-cache reuse on average when recomputing around 20% of affix tokens, and at that budget preserves more accuracy than selection criteria adapted from prior cross-request cache-reuse systems. We co-design ACache with a modern inference engine, whose attention reads each request's recomputed Anchor KV states alongside one affix cache shared across concurrent requests. Against the same system with only intra-request caching, ACache cuts recompute latency by up to 56.7%, translating to as much as 1.71$\times$ end-to-end throughput, while reducing peak KV cache memory by up to 45.8%.
Read the full abstract

All authors Kaihua Liang, An Zhong, Xin Tan, Zafar Ayyub Qazi, Hong Xu, Jian Weng, Marco Canini

Machine Learning · Cross-listed from cs.AI

AI Learning and Conceptual Transfer in the Game of Hidden Rules

Christo Mathew, Wentian Wang, Jacob Feldman et al. (+4 more)

This report summarizes the work conducted on the Game of Hidden Rules (GOHR), focusing on reinforcement learning agents trained to infer hidden rules from trial-and-error feedback, representation design, rule difficulty analysis, transfer learning, generalization, and pseudo-bot-assisted human learning analysis. The report focuses on the Transformer-based A2C framework, Feature-Centric and Object-Centric representations, experimental findings, and classification of human learning data.
Read the full abstract

All authors Christo Mathew, Wentian Wang, Jacob Feldman, Lazaros K. Gallos, Paul B. Kantor, Vladimir Menkov, Hao Wang

Machine Learning · Cross-listed from q-fin.CP

If It Walks Like an Arbitrage: Protocol-Agnostic Detection with Decidable Structural Equivalence

Adam Khayam, Hamid Kolli, Mohamed Iguernlala et al. (+1 more)

Whether a transaction performed an arbitrage, and by which route, is a question asked of its execution trace after the fact. We conjecture that such traces admit a normal form on which questions of this kind become queries, and we test it by building one and putting it to work. Each trace becomes an abstract syntax tree of token transfers, grouped by call- frame nesting. A term rewriting system of 16 rules reduces it. Rewriting terminates and carries exactly the transfers of the trace, whichever order the rules fire in. Under a deterministic kernel scanning the EVM-fixed trace order, every trace has a unique normal form, and the structural equivalence this induces on fund flows is decidable. Preservation, termination, soundness, uniqueness and decidability are mechanized in Rocq with zero admitted obligations. We report arbitrage detection in full: cycles emerge at the fixpoint and are read off the normal form with no protocol-specific patterns. Detection is the query we evaluate at scale; structural equivalence is a second query. The pipeline depends only on the standard ERC token and WETH ABIs, so the same binary runs unmodified on Arbitrum and BSC. We evaluate on two arbitrary block ranges, analysed in full with no transaction excluded: 220 000 Ethereum blocks against EigenPhi, a widely used MEV detection platform, and 1 000 shared blocks against ArbiNet, a graph neural network classifier. These are the only tools and label sets in this domain we were able to reuse. We report 469 801 confirmed arbitrages, overlapping 83.5% with EigenPhi and 81% with ArbiNet, together with 245 497 attempted arbitrages and 60 199 confirmed detections EigenPhi does not report. 99.2% follow from the fixpoint alone and are sound over the decoded transfers, and manual validation of 500 transactions finds no false positive among the confirmed.
Read the full abstract

All authors Adam Khayam, Hamid Kolli, Mohamed Iguernlala, Çagdas Bozman

Machine Learning

Geometry Is Not Robustness: A Trajectory-Level Study of PGD Evaluation

Dhairysheel Durgule

Projected Gradient Descent (PGD) is widely used to evaluate adversarial robustness, typically via final adversarial accuracy, which does not capture model behaviour throughout the attack. Recent work proposes trajectory-level diagnostics, such as loss evolution, gradient alignment, and steps-to-failure, for deeper insight into adversarial optimisation dynamics. However, whether these diagnostics reliably indicate robustness strength remains unclear. We conduct a trajectory-level investigation of PGD attacks on convolutional neural networks trained on Fashion-MNIST. We compare clean-trained and adversarially-trained models across multiple robustness regimes, using rigorous 20-step PGD evaluations with random initialisation and multiple restarts for robustness measurement, and single-initialisation trajectory recording for diagnostics. We record full PGD trajectories across 3000 clean-correct samples per model and analyse loss evolution, gradient alignment, and failure timing across attack iterations. Our results reveal a clear robustness hierarchy across models; however, trajectory metrics do not contribute equally to its identification. Mean loss trajectories and gradient alignment patterns appear quantitatively similar across adversarially-trained models with substantially different robust accuracies. In contrast, steps-to-failure distributions provide a clearer separation of robustness regimes, directly reflecting functional resistance to adversarial perturbation. These findings indicate that trajectory-level diagnostics describe optimisation geometry but do not independently measure adversarial robustness. Their interpretability depends on robustness regime, attack strength, and multi-metric evaluation. Trajectory-level analysis should be a complementary diagnostic tool, interpreted in context, rather than a replacement for standard robustness measurements.
Read the full abstract

Machine Learning

Don't Claim Benchmark-Oriented Optimization Improves General Coding Capability – Diverse Evaluation Is Required

Egor Shibaev, Vera Kudrevskaia, Timur Galimzyanov et al. (+9 more)

Post-training papers, model cards, and blog posts often treat scores on a small set of coding benchmarks (e.g., SWE-bench and LiveCodeBench) as evidence of broad coding capability, both for research artifacts and user-facing systems. We argue that optimization for these benchmarks leads to measuring task-specific performance, creating a meaning gap between measured scores and claims of general coding ability. We examine this gap with a Django-based case study benchmark suite we create. Evaluating foundation models and checkpoints post-trained on SWE-bench trajectories, we find that benchmark rankings frequently fail to generalize. Post-trained checkpoints show little cross-task transfer, and SWE-bench optimization yields limited or no gains on our tasks or on LiveCodeBench. Similarly, fine-tuning on individual Django modalities fails to transfer. We conclude that a small number of benchmarks is insufficient for evaluating diverse models under benchmark optimization pressure. We encourage the community to use differentiated evaluation - holistic assessment for frontier models, multi-task suites for research, and human-in-the-loop studies for narrow task applications. Finally, we argue for creating a capability taxonomy and sustained benchmark maintenance, rather than one-off benchmark releases. Without reliable evaluation standards, engineers and researchers using LLMs and agents have to rely on insufficient evidence to make research, development, and deployment decisions.
Read the full abstract

All authors Egor Shibaev, Vera Kudrevskaia, Timur Galimzyanov, Mikhail Evtikhiev, Ana Terna, Rastislav Rabatin, Timur Kudashev, Timofey Bryksin, Arina Puchkova, Patrik Bartak, Egor Bogomolov, Sergey Titov

Machine Learning · Cross-listed from cs.CY

Challenges for Musical Education in the Age of AI and Digital Transformation

Jean-Pierre Briot

Music education has never been a static discipline. Each major technological shift has forced educators and institutions to reconsider what they teach, how they teach it, and why. We now stand at what may be the most consequential of such turning points. Three deeply intertwined transformations have been converging simultaneously: 1. The very nature of music has changed: how it is made, distributed, consumed, and valued; 2. The public for music has changed: listening habits are now shaped by streaming algorithms and the boundary between consumer and creator has blurred; 3. Music-making itself has changed: digital audio workstations (DAWs) have for two decades been reshaping compositional practice. In addition, generative AI has now irrupted, capable of producing complete, stylistically coherent musical pieces from a short text prompt. These changes are not independent of one another, and they all bear directly on musical education - both the content that must be taught, and the pedagogical tools and methods available to teach it. This paper attempts to map these challenges and to consider how education might adapt. Section 2 surveys the changes in various aspects of music (nature, production, public, economics). Section 3 examines the implications for education before Section 4 concludes.
Read the full abstract

Machine Learning · Cross-listed from cs.AI

GLIDE: Guided Layerwise Hybrid Attention for Efficient LLM Inference

Vimal William, Ravi Tandon and Jyotikrishna Dass

As Large Language Models scale to increasingly long contexts, the memory I/O and computational overhead of the Key-Value (KV) cache during decoding emerges as the primary throughput bottleneck. To address this, we propose GLIDE, a Guided Layerwise Hybrid Attention that strategically integrates sliding-window softmax attention with linear recurrent aggregation. GLIDE is motivated by layer-wise heterogeneity: early layers exhibit high sensitivity to softmax removal, while deeper layers demonstrate redundancy and tolerate aggressive replacement by linear alternatives. Leveraging this insight, GLIDE introduces a layer-wise adaptive mechanism wherein each layer balances an efficient linear recurrence with a variable-sized softmax window. Unlike uniform hybrid approaches, GLIDE non-uniformly compresses the softmax footprint across the model, reducing aggregate KV cache I/O while preserving expressive power where most vital. Empirical evaluations demonstrate the GLIDE achieves superior performance-efficiency tradeoffs, reducing end-to-end latency for long-context generation without compromising quality.
Read the full abstract

Machine Learning · Cross-listed from cs.AI

LeanFlow: A Case Study in Workflow-Driven Lean Autoformalization

Lazar Milikic, Simon Guilloud, Khanh Nguyen et al. (+1 more)

We present and evaluate LeanFlow, an LLM agent system specialized for translating mathematical papers into buildable Lean projects. Recent verifier-in-the-loop systems show that large formal artifacts can be produced, but it remains unclear which runtime mechanisms affect completion, auditability, or efficiency in document-to-project formalization. We study this question through case studies on two previously unformalized mathematical papers in number theory and measure theory, using model, proof-workflow, and toolset ablations with Kimi2.6 and GPT5.5; we report task outcome, API calls, input tokens, and output tokens. With Kimi2.6, the full workflow completes both document-level projects within the 2000-call budget, while no-queue variants reach the budget limit; with GPT5.5, all document-level variants complete, and the full workflow has the lowest or tied-lowest input-token cost on both sources. As complementary calibration, LeanFlow reaches 75.7% BEq+ on the PFR slice of RLM25 and solves all five ICML 2026 AI for Math TCS challenge projects in our GPT5.5 runs.
Read the full abstract

All authors Lazar Milikic, Simon Guilloud, Khanh Nguyen, Viktor Kuncak

Machine Learning

Self-Evolving Just-In-Time Memory for Proactive Embodied Safety

Bingrui Sima, Lizhong Wang, Xiaoya Lu et al. (+2 more)

While Vision-Language Models (VLMs) have empowered embodied agents to execute complex household tasks, they struggle to proactively handle dynamically emerging hazards during closed-loop interactions. Existing safety approaches often rely on runtime guardrails to block unsafe actions or induce excessive caution, which severely stalls task progress instead of actively resolving the underlying risks. To break this safety-progress trade-off, we introduce the Self-Evolving Just-In-Time Memory framework, which reframes embodied safety from progress-stalling guardrails to proactive hazard mitigation. The framework consists of a Risk-Sufficient Topological Belief Graph (RSG) for persistent safety-relevant state tracking under partial observability, an Agency-Grounded Factual Memory for precise hazard anticipation, and an Experience Memory that injects procedural Meta-Skills to guide executable, progress-preserving mitigation. Furthermore, we propose an automated Test-Verify-Write loop, allowing agents to continually refine their mitigation Meta-Skills from execution traces at test time. Experiments on IS-Bench demonstrate that our framework substantially boosts the Safe-Success rate across multiple VLM backbones (e.g., +30.3% on Qwen3-VL-8B), enabling agents to proactively mitigate hazards without stalling task progress. Code is available at https://github.com/DyMessi/JIT-Memory.
Read the full abstract

All authors Bingrui Sima, Lizhong Wang, Xiaoya Lu, Kun He, Xiao Yang