paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

LakeMLB: Data Lake Machine Learning Benchmark

Feiyu Pan, Tianbin Zhang, Aoqian Zhang, Yu Sun, Zheng Wang, Lixing Chen, Li Pan, Jianhua Li

Data lakes have become a fundamental platform for large-scale machine learning by enabling flexible management of heterogeneous data. Despite their growing importance, standardized benchmarks for evaluating machine learning performance in data lake environments remain scarce. To address this gap, we present LakeMLB (Data Lake Machine Learning Benchmark), the first benchmark designed for multi-table machine learning in data lakes. LakeMLB focuses on two representative scenarios, Union and Join, and provides six real-world datasets spanning diverse domains. It supports three representative multi-table learning paradigms: pre-training, data augmentation, and feature augmentation, together with standardized data splits and evaluation protocols. We conduct extensive experiments with state-of-the-art tabular learning methods and provide insights into their performance across different data lake scenarios. We release both datasets and code to facilitate rigorous research on machine learning in data lake ecosystems; the benchmark is available at https://github.com/zhengwang100/LakeMLB.

arXiv

NeuroPareto: Calibrated Acquisition for Costly Many-Goal Search in Vast Parameter Spaces

Rong Fu, Chunlei Meng, Haoyu Zhao, Kun Liu, JiaBao Dou, Youjin Wang, Simon James Fong

The pursuit of optimal trade-offs in high-dimensional search spaces under stringent computational constraints poses a fundamental challenge for contemporary multi-objective optimization. We develop NeuroPareto, a cohesive architecture that integrates rank-centric filtering, uncertainty disentanglement, and history-conditioned acquisition strategies to navigate complex objective landscapes. A calibrated Bayesian classifier estimates epistemic uncertainty across non-domination tiers, enabling rapid generation of high-quality candidates with minimal evaluation cost. Deep Gaussian Process surrogates further separate predictive uncertainty into reducible and irreducible components, providing refined predictive means and risk-aware signals for downstream selection. A lightweight acquisition network, trained online from historical hypervolume improvements, guides expensive evaluations toward regions balancing convergence and diversity. With hierarchical screening and amortized surrogate updates, the method maintains accuracy while keeping computational overhead low. Experiments on DTLZ and ZDT suites and a subsurface energy extraction task show that NeuroPareto consistently outperforms classifier-enhanced and surrogate-assisted baselines in Pareto proximity and hypervolume.

arXiv

AROpt: An Optimization Method for Autoregressive Time Series Forecasting

Zheng Li, Jerry Cheng, Huanying Gu

Current time-series forecasting models are primarily based on transformer-style neural networks. These models achieve long-term forecasting mainly by scaling up the model size rather than through genuinely autoregressive (AR) rollout. From the perspective of large language model training, traditional time-series forecasting model training ignores the monotonic error-growth heuristic. In this paper, we propose a novel training method for time-series forecasting that enforces two key properties: (1) AR prediction errors should increase with the forecasting horizon. Violations of this trend are interpreted as rollout inconsistency and are softly penalized during training, and (2) the method enables models to be able to concatenate short-term AR predictions to form flexible long-term forecasts. Empirical results demonstrate that our method establishes a new state-of-the-art across multiple benchmarks, achieving an MSE reduction of more than $10\%$ compared to iTransformer and other recent strong baselines. Furthermore, it enables short-horizon forecasting models to perform reliable long-term predictions at horizons over 7.5 times longer. Code is available at https://github.com/LizhengMathAi/AROpt

arXiv

Geometric Analysis of Token Selection in Multi-Head Attention

Timur Mudarisov, Mikhal Burtsev, Tatiana Petrova, Radu State

We present a geometric framework for analysing multi-head attention in large language models (LLMs). Without altering the mechanism, we view standard attention through a top-N selection lens and study its behaviour directly in value-state space. We define geometric metrics - Precision, Recall, and F-score - to quantify separability between selected and non-selected tokens, and derive non-asymptotic bounds with explicit dependence on dimension and margin under empirically motivated assumptions (stable value norms with a compressed sink token, exponential similarity decay, and piecewise attention weight profiles). The theory predicts a small-N operating regime of strongest non-trivial separability and clarifies how sequence length and sink similarity shape the metrics. Empirically, across LLaMA-2-7B, Gemma-7B, and Mistral-7B, measurements closely track the theoretical envelopes: top-N selection sharpens separability, sink similarity correlates with Recall. We also found that in LLaMA-2-7B heads specialize into three regimes - Retriever, Mixer, Reset - with distinct geometric signatures. Overall, attention behaves as a structured geometric classifier with measurable criteria for token selection, offering head level interpretability and informing geometry-aware sparsification and design of attention in LLMs.

arXiv

Searching for Quantum Effects in the Brain: A Bell-Type Test for Nonclassical Latent Representations in Autoencoders

I. K. Kominis, C. Xie, S. Li, M. Skotiniotis, G. P. Tsironis

Whether neural information processing is entirely classical or involves quantum-mechanical elements remains an open question. Here we propose a model-agnostic, information-theoretic test of nonclassicality that bypasses microscopic assumptions and instead probes the structure of neural representations themselves. Using autoencoders as a transparent model system, we introduce a Bell-type consistency test in latent space, and ask whether decoding statistics obtained under multiple readout contexts can be jointly explained by a single positive latent-variable distribution. By shifting the search for quantum-like signatures in neural systems from microscopic dynamics to experimentally testable constraints on information processing, this work opens a new route for probing the fundamental physics of neural computation. The proposed test identifies violations of classical latent-variable consistency at the level of statistical representations, without assuming a specific underlying physical mechanism.

arXiv

Gradient-based Optimisation of Modulation Effects

Alistair Carson, Alec Wright, Stefan Bilbao

Modulation effects such as phasers, flangers and chorus effects are heavily used in conjunction with the electric guitar. Machine learning based emulation of analog modulation units has been investigated in recent years, but most methods have either been limited to one class of effect or suffer from a high computational cost or latency compared to canonical digital implementations. Here, we build on previous work and present a framework for modelling flanger, chorus and phaser effects based on differentiable digital signal processing. The model is trained in the time-frequency domain, but at inference operates in the time-domain, requiring zero latency. We investigate the challenges associated with gradient-based optimisation of such effects, and show that low-frequency weighting of loss functions avoids convergence to local minima when learning delay times. We show that when trained against analog effects units, sound output from the model is in some cases perceptually indistinguishable from the reference, but challenges still remain for effects with long delay times and feedback.

arXiv

Conformal bandits: bringing statistical validity and reward efficiency under weak arm separability

Simone Cuonzo, Nina Deliu

We introduce Conformal Bandits, a novel framework integrating Conformal Prediction (CP) into bandit problems, a classic paradigm for sequential decision-making under uncertainty. Traditional regret-minimisation bandit strategies like Thompson Sampling and Upper Confidence Bound (UCB) typically rely on distributional assumptions or asymptotic guarantees; further, they remain largely focused on regret, neglecting their statistical properties. We address this gap. Through the adoption of CP, we bridge the regret-minimising potential of a decision-making bandit policy with statistical guarantees in the form of finite-sample prediction coverage. We demonstrate the potential of Conformal Bandits through simulation studies and an application to portfolio allocation, a typical scenario where differences in arm rewards are far too small (weak arm separability) for classical policies to be optimal in finite sample. We showcase our framework's practical advantage in terms of regret in this setting, as well as its added value in achieving nominal coverage guarantees where classical UCB policies may fail. Focusing on our application of interest, we further illustrate how integrating hidden Markov models to capture the regime-switching behaviour of financial markets, enhances the exploration-exploitation trade-off, and translates into higher risk-adjusted returns, while preserving coverage guarantees.

arXiv

Amortized Inference of Multi-Modal Posteriors using Likelihood-Weighted Normalizing Flows

Rajneil Baruah

We present a novel technique for amortized posterior estimation using Normalizing Flows trained with likelihood-weighted importance sampling. This approach allows for the efficient inference of theoretical parameters in high-dimensional inverse problems without the need for posterior training samples. We implement the method on multi-modal benchmark tasks in 2D and 3D to check for the efficacy. A critical observation of our study is the impact of the topology of the base distributions on the modelled posteriors. We find that standard unimodal base distributions fail to capture disconnected support, resulting in spurious probability \textit{bridges} between modes. We demonstrate that initializing the flow with a Gaussian Mixture Model that matches the cardinality of the target modes significantly improves reconstruction fidelity, as measured by some distance and divergence metrics. Finally, we apply this method to a curated problem in heavy flavour physics --- the extraction of the Wolfenstein parameters from the CP asymmetry in $B^0\to J/ψ\,K^0$; it is multimodal, non-Gaussian, and asymmetric in its mode weights --- and compare the results against a well-converged Markov Chain Monte Carlo reference using different metrics.

arXiv

Variance-Aware Baselines and Adaptive Learning Rates for Reinforcement Learning with Verifiable Rewards

Zixun Huang, Jiayi Sheng, Zeyu Zheng

Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective paradigm for post-training large language models, yet the design of its baselines and learning-rate schedules remains largely heuristic. This limits our understanding of the statistical properties of policy-gradient estimators and their interaction with optimization dynamics. In this work, we develop a theoretical framework for variance-aware baseline design and adaptive learning-rate selection in RLVR. Under a KL-regularized policy-optimization setting, we establish the unbiasedness of the resulting gradient estimator, derive exact variance expressions including the KL cross-covariance, and obtain an optimization-loss upper bound that enables principled reasoning about learning dynamics. Building on these results, we prove convergence guarantees and derive an adaptive learning-rate schedule governed by the signal-to-noise ratio (SNR) of the policy gradient. We further show that the variance-optimal baseline is a gradient-weighted estimator of the KL-regularized reward, providing a principled alternative to commonly used reward-based baselines. These results lead to two complementary improvements: a variance-optimal baseline and an SNR-adaptive learning-rate rule. Experiments on Qwen3-4B-Base show that each component independently improves policy-optimization performance. The learning-rate rule can also be naturally integrated with existing policy optimization methods to yield further gains, while combining it with the variance-optimal baseline gives the full Optimal Baseline and Learning-Rate Policy Optimization (OBLR-PO) method and achieves the strongest overall performance.

arXiv

Benign Overfitting in Linear Classifiers with a Bias Term

Yuta Kondo

Overparameterized models often generalize well even when they interpolate noisy training data. This is known as benign overfitting. For linear classification, Hashimoto et al. (2025) analyzed the phenomenon under a broad class of mixture distributions, but only for homogeneous classifiers without a bias term. We extend their framework to classifiers with an intercept. Benign overfitting still occurs, but the intercept perturbs the normalized Gram matrix of the noise and creates extra constraints on the covariance. These constraints are strongest with label noise. Their effect depends on the covariance: under isotropic noise they are dominated by the homogeneous conditions, while in anisotropic or noisy regimes they can raise the dimensionality needed for benign generalization. Thus the bias term changes the theory in some covariance regimes and leaves the asymptotic thresholds unchanged in others.

arXiv

Efficiency vs. Alignment: Investigating Safety and Fairness Risks in Parameter-Efficient Fine-Tuning of LLMs

Mina Taraghi, Yann Pequignot, Amin Nikanjam, Mohamed Amine Merzouk, Foutse Khomh

Organizations increasingly adapt Large Language Models (LLMs) from public repositories such as HuggingFace to downstream tasks. Prior work shows that even fine-tuning on benign datasets can weaken safety alignment, raising a practical question: does benign parameter-efficient fine-tuning (PEFT) also affect safety and fairness? We present the first large-scale, systematic study showing that benign PEFT can significantly alter both. We fine-tune four instruction-tuned model families (Meta-Llama-3-8B, Qwen2.5-7B, Mistral-7B, and Gemma-7B) with four widely used PEFT methods: LoRA, IA3, Prompt-Tuning, and P-Tuning. In total, we evaluate 235 conversationally fine-tuned variants across eleven safety hazard categories and nine fairness dimensions. We assess generalization beyond conversational tuning by incorporating a compact extension focused on coding tasks, involving 96 additional fine-tuned models. Results show that benign PEFT can induce detrimental alignment shifts. Adapter-based methods (LoRA, IA3) are generally safer and less disruptive to fairness, whereas prompt-based methods more often reduce safety and worsen fairness accuracy. Base model choice strongly moderates these effects: LLaMA is comparatively stable, Qwen shows modest gains, Gemma exhibits the steepest safety decline, and Mistral is the most variable. The coding-task extension also produces alignment shifts relative to base models, but matched comparisons with the conversational task reveal limited task-level differences. Overall, safety improvements do not reliably transfer to fairness, and no single configuration optimizes every fairness metric. These findings support a practical guideline for safety-critical deployment: benign intent does not guarantee safe behaviour; start from a well-aligned base model, favour adapter-based PEFT, and audit safety and fairness at the category level.

arXiv

PyDPF: A Python Package for Differentiable Particle Filtering

John-Joseph Brady, Benjamin Cox, Yunpeng Li, Víctor Elvira

State-space models (SSMs) are a widely used tool in time series analysis. In the complex systems that arise from real-world data, it is common to employ particle filtering (PF), an efficient Monte Carlo method for estimating the hidden state corresponding to a sequence of observations. Applying particle filtering requires specifying both the parametric form and the parameters of the system, which are often unknown and must be estimated. Gradient-based optimisation techniques cannot be applied directly to standard particle filters, as the filters themselves are not differentiable. However, several recently proposed methods modify the resampling step to make particle filtering differentiable. In this paper, we present an implementation of several such differentiable particle filters (DPFs) with a unified API built on the popular PyTorch framework. Our implementation makes these algorithms easily accessible to a broader research community and facilitates straightforward comparison between them. We validate our framework by reproducing experiments from several existing studies and demonstrate how DPFs can be applied to address several common challenges with state space modelling.

arXiv

NashPG: A Policy Gradient Method with Iteratively Refined Regularization for Finding Nash Equilibria

Eason Yu, Tzu Hao Liu, Clément L Canonne, Yunke Wang, Chang Xu, Nguyen H. Tran, Stefano V. Albrecht

Finding Nash equilibria in two-player zero-sum imperfect-information games remains a central challenge in multi-agent reinforcement learning. Recent multi-round regularization methods offer a promising direction, yet existing approaches either require full enumeration of the game tree or rely on non-policy-gradient inner solvers that underperform in practice, leaving a scalable policy-gradient-based solution open. In this paper, we propose a novel multi-round regularization procedure and show that it guarantees strictly monotonic reduction in Bregman divergence to Nash equilibria and eventual convergence to one in two-player zero-sum extensive-form games. Guided by this framework, we develop a practical algorithm, Nash Policy Gradient (NashPG), which places the regularization directly in the policy optimization objective and is implemented using standard policy gradient methods. Empirically, NashPG achieves comparable or lower exploitability than prior model-free methods on classic benchmark games and scales to large domains such as Battleship and No-Limit Texas Hold'em, where it attains higher average payoff in head-to-head play.

arXiv

A Semiparametric Discrete Hawkes Model with a Collapsed Gaussian-Process Prior

Trinnhallen Brisley, Gordon Ross, Daniel Paulin

Hawkes processes are used in settings where past events increase the likelihood of future events occurring, resulting in a natural clustering structure. Traditional Hawkes process models treat events as occurring in continuous time, but in many applications only the number of events occurring within a sequence of time bins is observed. We propose the Gaussian Process Discrete Hawkes Process (GP-DHP), a semiparametric model for discrete-time self-exciting count data that places Gaussian-process priors on both the baseline and the excitation. Marginalizing the two GP components induces a single latent Gaussian trajectory. A finite-rank factorization of this collapsed prior permits maximum a posteriori (MAP) estimation without forming or factorizing a \(T\times T\) covariance matrix. External covariates can enter the baseline through the same construction. In simulations, GP-DHP recovers diverse excitation shapes and evolving baselines. In applications to weekly disease surveillance (Singapore dengue and German cryptosporidiosis), daily shooting counts (New York City and the Gun Violence Archive), and a daily worldwide terrorism-incident series, it attains the best held-out predictive accuracy on four of the five series and, on the fifth, an accuracy not significantly different from the best.

arXiv

SingLEM: Single-Channel Large EEG Model

Jamiyan Sukhbaatar, Satoshi Imamura, Ibuki Inoue, Shoya Murakami, Kazi Mahmudul Hassan, Seungwoo Han, Ingon Chanpornpakdi, Toshihisa Tanaka

Current deep learning models for electroencephalography (EEG) are often task-specific and depend on large labeled datasets, limiting their adaptability. Although EEG foundation models seek broader applicability, many still rely on predefined multi-channel inputs, electrode-layout assumptions, or model-specific channel handling. To address these limitations, we introduce the Single-Channel Large EEG Model (SingLEM), a self-supervised foundation model whose hybrid convolutional--Transformer encoder maps each channel independently to a reusable representation capturing local and long-range temporal structure. These representations can be used individually or concatenated through late fusion. We assembled 71 public EEG datasets comprising approximately 9,200 subjects and 357,000 single-channel hours. For leakage-controlled evaluation, downstream results were obtained with a model pretrained on 68 datasets after excluding the three source datasets underlying the six tasks. A model pretrained on all 71 datasets is provided for general reuse. Across six motor imagery and cognitive tasks under strict leave-one-subject-out (LOSO) evaluation, the leakage-controlled model with concatenated representations and a support vector machine (SVM) classifier achieved the best overall performance among the compared pretrained and classical feature-based methods. Additional classifier and subject-adapted analyses supported the robustness of its representations. These findings support single-channel self-supervised learning as a montage-flexible foundation for reusable EEG feature extraction and electrode-level spatial analysis. The source code and pretrained models are available at https://github.com/ttlabtuat/SingLEM.

arXiv

CAPMix: Robust KPI Anomaly Detection for AIOps in Noisy and Dynamic Environments

Xudong Mou, Rui Wang, Tiejun Wang, Zexin Wu, Fangda Guo, Jie Sun, Shiru Chen, Penghao Zhang, Tiezi Zhang, Tianyu Wo, Hao Peng, Chunming Hu, Xudong Liu, Renyu Yang

Time-series anomaly detection is crucial in AIOps for maintaining large-scale service reliability. In production, streams of Key Performance Indicators (KPI) are high-dimensional, non-stationary, and affected by noise, deployment changes, and latent anomalies, making real failures hard to distinguish from benign variation. Most existing methods assume either normality (learning from "normal" history) or rely on injected anomalies for training. Yet injected patterns often misalign with real failure modes, skewing decision boundaries -- aka. Anomaly Shift. We propose CAPMix, a controllable anomaly augmentation framework with prior-guided injection for realistic temporal behaviors. CAPMix combines label revision and dual-space mixup to enhance robustness under contaminated and mixed data. CAPMix consistently outperforms state-of-the-art methods on public AIOps and time-series benchmarks. It has been deployed in Kuaishou's large-scale production system, reducing false alarms and improving monitoring reliability. A real-world dataset is also released to enrich the research on robust KPI anomaly detection.

arXiv

From Global to Local: A Scalable Benchmark for Local Posterior Sampling

Rohan Hitchcock, Jesse Hoogland

Degeneracy is an inherent feature of the loss landscape of neural networks, but it is not well understood how stochastic gradient MCMC (SGMCMC) algorithms interact with this degeneracy. In particular, existing global convergence guarantees for common SGMCMC algorithms rely on assumptions which are likely incompatible with degenerate loss landscapes. In this paper, we argue that this gap requires a shift in focus from global to local posterior sampling, and, as a first step, we introduce a novel scalable benchmark for evaluating the local sampling performance of SGMCMC algorithms. We evaluate a number of common algorithms, and find that RMSProp-preconditioned SGLD is most effective at faithfully representing the local geometry of the posterior distribution among the samplers we evaluate. Although we lack theoretical guarantees about global sampler convergence, our empirical results show that we are able to extract non-trivial local information in models with up to O(100M) parameters.

arXiv

PB$^2$: Preference Space Exploration via Population-Based Methods in Preference-Based Reinforcement Learning

Brahim Driss, Alex Davey, Riad Akrour

Preference-based reinforcement learning (PbRL) has emerged as a promising approach for learning behaviors from human feedback without predefined reward functions. However, current PbRL methods face a critical challenge in effectively exploring the preference space, often converging prematurely to suboptimal policies that satisfy only a narrow subset of human preferences. In this work, we identify and address this preference exploration problem through population-based methods. We demonstrate that maintaining a diverse population of agents enables more comprehensive exploration of the preference landscape compared to single-agent approaches. Crucially, this diversity improves reward model learning by generating preference queries with clearly distinguishable behaviors, a key factor in real-world scenarios where humans must easily differentiate between options to provide meaningful feedback. Our experiments reveal that current methods may fail by getting stuck in local optima, requiring excessive feedback, or degrading significantly when human evaluators make errors on similar trajectories, a realistic scenario often overlooked by methods relying on perfect oracle teachers. Our population-based approach demonstrates robust performance when teachers mislabel similar trajectory segments and shows significantly enhanced preference exploration capabilities,particularly in environments with complex reward landscapes.

arXiv

Training Deep Morphological Neural Networks as Universal Approximators

Konstantinos Fotopoulos, Petros Maragos

We investigate deep morphological neural networks (DMNNs), studying how changes in algebraic structure affect the expressivity and trainability of deep architectures. We show that despite the inherent non-linearity of morphological operations, existing deep morphological architectures fail to be universal approximators and exhibit optimization limitations related to sparse and uninformative gradients. To address these issues, we introduce architectures incorporating constrained "linear" activations between morphological layers and averaging max-plus and min-plus neurons. Only O(N) parameters (or learnable parameters) per layer of size N belong to the activations, with the remaining parameters constrained to morphological operations. We prove universal approximation results for the proposed architectures without requiring substantially larger parameter counts than comparable linear networks. Residual connections and weight dropout further improve generalization. Our experiments show that our networks are trainable and compact, despite the imposed architectural restrictions.

arXiv

Reinforcement Learning from Human Feedback

Nathan Lambert

Reinforcement learning from human feedback (RLHF) has become a crucial tool to build the latest machine learning systems at scale. The field grew around the core methods of RLHF into today's broader suite of post-training techniques. In this book, we give a comprehensive introduction to the core methods for post-training models for people with some level of quantitative background, organized around the canonical RLHF recipe. The book starts with what RLHF does and why it was created, with seminal technical milestones in its young history and a primer on reinforcement learning context needed to understand the book. The core of the book details every optimization stage in using RLHF, from starting with instruction tuning to training a reward model and finally all of rejection sampling, reinforcement learning, on-policy distillation, and direct alignment algorithms. The book also discusses broader topics, such as the origins of RLHF -- both in recent literature and in a convergence of disparate fields of science in economics, philosophy, and optimal control. The book concludes with advanced topics -- understudied or emerging research questions in synthetic data, tool-use, character training, and evaluation -- and open questions for the field. The book is released with a variety of companion resources, including a codebase, a library to compare model completions from within post-training stages, and an educational course, to be a one-stop shop for learning all foundational concepts for post-training language models.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.