cs.LG · 2026-07-28 · No. 67
Machine Learning, 2026-07-28.
62 new papers in cs.LG. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
62 entries-
01
Global Convergence of DGM and PINN Algorithms for Solving Nonlinear PDEs
Justin Sirignano, Konstantinos Spiliopoulos, Samuel Cohen
cs.LG · math.NA
The Deep Galerkin Method (DGM) and Physics Informed Neural Networks (PINNs) have become widely-used methods for solving partial differential equations (PDEs) in the rapidly growing field of scientific machine learning. In these methods, a neural network is trained to approximate the PDE solution by using (stochastic) gradient descent to minimize the PDE residual of the neural network. Due to the non-convexity of the PDE residual objective...
-
02
Causal-TS: A Python Library for Causal Discovery in High-Dimensional and Nonstationary Time Series
Mohammad Fesanghary
cs.LG · stat.ME
We describe Causal-TS, an open-source Python library for causal discovery in high-dimensional and nonstationary multivariate time series. Causal-TS provides four specialized algorithms-CDNOTS, CDNOTS+, CEDAR, and GRACE-along with wrappers for GES, Granger, LASSO-VAR, and LGES, all sharing a unified conditional independence (CI) test layer with GPU acceleration via PyTorch. A regime discovery pipeline detects structural breaks via pluggable...
-
03
Explainable Reinforcement Learning via Physics-Aware Policy Distillation
Shaker Al-Tamari, Waled Kadour
cs.LG
In safety-critical sectors such as robotics and automotive engineering, the deployment of Deep Reinforcement Learning (DRL) is often hindered by the black-box nature of deep neural networks. This lack of transparency poses significant challenges for regulatory compliance and human-agent trust. This paper presents an experimental study aimed at making high-performance continuous control DRL systems interpretable. A policy distillation...
-
04
When Can You Correct Distribution Drift in Temporal Graph Generation? A Sharpening--Drift Tension and an Impossibility for Observation-Based Correction
Tianpeng Li, Xuan Guo, Wenjun Wang, Wang Zhang, Pengfei Jiao
cs.LG · cs.SI
Generative models of temporal graphs are trained on one stretch of an evolving network and deployed on the next, and they degrade badly in the gap. We show this degradation is derivable, general, and not fixable from observations. The masked flow-matching loss decomposes exactly, with no independence assumption, into an irreducible entropy plus a divergence whose derivative along the training path is positive precisely for structures rare...
-
05
Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects
Phu Gia Hoang, Anwoy Chatterjee, Tanmoy Chakraborty, Iryna Gurevych, Subhabrata Dutta
cs.LG · cs.AI · cs.CL
The wide-scale use of sparse autoencoders (SAEs) as interpretability tools is limited by inconsistent links between SAE features and model behavior. Features with clear activation descriptions may have weak or unexpected causal effects; steering can vary across prompts or oppose the intended direction; and activation-based feature selection can miss features that produce the desired output change. Prior work has studied feature geometry...
-
06
Attribution and Uncertainty Behavior of Learned Residual Gyro Correction for Gyro-Stellar Estimation
Mariela De Lucas Álvarez, Melvin Laux, Arthur de Freitas Precht, Maurice Martin, Edoardo Caroselli, Frank Kirchner,...
cs.LG
This work investigates uncertainty decomposition and explainability in a deep learning-based framework for gyroscope bias correction. A 1-D Convolutional Neural Network is trained to predict residual angular rate corrections from multi-sensor inputs, including gyroscope and star tracker measurements. The bias corrections are sent to a flight-representative Gyro-Stellar Estimator. The network produces both mean corrections and input-dependent...
-
07
PYPM-GGD: Pitman-Yor Process Mixture with Generalized Gaussian Density using ADAM
Kart-Leong Lim
cs.LG
Large scale Bayesian nonparametrics (BNP) learner such as Stochastic Variational Inference (SVI) can handle datasets with large class number and large training size at fractional cost. Like its predecessor, SVI rely on the assumption of conjugate variational posterior to approximate the true posterior. A more challenging problem is to consider large scale learning on non-conjugate posterior. Recent works in this direction are mostly...
-
08
Evaluating Fuzz Testing for Reinforcement Learning Agents
Zhibin Kang, Hanmo You, Dong Wang, Haiming Zheng, Junjie Chen
cs.LG · cs.SE
Reinforcement Learning (RL) agents are increasingly deployed in safety-critical domains such as robotics, autonomous driving, and drone control, where unexpected behaviors may lead to severe real-world consequences. Fuzz testing has recently emerged as a promising method for exploring the vast state spaces of RL agents and exposing crashes. Although numerous RL fuzzing methods have been proposed, existing studies often differ in evaluation...
-
09
Bit-Accurate FPGA Evaluation of Learned Feature Gating in a Fixed-Point Fourier-Feature Automatic Modulation Classifier
Gawthaman Senthilvelan, Luthira Abeykoon
cs.LG
Learned feature reweighting can improve automatic modulation classification (AMC) in software, but the same operation introduces additional arithmetic and latency when implemented on an FPGA. This work measures that trade-off in a compact fixed-point classifier using 24 sparse DFT-energy features, 8 phase/statistical features, and a 32-to-128-to-11 multilayer perceptron. A second architecture inserts a learned 32-element, 8-bit,...
-
10
BettiSplit: Topology-Guided Privacy-Aware Split Learning Against Feature Inversion and Gradient Leakage
Akarsh K. Nair, Muhammad Arifur Rahman, David Brown, Mufti Mahmud
cs.LG · cs.AI · cs.CR
Split learning enables collaborative model training by partitioning neural networks across clients and servers. However, improper split placement can lead to severe privacy leakage through intermediate representations. In this work, we propose a topology-guided framework for privacy-aware split learning based on the persistent Betti complexity of smashed activations. Through comprehensive layer-wise analysis, we show that privacy risk in...
-
11
LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding
Junsung Hwang
cs.LG · cs.AI
Serving large language models at long context is bottlenecked by the key-value (KV) cache, which is read in full at every decode step. Attention keys are locally low-rank though globally high-rank: shared low-rank bases discard page-specific directions that a page's own compact basis retains. LOCKS gives every page its own spectral summary (resident, about a tenth the cache's size), reconstructs within-page logits, estimates each page's...
-
12
EchoBridge: Long-Tail-Aware ECG-Echocardiography Text Alignment for Echocardiography-Derived Cardiac Findings
Xiaocheng Fang, Jieyi Cai, Guangkun Nie, Haoyu Wang, Jiarui Jin, Yujie Xiao, Bo Liu, Chenyang He, Qinghao Zhao,...
cs.LG · cs.AI
Standardized echocardiography conclusions provide meaningful supervision for learning ECG representations of echocardiography-derived cardiac findings. Global ECG--text alignment may entangle modality-specific factors, while long-tailed finding distributions provide sparse positive supervision for low-prevalence conditions. We propose EchoBridge with Complementary Shared--Private Projection (CSPP) and Adaptive Prototype Boundary Calibration...
-
13
The K-SCAN Clustering Algorithm
Filip Kosiorowski, Grzegorz Sroka
cs.LG · cs.NE
In the Big Data era, the scalability of clustering algorithms constitutes a key challenge. Traditional density-based methods (e.g., DBSCAN) offer robustness to noise and the ability to detect non-linear clusters, yet their quadratic time complexity $O(N^2)$ drastically limits their applicability. Conversely, partitional algorithms (e.g., K-Means), with their linear complexity $O(N)$, impose sphericity on the resulting groups and fail in the...
-
14
From Machine Learning to Large-Scale EO Products: Best Practices for Making Maps
Ghjulia Sialelli, Robin Young, Yuchang Jiang, Cesar Aybar, Linus Scheibenreif, Damien Robert, Clemens Mosig, Adam J....
cs.LG
Recent years have seen a rapid expansion in the production of large-scale geospatial maps derived from Earth observation (EO) data, driven largely by advances in machine learning (ML) and large computing infrastructure. Although the barrier to generating such maps has dropped substantially, established best practices have yet to emerge, and design decisions made early in the pipeline can quietly propagate errors into the final product....
-
15
FlowCTS: On-policy Continuous Trajectory Supervision of Flow Models
Kaiyang Ye, Yuan Ge, Junxiang Zhang, Bei Li, Ziming Zhu, Haishu Zhao, Xiaoqian Liu, Chenglong Wang, Jingbo Zhu,...
cs.LG · cs.CV
While on-policy distillation (OPD) effectively addresses sparse rewards and exposure bias in large language model post-training, its extension to flow models remains underexplored. To this end, we propose Flow Continuous Trajectory Supervision (FlowCTS), which matches subsequent student and reference trajectories initialized from the same student-visited state. Using the integral relation between trajectories and velocity fields, we derive a...
-
16
Stress-Testing EEG Foundation Models for Clinical Decoding: Dataset Identity and Targeted Negative Controls
Marzieh Zare
cs.LG · cs.AI · cs.NE
Pretrained EEG foundation models are increasingly proposed for clinical decoding, but their transfer across populations and robustness to negative controls remain unclear. We benchmark six models (LaBraM, EEGMamba, CBraMod, REVE, BENDR, and BIOT) on five clinical tasks across four datasets using frozen linear probes with leave-one-subject-out, subject-grouped, or explicitly identified recording-level splits. Selected REVE findings are tested...
-
17
Low-Rank Dependence Decomposition via Accelerated Symmetric Non-negative Matrix Factorization
Lavinia Ghita, Dhruv Desai, Jake Goldberg, Roman Yokunda Enzmann
cs.LG · math.NA
Symmetric non-negative matrix factorization (SymNMF) recovers latent group structure from a dependence matrix, but its dense, quadratic-memory objective has confined prior work to moderate sizes. We present a large-scale GPU study of seven algorithm families (over 30 configurations) on absolute Pearson correlation and tail pairwise dependence matrices from Extreme Value Theory, two proxies for empirical risk-factor estimation on large...
-
18
Physics Transformer: Tailoring Transformer for General PDE Prediction
Guoze Sun, Rui Zhang, Jiankai Tang, Mengtao Yan, Runze Mao, Zhi X. Chen, Hao Sun
cs.LG
Transformer architectures have attracted increasing attention for solving partial differential equations (PDEs), owing to their flexibility in handling irregular discretizations and their ability to capture long-range physical dependencies. However, unlike discrete language tokens or fixed-resolution image patches, observed physical fields are finite samples of underlying infinite-dimensional functions. Consequently, effectively applying...
-
19
UNIFUSION: Adapting Autoregressive Language Models into Discrete Diffusion under a Unified Reverse-Rate Objective
Xiaoyi Jiang, Jingyuan Li, Yixuan Jiang, Wei Liu, Yi Zhu, Zuoqiang Shi, Pipi Hu
cs.LG · cs.AI
Existing methods mainly adapt pretrained autoregressive (AR) language models to masked diffusion, whereas we directly adapt them to uniform-noise diffusion, where every token remains editable during sampling. However, adapting AR checkpoints across corruption kernels remains challenging because existing DLMs use different objectives and prediction parameterizations. We establish connections among SEDD, MDLM/GIDD, M2S, and Neural CTMC by...
-
20
What do Reward Models Memorize?
Ivo Verhoeven, Pushkar Mishra, Ekaterina Shutova
cs.LG · cs.CL
This paper studies what discriminatively trained reward models (RMs) memorize by measuring counterfactual memorization on two human preference datasets. We show that RMs 1) misallocate memorization to easy, high margin preference pairs, 2) memorize dataset-specific shortcuts (e.g., model identity, user sampling strategy), and 3) overgeneralize simple heuristic correlates of human preference (e.g., length, compliance) when confronted with...
-
21
DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference
Dengke Han
cs.LG · cs.AI
Large Mixture-of-Experts (MoE) language models are attractive for end-device deployment because only a small subset of experts is active per token, but their routed expert weights often exceed accelerator memory. We target latency-critical single-user settings where routed experts are staged on demand from CPU memory to a GPU or from Flash to a mobile NPU. In this setting, self-speculative decoding faces a new bottleneck: increasing the draft...
-
22
Context Is King: How In-Context Specification Shapes the Geometry of Concepts
Elad David, Max Fomin
cs.LG
Large language models place structured concepts on geometrically faithful manifolds: weekdays lie on a circle, months on another, usually taken to be a fixed world-model the network stores and looks up. We show that context is king: the structure a model actually uses is set by the in-context specification. A declarative rule fixes not only which relations the geometry encodes but its topology type: the same tokens form a cycle or a branching...
-
23
K-Survival Means
Abdallah Alabdallah
cs.LG
In this work, we propose K-SurvMeans, a novel extension of K-Means for clustering survival data. The method explicitly uses the survival outcome in the clustering process to optimize cluster centers, thereby maximizing pairwise survival differences between clusters. The objective function encourages the clusters to be well-separated from the survival perspective. Since the resulting optimization problem is non-differentiable, we employ the...
-
24
MXAttention: Data-Free Optimal Scaling and Pre-Normalization Quantization for MXFP4 Attention
Jianlin Yu, Jing Lin, Linghui Kong, Aiyue Chen, Weiyi Sun, Chenyu Zeng, Wangli Lan, Jinxi Li, Zhuo Zheng, Ziyang...
cs.LG · cs.AI · cs.CV
The quadratic cost of attention is a major bottleneck in diffusion-based video generation models. MXFP4 attention provides a promising path toward efficient inference, but direct MXFP4 quantization often degrades generation quality due to two numerical issues: the clipping-underflow trade-off from power-of-two scaling and the row-wise normalization error introduced in the softmax loop. We propose MXAttention, a data-free post-training...
-
25
MobiWave: Dispatch-Oriented Graph Wavelets and Drift-Guided Selective Optimization for Autonomous Fleet Rebalancing
Xiao Han, Pinbo Wang, Yuanshao Zhu, Guojiang Shen, Xiangjie Kong
cs.LG
Autonomous fleets enable mobility platforms to coordinate idle vehicles directly, making fleet-wide rebalancing possible. However, two obstacles limit reliable deployment: overlapping regional and local traffic patterns can hide roads that remain useful for dispatch, and mobility drift can make a trained policy unreliable. Existing spatial aggregation mixes these patterns, while updating all parameters from limited recent data is costly and...
-
26
Perturbative-NeuSA: A Structured Spectral Framework for Time-Dependent PDEs
Xianli Zhu, Jia Yin
cs.LG · math.NA
Neural spectral PDE solvers often learn an entire unresolved vector field even when an inexpensive approximate model can already capture most of the trajectory. Here we introduce Perturbative-NeuSA, a residual formulation that decomposes the target solution into a low-fidelity background and a high-resolution perturbation, so that only the unresolved dynamics is learned. Starting from the exact perturbation equation, the method combines a...
-
27
Beyond Aggregate Risk: Role-Stratified Conformal Risk Control for LLM Tool Calls
Md Ashikur Rahman, Md Arifur Rahman, Niamul Hassan Samin, Khandaker Rifah Tasnia, Sifat Rahman Ahona, Juena Ahmed Noshin
cs.LG · cs.AI · cs.CL
Language-model agents act through structured tool calls whose arguments carry different risks. Untrusted content may safely influence an email body but should not determine a recipient, account, command, or credential. Existing statistical methods typically control risk over the entire action, allowing failures in rare, high-risk fields to be obscured by benign arguments. We introduce role-stratified per-field conformal risk control, a...
-
28
Unsupervised Graph Representation Learning with Complementary View Alignment
Zengyi Wo, Shiyu Zhang, Qiyao Peng, Tianpeng Li, Xuan Guo
cs.LG
Unsupervised graph representation learning aims to derive meaningful node embeddings by capturing both structural and attribute information without relying on labeled data. Existing methods, such as GAEs, have demonstrated effectiveness but typically rely on message-passing mechanisms that assume homophily, leading to performance degradation on heterophilous graphs, where connected nodes exhibit dissimilar features. This homophily bias...
-
29
DynaCalKV: Key-Value Cache Compression via Head Grouping and Adaptive Rank Allocation
Tan T. Nguyen, Quan V. Dang
cs.LG
As the inference phase of Large Language Models (LLMs) requires handling long context windows, the Key-Value (KV) cache initially appears to address this challenge but eventually becomes a significant bottleneck as the context window continues to grow. Low-rank compression has recently been studied as an effective approach to reduce KV cache memory while maintaining model performance. However, only a few existing methods treat the Key and...
-
30
MEGA-CL: A Molecular Foundation Model for Generalizable ADMET Prediction through Graph External Attention and Contrastive Learning
Tinghui Jin, Kedu Jin, Ying Li, Guanghui Ren, Jingzhi Xue, Shiyu Zhou, Xiaoli Dai, Li-bin Wei, Xijing Chen, Di Zhao,...
cs.LG
Predicting the absorption, distribution, metabolism, excretion and toxicity (ADMET) properties of small molecules remains a major challenge in drug discovery. Here, we present MEGA-CL, a foundation graph neural network framework for universal molecular ADMET prediction. MEGA-CL integrates self-supervised contrastive learning with a multi-head external attention mechanism and an enhanced message-passing architecture, enabling simultaneous...
-
31
Physics-Guided Generative AI for Property-Targeted 3D Porous Media Design
Peng Wang
cs.LG · cs.AI
Inverse design of three-dimensional porous media is central to applications in filtration, catalysis, energy storage, fuel cells, thermal management, and biomedical scaffolds, but remains challenging because many distinct pore geometries can share similar porosity or permeability while small structural changes can strongly affect transport behaviour. This paper proposes a physics-guided generative AI framework for property-targeted porous...
-
32
KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems
Shuo Wang, Fang Xi, Wenyuan Huang, Qing Wang, Junming Su
cs.LG
Modern LLM systems increasingly rely on knowledge-selection processes that produce high-value structured priors, such as ranked evidence, graph topology, multimodal alignment, and confidence signals. Yet LLM serving remains fundamentally oblivious to this rich structure: once such signals are serialized into a prompt, the backend observes only a flat token sequence, forcing dense and uniform consumption of the full key-value (KV) state during...
-
33
ML-based Predictive Models for Power Consumption in Virtualised O-RANs
Rishu Raj, Genevieve Akude, Urooj Tariq, Daniel Kilper
cs.LG · cs.AI
As communication networks adopt virtualized and disaggregated architectures, achieving energy efficiency has become increasingly important for both economic and environmental reasons. Traditional methods for power modeling are inadequate in these dynamic software-defined environments due to their inability to model complex and nonlinear factors affecting energy use. We investigate the use of feature extraction and regressor-based machine...
-
34
Why does Greedy Search produce Optimal Clustering Outcomes? A Fixed-Core Assignment Theory
Kai Ming Ting, Kaifeng Zhang, Sanjay Chawla
cs.LG
Many existing clustering methods are designed based on a set-oriented definition---a cluster is a set of similar points---relying a point-to-point similarity function to find similar points. This works well for compact clusters, but clustering performance can deteriorate badly when cluster shapes are irregular, and densities or sizes vary between clusters. Recent `Cluster-as-Distribution' (CaD) clustering has been shown to discover these...
-
35
Every Client Is an Environment: Federated De-confounding for Spatio-Temporal Forecasting
Qingxiang Liu, Anqi Liang, Heng Wang, Yuxuan Liang
cs.LG · cs.AI
Federated learning has emerged as a promising paradigm for spatio-temporal forecasting (STF), enabling collaborative model training without sharing raw observations. Existing federated STF methods primarily regard cross-client heterogeneity as an optimization challenge and mitigate it through personalized approaches. However, such heterogeneity fundamentally stems from diverse \emph{environmental conditions}, and these methods capture...
-
36
Monitoring Post-Disaster Urban Recovery Using High-Resolution SAR Time Series and Unsupervised Learning: Evidence from the 2023 Türkiye-Syria Earthquake
Luigi Russo, Deodato Tapete, Silvia Liberata Ullo, Paolo Gamba
cs.LG · cs.AI
Monitoring post-disaster recovery is essential for understanding how urban systems rebuild and progressively return to functionality. However, tracking reconstruction remains difficult because reliable ground-truth information is often scarce and recovery processes evolve over time. This paper proposes an unsupervised framework for recovery monitoring based on multi-temporal synthetic aperture radar (SAR) observations and deep-learning...
-
37
Forecasting the Emergence and Evolution of Crash Hotspots: A Unified Deep Learning Framework for Proactive Traffic Safety
Jingwen Zhu, Keshu Wu, Pei Li, Steven T. Parker, Bin Ran, David A. Noyce
cs.LG · cs.ET
Road crashes remain among the gravest threats to public safety, and preventing them is a defining task of transportation systems worldwide. Much of that harm concentrates at hotspots, yet a hotspot is less a place than an episode; it emerges quietly at an intersection or along an arterial, intensifies for weeks, then subsides, only to reappear elsewhere. Enforcement guided by maps of past crashes inevitably trails this cycle, patrolling...
-
38
Calibrated Tree-Neural Fusion for Fine-Grained Vegetation Community Classification
Dristi Datta, Md Khalid Hasan Sakib, Manoranjan Paul
cs.LG
Accurate vegetation-community classification is essential for ecological monitoring, habitat assessment, and evidence-based environmental management in heterogeneous landscapes. Existing studies often rely on standalone tree ensembles or generic neural networks, although fine-grained ecological classes frequently exhibit overlapping spectral, topographic, and structural characteristics. Many frameworks also provide limited protection against...
-
39
An Empirical Study of Feature Selection Granularity
Muhammad Rajabinasab, Arthur Zimek
cs.LG
Feature selection aims to identify the most informative and relevant features for a given dataset, either in terms of capturing the underlying data structure and distribution better, or with respect to the performance on a downstream task. Existing research in this area has largely focused on developing novel algorithms (in both supervised and unsupervised settings), proposing new evaluation metrics and frameworks, or benchmarking the...
-
40
MAPLE: Efficient and Diverse Multi-Alpha Generation for Portfolio Construction
Yu-Chen Den, Kuan-Yu Chen, Kendro Vincent, Tien-Hao Chang
cs.LG · cs.CE
Classical alpha mining achieves strong risk-adjusted returns by combining many low-correlated predictive signals, yet deep learning stock-ranking methods typically produce a single alpha per stock, rely on increasingly complex architectures with diminishing gains, and obtain diversity only through separate models or implicit routing, without explicitly controlling inter-alpha correlation. We introduce MAPLE (Multi-Alpha Position-aware...
-
41
Learning Reusable Hybrid Motion Priors for Humanoid Locomotion from Motion Imitation
Valerio Belli, Valerio Modugno, Enrico Mingo Hoffman, Fabio Amadio
cs.LG · cs.RO
Reinforcement learning can produce robust humanoid controllers, but each new task is typically trained as a separate policy with its own reward design and training process. Motion imitation provides an alternative source of motor competence by training policies to track retargeted human motions, yet the resulting controllers remain reference trackers and are not directly usable as task policies. We propose a three-stage pipeline that turns...
-
42
ACRL: Adaptive Control of Training-Inference Discrepancy for Stable Reinforcement Learning
Wenwu Fan, Qihong Lin, Zhijie Xia, Zhuo Zheng, Sihao Wang, Qiang Chen, Liangsheng Zhu
cs.LG · cs.AI · cs.CL
Reinforcement Learning (RL) training for Large Language Models (LLMs) often suffers from instability due to the discrepancy between training and inference. This training-inference discrepancy stems from two primary factors: an architectural separation between training and inference engines, and the use of low-precision quantization in inference versus higher-precision computation in training. To address training instability issues caused by...
-
43
Constrained Reinforcement Learning Using Successor Representations
Michael Girstl, Alexander Mattick, Christopher Mutschler
cs.LG
Real-world Reinforcement Learning depends on the ability to formulate safety constraints into a policy. A common way to model such constraints is to introduce an additional cost signal in the Markov Decision Process, which notifies the agent of unwanted behavior independently of the reward signal. Unfortunately, current methods are hard to adapt to changes in the cost function introduced by, e.g., domain shift or obstacles moving over time....
-
44
Capacity-Aware Deep Learning for Generalizable Traffic Volume Estimation Across Links and Cities
Léo Hein, Giovanni De Nunzio, Aurélie Pirayre, Laurent Najman
cs.LG · cs.AI
Network-wide traffic volume estimation typically relies on propagating measurements from fixed sensors, making performance highly dependent on sensor density and limiting deployment in sparsely instrumented networks. We propose a link-level learning framework that estimates hourly traffic volumes from widely available territorial data only, including probe speed profiles, road and topological descriptors, along with weather observations. A...
-
45
When Should Active RAG Retrieve? A Budget-Aware Evaluation of Utility, Calibration, and Cost
Pin Qian, Su Wang, Chong Peng, Junxian You, Lifei Liu, Haoran Yu, Yihang Chen, Xiaochong Jiang
cs.LG
Active RAG systems decide when to retrieve external knowledge during generation, making them a budget-sensitive case of agentic RAG and self-adaptive retrieval. Yet evaluations often leave the operating point underspecified: two systems may both claim a 50% evidence-usage budget while realizing different held-out usage rates, so higher accuracy can reflect a looser budget rather than a better retrieval policy. We study budget-aware evaluation...
-
46
Adaptive Data Admission and Retention for Streaming Federated Learning
Zhuoyi Zhao, Ben Liang
cs.LG · cs.AI · cs.NI
We study streaming federated learning with limited client memory, where newly generated training data incur time-varying sampling costs and must be selectively admitted and retained over time. We consider a joint server-side admission and client-side memory-management framework with the objective of minimizing the cumulative excess population risk under a sampling-cost budget and buffer constraints. We first derive a learning-error bound that...
-
47
Understanding Machine Unlearning Through the Lens of Mode Connectivity
Jiali Cheng, Hadi Amiri
cs.LG · cs.AI · cs.CL
Machine Unlearning aims to remove undesired information from trained models without full retraining from scratch. Despite recent progress, the loss landscape and optimization geometry of unlearning are poorly understood. In this paper, we study machine unlearning through the lens of mode connectivity--the phenomenon that independently trained models can often be connected by smooth low-loss paths in parameter space. We introduce {\em mode...
-
48
Joint Flow Matching for Generator-Consistent Classification
Hayden McAlister, Lech Szymanski
cs.LG
We introduce Joint Flow Matching (JFM), a training framework for continuous normalising flows over multiple variables. Standard flow matching transports variables from noise to data simultaneously, offering no natural mechanism for forward and reverse conditional inference from a shared joint model. JFM resolves this by assigning opposite roles to each variable at the temporal endpoints. We prove that JFM produces a consistent joint...
-
49
Variational Boosting for Physics-Informed Neural Networks
Pavlos Protopapas, Kaylee Vo
cs.LG
Physics-Informed Neural Networks (PINNs) solve differential equations by minimizing the residual of a nonlinear operator over a neural parameterization of the solution. However, monolithic PINNs often suffer from ill-conditioning, spectral bias, and optimization instability. We introduce a variational boosting framework in which solutions are constructed additively in function space. Each stage trains a weak learner whose converged correction...
-
50
DECAF: De-Clustering for Adaptive Representational Unlearning
Anjie Le, Can Peng, Hongcheng Guo, J. Alison Noble
cs.LG
Machine unlearning, which aims to remove the influence of specific training data from a trained model, is a key requirement for privacy, accountability, and adaptive deployment. We argue that many unlearning methods are vulnerable to a simple clustering attack, which can recover class structure in an unsupervised manner, limiting their suitability for continual deployment where removal requests must be handled reliably on demand. To address...
-
51
Greedy dynamical meta-learning
Aria Yom
cs.LG
Gradient descent scales well to large models, but becomes unstable over long time horizons. Gradient-free optimizers can scale to arbitrary timespans, but are hobbled by high dimensions. Since learning occurs in large models over long timescales, neither of these approaches is likely to produce traits which can accelerate the learning process. Instead, we propose a meta-learning algorithm in which the agent learns to modify its own weights...
-
52
WorldDiT: A Unified Diffusion Architecture for World and Action Modeling
Sen Wang, R. Gnana Praveen, Bidhan Roy, Marcos Villagra
cs.LG · cs.RO
Many recent robot policies pursue stronger control by using large pretrained vision-language models (VLMs) as the action backbone. We introduce WorldDiT, a unified diffusion transformer architecture that couples action generation with visual world modeling and achieves strong performance without a large pretrained VLM action backbone. During training, a single diffusion transformer generates continuous action chunks and predicts normalized...
-
53
ADVERSARIAL: And-Inverter Graph-Assisted Hardware Trojan Detection At Scale
Yaroslav Popryho, Debjit Pal, Inna Partin-Vaisband
cs.LG · cs.AR · cs.CR
Modern System-on-Chip (SoCs) often contain hundreds of millions to tens of billions of gates, making existing Hardware Trojan (HT) detection methods impractical due to their immense scale. The proposed approach incorporates symbolically enabled learning by modeling flattened gate-level netlists as Boolean networks represented as And-Inverter Graphs (AIGs), where all internal nodes are 2-input AND gates and inversions reside on the edges. Each...
-
54
Physics-Informed Neural Networks for Predicting Nitrous Oxide Flux
Freddy Yu, Jashanjeet Kaur Dhaliwal, Subhadeep Chakraborty
cs.LG · cs.AI · stat.ML
Nitrous oxide (N$_2$O) is the dominant ozone-depleting substance emitted in the 21st century, and the third largest contributor to anthropogenic greenhouse gases due to its high potency and long atmospheric lifetime, with more than 70% of N$_2$O emissions occurring as a result of agricultural processes. Current approaches to predicting N$_2$O flux emissions include process-based models such as DayCent and Cycles, as well as classical AI...
-
55
Flash-CNNCap: Capacitance Extraction via Image Mapping
Hector R. Rodriguez, Jiechen Huang, Wenjian Yu
cs.LG
We present Flash-CNNCap, a CNN-based capacitance extractor that reformulates full-matrix capacitance prediction as image-to-image regression over spatial contribution maps. Prior scalar CNN-based extractors require $O(n^2)$ forward passes to recover all pairwise capacitances in a window with $n$ conductors. Flash-CNNCap replaces the scalar target with dense contribution maps: a total-capacitance model and a master-conditioned coupling model...
-
56
A Coulomb Particle Model for Learning Kernel Attention in Transformers
Masoud Badiei Khuzani, Sharath Honnaiah, Atiq Islam, Alex Cozzi, Abraham Bagherjeiran
cs.LG · cs.AI
Randomized features provide a scalable approximation to kernel machines, but their performance depends strongly on the choice of feature distribution. We propose a particle-based method that learns this distribution by optimizing kernel-target alignment while regularizing particles with a Riesz/Coulomb repulsive potential. The resulting Hamiltonian yields diverse, task-adaptive random features and admits a mean-field description through a...
-
57
XMix: Combating Extremely Noisy Labels via Local Smoothness in Self-Supervised Feature Space
Chengqi Li, Yangdi Lu, Zhihao Shi, Wenbo He, Chamseddine Talhi, Nadjia Kara
cs.LG
Supervised deep learning models rely on large, accurately labeled datasets, yet noisy annotations are often unavoidable and can severely degrade performance under high noise levels. Recent state-of-the-art methods tackle this by using sample selection strategies that exploit the memorization effect to filter out clean data for semi-supervised learning. However, these methods struggle with extreme noise, class imbalance, and require careful...
-
58
Controllable Diversity in Normalization-Based Implicit Ensembles via Softmax-Temperature Modulation
Mihai Suteu, Ovidiu Serban
cs.LG · cs.CV
Deep ensembles provide the most reliable uncertainty estimates in deep learning, but their cost grows linearly with the number of members. Implicit ensembles lower this cost by sharing a single backbone across members. Member diversity is a primary determinant of ensemble quality, yet no implicit ensemble can shape it during training; existing methods fix it at initialisation or build it into the architecture. We introduce $σ$N-Ens, a...
-
59
Covariance Last-Layer Ensembles: Function-Space Diversity for Efficient Uncertainty Quantification
H. Martin Gillis, Isaac Xu, Gabriel Spadon, Thomas Trappenberg
cs.LG
A Last-Layer Ensemble (LLE), $K$ linear units on one shared frozen feature map, is an efficient single-pass approach to the disagreement-based epistemic uncertainty for out-of-distribution (OOD) detection. Its weakness is that members share the backbone gradient and can converge toward the same function, collapsing the inter-member diversity the signal depends on. Whether last-layer diversity can be restored, and what mitigates the collapse,...
-
60
Latent-LoRA: Compact Latent-Space Adapters with Gradient-Free Routing for Continual Learning
Reza Rahimi Azghan, Gautham Krishna Gudur, Giulia Pedrielli, Pavan Turaga, Hassan Ghasemzadeh
cs.LG · cs.CL
Large language models generalize well to individual tasks but lack an inherent mechanism for learning them sequentially, leading to catastrophic forgetting. To mitigate this, LoRA-based continual learning methods allocate a separate low-rank adapter per task, yet existing approaches either require task identity at inference or sum all adapters indiscriminately, letting irrelevant branches distort the output. Recent gating-based solutions...
-
61
DriveDNA: A Large-Scale Multimodal Naturalistic Driving Dataset and Benchmark for Driving Style Identification
Yuhang Wang, Lingyao Li, Hao Zhou
cs.LG
Driving style captures stable, driver-specific patterns in how a vehicle is driven. In naturalistic data, however, this signal is hard to isolate because drivers are observed in different vehicles, on different roads, and under different conditions, so models may mistake vehicle- or situation-specific regularities for driver-specific style. We introduce DriveDNA, a large-scale naturalistic dataset and benchmark for personalized driving-style...
-
62
SCTA: An Agentic Framework for Stable and Interpretable Target Gene Discovery from Single-Cell RNA Sequencing
Shuyu Chen, Chen Zhu, Ye Zhang, Yang Li, Qiqi Xie, Haohan Wang
cs.LG · q-bio.GN
Identifying therapeutic target genes from single-cell RNA sequencing (scRNA-seq) data remains a fundamental challenge in translational biology. Unlike bulk assays, scRNA-seq captures heterogeneous cellular states and rare subpopulations, but this same heterogeneity makes target discovery highly sensitive to analytical choices throughout the pipeline, including preprocessing, cell population selection, differential expression analysis, and...
This edition is part of The Daily Abstract — cs.LG archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.