cs.LG · 2026-08-11 · No. 81
Machine Learning, 2026-08-11.
57 new papers in cs.LG. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
57 entries-
01
Fairness in Link Prediction Beyond Demographic Parity: A Reproducibility Study
Valentijn Oldenburg, Floris de Kam, Stef de Wildt, Jarno Nilson Balk
cs.LG · cs.SI
In fair ranked link prediction, demographic parity ($Δ_\mathrm{DP}$) is a common fairness metric. Yet, Mattos et al. (2025) argue that it fails to detect exposure bias because it ignores where links appear in the ranking. In this study, we reproduce this claim by showing that $Δ_\mathrm{DP}$ can indicate aggregate parity even when some subgroup-pair links are systematically ranked lower than others. The proposed rank-aware Normalized...
-
02
Real-Time Climate Risk Assessment for Supply Chain Resilience: A Data-Driven Nowcasting Framework for Colombian Agriculture
Hernan J. Silva-Sosa
cs.LG
This paper presents a methodological framework for real-time climate risk assessment using data-driven nowcasting techniques to enhance supply chain resilience in Colombian agricultural contexts. Climate variability in Colombia, characterized by irregular rainfall, temperature fluctuations, and recurrent extreme events, has a direct impact on agricultural production and logistics, particularly for time sensitive crops. The proposed approach...
-
03
Deep Multimodal Wearable Sensor Fusion for Detection of Body-Focused Repetitive Behaviors
Samaneh Rezaeimanesh, Mohsen Behradfar, Mohammad Fili, Guiping Hu
cs.LG
Body-focused repetitive behaviors, such as hair pulling and skin picking, are compulsive motor actions commonly associated with obsessive-compulsive and anxiety disorders. Their early, objective detection remains difficult because the movements are subtle and overlap with ordinary, non-pathological gestures. We developed and evaluated a multimodal deep learning framework to detect and classify these behaviors from wrist-worn sensor data. The...
-
04
Multi-Agent AI Safety as an Institutional Design Problem
Abdullah X
cs.LG · cs.AI · cs.MA
AI agents increasingly work inside systems that govern how they delegate tasks, move information, execute actions, and use shared resources. Recent work already shows that deployment rules can change collective behavior. Here we ask which parts of an AI institution produce safety and how they do it. This is the first paper from POLIS, an ongoing research programme studying algorithmic institutions for multi-agent systems. We report a frozen...
-
05
Distill Skills into Weights, Not Prompts: Abstract Skills as Privileged Signals for On-Policy Self-Distillation
Yubo Jiang, Fengying Xie, Zhiguo Jiang, Haopeng Zhang
cs.LG · cs.AI
Reinforcement learning with verifiable rewards yields no group-relative signal when rollout groups are uniformly correct or uniformly wrong, which account for 63.0-68.0% of groups in our experiments. We propose SKALD (Skill-Anchored Latent Distillation), an on-policy self-distillation framework that uses two context views of the same Qwen3-Base model: a question-only student and a teacher conditioned on an abstract, explicit-answer-filtered...
-
06
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA
Mind Lab, :, Vin Bo, Asher Cai, Jingwei Cao, Song Cao, Vic Cao, Amelia Chen, Andrew Chen, Kaijie Chen, Cleon Cheng,...
cs.LG · cs.CL
Macaron-V1 is an open agent-model family for experiential intelligence: learning from experience in real environments and continuing to learn after deployment. It is organized around two system goals. Adaptation is pursued through recursive improvement of versioned model-harness pairs, where experience from one configuration is evaluated under an external contract and used to construct its successor. Collaboration is pursued via the...
-
07
Parameter Exploration for RLVR via Variational Learning
Vatsal Venkatkrishna, Nico Daheim, Iryna Gurevych
cs.LG · cs.AI · cs.CL
Exploration has been a focus of reinforcement learning research for a long time. Recently, there has been growing evidence that it is also an important ingredient in LLM reinforcement learning recipes that can significantly impact downstream performance. Many existing methods control exploration in the action-space, for example, using temperature scaling. However, these methods cannot reorder tokens but only influence the variance in the...
-
08
ReliableNet: A Chance-Constrained Approach to Trustworthy Classification in Deep Learning
Ange-Clément Akazan, Ineza Remy Mugenga, Abebe Geletu, Jean Medard Ngnotchouye, Issa Karambal
cs.LG
A prediction that is both confident and wrong is a critical reliability failure because it can bypass abstention and human review precisely when the model is mistaken. Empirical risk minimization (ERM) controls average loss but not this failure directly, while calibration, uncertainty estimation, conformal risk control, and selective prediction methods target related reliability properties rather than bounding the joint failure event during...
-
09
MoNo: Multiscale Optimal Transport Neural Operator for Solving PDEs on General Geometries
Zijiang Yang, Xiaomeng Wu, Dongmei Fu
cs.LG · cs.AI
Transformer-based neural operators have achieved substantial progress in solving Partial Differential Equations (PDEs) by projecting spatial observations into compact latent tokens and learning physical interactions in latent spaces. However, we reveal that existing learnable projection mechanisms cannot ensure stable and balanced assignments from observation points to latent tokens, causing some latent tokens to be over-assigned while others...
-
10
SR-OPSD: Self-Referenced On-Policy Self-Distillation
Zhuo Sun, Entong Li, Yanlong Zhao, Xiaoyuan Cheng, Wenxuan Yuan, Kaiyu Li, Che Liu, Huihang Liu, Harrison Bo Hua Zhu, Li Zeng
cs.LG · cs.AI · stat.ML
On-policy self-distillation (OPSD) converts feedback into dense token-level supervision on trajectories generated by the policy to be optimized, providing a useful complement to reinforcement learning with sparse outcome rewards. However, the self-teacher policy used in OPSD is typically a stop-gradient or exponential-moving-average copy of the policy conditioned on additional context information, and thus co-evolves with both the student...
-
11
Rethinking Factor Sharing in Federated LoRA: A Rank-Aware Adaptive Approach
Xinyi Xu, Bingnan Xiao, Shuang Qin, Gang Feng, Tony Q. S. Quek
cs.LG · cs.AI · cs.DC
Low-rank adaptation (LoRA) represents large language model (LLM) updates with two compact matrix factors, i.e., $A$ and $B$, providing an efficient way to fine-tune large models in federated learning paradigm. Inspired by the asymmetric roles of the LoRA factors, we study whether $A$ should be shared across clients while $B$ remains client-specific (Share-A/Local-B), or whether $B$ should instead be shared while $A$ remains client-specific...
-
12
PET/CT Radiogenomic Mutation Prediction in Non-Small Cell Lung Cancer Using Multi-Label Learning
Mona Furukawa, Sai Hyne, Daniel R. McGowan, Bartłomiej W. Papież
cs.LG
Lung cancer remains one of the leading causes of cancer- related mortality worldwide. Although targeted therapies have improved outcomes for patients with non-small cell lung cancer (NSCLC), they rely on mutation profiling through tissue biopsy, an invasive procedure with several limitations. This study investigates PET/CT-based radio- genomic prediction of epidermal growth factor receptor (EGFR), tumour protein 53 (TP53), and Kirsten rat...
-
13
Evaluating Generative Time-Series Models on Data with Point Masses
Jian Xu
cs.LG · cs.AI
Many of the series that generative time-series models are benchmarked on place a large probability mass on a single value --- it does not rain, no ride is requested, no part is ordered. We report what happens when such data is evaluated carefully. First, the standard rolling-origin protocol can score a model on a window whose atom structure bears no resemblance to the dataset: on one benchmark the dataset is $42\%$ zeros and the evaluation...
-
14
Recurrent Neural Networks Beyond Time: Learning from Multiple Ordered Projections
Vagan Terziyan, Artur Terziian, Oleksandra Vitko
cs.LG
Recurrent neural networks (RNNs) are widely used for sequence learning, yet their application is commonly associated with temporal data, although recurrent computation fundamentally operates on ordered sequences rather than on time itself. Building on this observation, we introduce the Ordered Structural Dependency Hypothesis (OSDH), which proposes that multiple admissible orderings of the same observations may reveal complementary structural...
-
15
Confusion-Geometry Rebalancing for Long-Tailed Adversarial Training
Mengnan Zhao, Geyong Min, Lihe Zhang, Tianhang Zheng, Jie Cui
cs.LG · cs.AI
Adversarial training under long tailed distributions suffers from a dual imbalance: the class imbalance skews the training objective toward head classes, and the adversarial inner maximization may further amplify this bias. Existing methods mitigate this issue by correcting class priors or adapting class wise robust supervision, yet they treat each class in isolation and fail to identify which boundaries drive long tailed collapse. We propose...
-
16
FedOrbit: Adaptive Personalized Federated Learning for Non-IID LEO Satellite Constellations
Satwat Bashir, Tasos Dagiuklas, Muddesar Iqbal
cs.LG
Federated learning (FL) in Low Earth Orbit (LEO) satellite constellations is affected by non-IID data and irregular ground-station visibility, both driven by orbital geometry. Global aggregation performs poorly when orbit-level class distributions are disjoint, while strong personalisation can be excessive when these distributions overlap. We present FedOrbit, which combines continuous orbit-level training over inter-satellite links,...
-
17
Deep Learning Imputation of Missing Radius of Maximum Winds (Rmax) Values in Tropical Cyclone Best-Track Data
Swastik Agrawal, Nishkal Hundia, Ziyue Liu, Michelle Bensi
cs.LG · physics.ao-ph
Probabilistic coastal hazard assessments require accurate characterization of tropical cyclone (TC) parameters, yet datasets often contain missing records for the radius of maximum winds (Rmax), a key variable in Joint Probability Method analyses. This study evaluates data-driven approaches for Rmax imputation, including one-dimensional Convolutional Neural Networks (1DCNNs), Long Short-Term Memory (LSTM) networks, and conventional machine...
-
18
Satellite Trajectory Optimization via Proximal Policy Optimization for Space Debris Avoidance
Logan Luna, Juan Ortiz Couder, Raul Alejandro Vargas-Acosta
cs.LG · cs.RO
Collision avoidance systems are commonly used to avoid fragmentation events occurring in Low-Earth Orbit (LEO) and Geosynchronous Equatorial Orbit (GEO). However, these events have been growing in frequency as orbital congestion worsens with the launch of megaconstellations. Consequently, conjunction alerts and collision risks are becoming increasingly common. Current practices, which are commonly manual or rule-based, have difficulty scaling...
-
19
Bayesian Symbolic Regression with Entropic Reinforcement Learning
Oussama Boussif, Mohammed Mahfoud, Younesse Kaddar, Moksh Jain, Sida Li, Damiano Fornasiere, Xiaoyin Chen, Yoshua...
cs.LG
Symbolic regression is the problem of finding an algebraic expression describing a stochastic dependence of a target variable on a set of inputs. Unlike forms of regression that fit parameters assuming a fixed model structure, symbolic regression is a search problem over the space of expressions, represented, for example, as abstract syntax trees using a library of operators. Symbolic regression is typically used in settings with limited,...
-
20
LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN
Killian Cressant, Pedro B. Velloso
cs.LG · cs.AI
Graph Neural Networks (GNNs) suffer from two fundamental limitations: over-smoothing, where node representations become indistinguishable with depth, and over-squashing, where long-range information is compressed through limited message-passing channels. Existing metrics such as Dirichlet energy provide global characterizations of over-smoothing but lack the resolution to analyze node-level behavior and guide architectural improvements. In...
-
21
Hyperbolic Multimodal Continual Learning
Jiahong Liu, Ming Shen, Xiaohao Liu, Rex Ying, Menglin Yang, Tat-Seng Chua, Irwin King
cs.LG
Hyperbolic geometry has recently emerged as a powerful representation space for multimodal learning, as it naturally captures hierarchical semantic structure across modalities. Despite this progress, how such representations behave under continual learning poses fundamentally different challenges that remain underexplored. This work provides a geometric perspective on this problem and establishes a theoretical foundation for representation...
-
22
Training-Free Universal Approximation by Prompting Random Transformers
Alexander Hsu, Rongjie Lai
cs.LG · math.NA · math.ST
How expressive is prompting a transformer? Answering this question is important for separating the roles of prompting, architecture, and pretraining in transformer models, and for determining whether task-specific behavior must be stored in model weights or can instead be induced at inference time through the prompt. We show, in an approximation-theoretic sense, that pretraining is optional: a single-layer softmax attention network with...
-
23
Dual-Adversarial Safety Alignment: Cultivating Intrinsic Threat Comprehension in LRMs
Hongli Shen, Shaopeng Fu, Qinbo Zhang, Jian Li, Di Wang
cs.LG · cs.AI · cs.CR
Large reasoning models (LRMs) achieve remarkable success on complex tasks but remain vulnerable to harmful prompts that induce unsafe outputs. Recent methods align LRMs using direct refusals or safety rationales, yet often focus on prompt patterns rather than intrinsic attack mechanisms. As a result, these pattern-centric alignments struggle to generalize across diverse jailbreaks, compromising adversarial robustness and reasoning utility. We...
-
24
Generalized Convexity and Smoothness via Conjugate Duality: Optimization Theory for Deep Neural Networks
Binchuan Qi
cs.LG
Deep neural network (DNN) training with stochastic gradient descent (SGD) and its variants achieves strong empirical performance, yet classical optimization theory does not fully explain this success. This limitation arises because conventional analyses rely on assumptions such as differentiability, convexity, or smoothness, which are often violated by DNN objectives. In this paper, we establish a unified optimization framework for DNN...
-
25
Tracking the Best Strategy in an Extensive-Form Game
Stephen Pasteris, Rahul Savani, Theodore Turocy
cs.LG
We consider the extensive-form bandit problem where on each trial the learner plays an extensive-form game against an oblivious adversary. We focus on the notion of switching regret, which measures the expected performance of the learner against that of any switching sequence of mixed strategies in retrospect. Our algorithm takes a parameter $ρ>0$ and achieves a switching regret of $\tilde{\mathcal{O}}((1/ρ+ρK)\sqrt{H A T})$ where $K$ is the...
-
26
When Do Task Vectors Interfere? Mapping the Validity Boundaries of Weight-Space Composition
Chencheng Zhu, Xiaoyang Li, Taotao Cai
cs.LG
Task arithmetic treats fine-tuning displacements as composable directions in weight space, yet it remains unclear when parameter addition reflects predictable changes in model function. We separate parameter geometry from functional geometry and measure pairwise functional non-additivity over a two-dimensional task-vector surface, using a first-token predictive-distribution interaction ratio conditioned on an input distribution and evaluated...
-
27
Hierarchical rank-evolving representation for physics-informed neural networks
Ruoyang Su, Xi-Le Zhao, Kun Li, Liang Li
cs.LG · math.NA · physics.comp-ph
Recently, tensor-based physics-informed neural networks (T-PINNs) have received increasing attention. However, existing T-PINNs still face a fundamental challenge: they mainly rely on pre-specified low-rank tensor decompositions with manually tuned ranks, which limits their ability to capture the underlying structures of multivariate solution functions and hinders their practical deployment. To address this challenge, we propose a...
-
28
MixFormer: Linear Transformer with Mixture of Memory Experts
Yu Guo, Lei Duan
cs.LG · cs.AI
State Space Models (SSMs), as a mainstream research direction of linear Transformers, aim to achieve higher efficiency than standard Transformers in long-context modeling. However, existing SSMs suffer from limited input adaptivity and constrained memory capacity, leading to information loss when modeling ultra-long sequences. To address these limitations, we propose MixFormer, a novel linear Transformer that integrates a...
-
29
Flow-based conditional cardiac anatomy generation for virtual cohorts
Konstantinos Kevopoulos, Beatrice Moscoloni, Benjamin Alheit, Cameron Beeche, Julio A. Chirinos, Alexander Heinlein,...
cs.LG · cs.CV · q-bio.QM · q-bio.TO
Cardiac digital twin research is moving from subject-specific anatomical replicas toward virtual cohorts that represent clinically relevant population subgroups. Yet access to representative imaging-derived anatomy datasets remains limited by cohort size, subgroup sparsity, and data-sharing constraints. Conditional generative models could help address this gap, but virtual cohorts are useful only if they preserve realistic, metadata-dependent...
-
30
Learning to Modulate, Not to Cycle: Soft Actor---Critic Recovers Inverter-Style Heat-Pump Control
Faizan Ahmed, Aniket Dixit, James Brusey
cs.LG · cs.AI
On--off cycling is the main cause of compressor wear in residential heat pumps, yet reinforcement learning (RL) controllers for buildings typically optimise only energy cost and thermal comfort, ignoring how much the learned policy cycles. We add a levelised compressor-wear term to the control reward and study how the resulting behaviour depends on the RL algorithm. Training Soft Actor---Critic (SAC) and Proximal Policy Optimisation (PPO) on...
-
31
From Approachability Residuals to Anytime-Valid Evidence: The Online Convex Geometry of Testing by Betting
Jinze Zhao
cs.LG
Betting-based sequential tests and Blackwell approachability are linked by a rate-explicit reduction through support-function residuals. For a compact convex target $S$ and vector observations $r_t$, an OCO learner selects a predictable normal $w_t$ and produces $q_t=\langle w_t,r_t\rangle-h_S(w_t)$. We prove the exact pathwise identity $$ \dist(\bar r_T,S) =\frac1T\sum_{t=1}^Tq_t+\frac{\Reg_T}{T}. $$ When $|q_t|\leq B$, composing this...
-
32
WDL-OPD: Weak-Driven On-Policy Distillation via Mixture-Constrained Co-Training
Zehao Chen, Gongxun Li, Tianxiang Ai, Yifei Li, Zixuan Huang, Wang Zhou, Tao Huang, Fuzhen Zhuang, Xianglong Liu,...
cs.LG · cs.AI
On-policy distillation (OPD) aligns a student with a teacher on trajectories sampled from the student itself, reducing the train-test state mismatch of offline distillation. The same feedback loop can nevertheless be unstable: each update changes both the policy and the states on which the next update is computed. We introduce WDL-OPD, a mixture-constrained co-training method with two trainable policies. An anchor policy generates every...
-
33
Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching
Kristian Schwethelm, Daniel Rueckert, Georgios Kaissis
cs.LG · cs.CL · cs.DC
A main promise of looped language models (LMs) is depth-adaptive inference. By iterating a block of shared layers a variable number of times, the model can use less compute for "easy" tokens and more for "hard" ones. However, this adaptivity breaks standard batching: tokens in the same batch now require a different number of loops, so there is no unified forward pass, making efficient inference difficult. Standard inference frameworks like...
-
34
How Simple Can It Get? From Interpretable Equations to Readable Rules for Financial Decision Making
Adia Lumadjeng, Ilker Birbil, Erman Acar
cs.LG · cs.AI
In regulated domains such as finance, a model that cannot be explained cannot be deployed, yet many interpretable classifiers defeat their own purpose by producing formulas with dozens of features that no regulator could read. We take the reverse direction. Starting from an interpretable classifier expressed as a single equation over the input features, we progressively simplify it into more readable forms, including a pruned monomial, a...
-
35
LITEWAY: LIghtweight HAR via Temporal Efficient highWAY
Dominique Nshimyimana, Vitor Fortes Rey, Mengxi Liu, Bo Zhou, Paul Lukowicz
cs.LG · cs.AI · cs.HC
Wearable human activity recognition (HAR) remains challenging due to the computational and energy constraints of deep learning models on resource-limited devices. Existing lightweight approaches often rely on recurrent architectures (e.g., GRU and LSTM), limiting parallelism and increasing inference latency. We propose LITEWAY, a modality-agnostic, fully convolutional framework for multichannel sensor time series that replaces recurrent...
-
36
A Mechanistic Diagnostic of Rank Collapse in Post-Norm Decoder Transformers
Xingjian Wang, Qingyu Han, Xiaodong Luo, Yin Zhang
cs.LG
Deep decoder-only Transformers often replace the original Post-Norm architecture with Pre-Norm variants because Post-Norm training is highly sensitive to warmup and learning rate under conventional initialization schemes. Although prior work has identified rank collapse and gradient vanishing as related symptoms, it remains poorly understood how causal attention creates high-similarity representations and why training dynamics fail to repair...
-
37
From Objectives to What Models Learn: A Landau Theory of Invariant Learning
Pinli Wang, Yue He, Peng Cui
cs.LG
Invariant learning seeks representations that remain predictive across environments, yet the behavior of its objectives along the regularization path is often opaque. We address this objective-behavior gap by viewing representation learning as multimode magnetization and deriving, from concrete invariant-learning objectives, a Landau-type effective free energy whose low-order coefficients form objective signatures and induce distinct...
-
38
Imaginative Generative AI: Crossing the Entropy Wall into Worlds Beyond Imitation
Hossein Goli, Farzan Farnia, Amin Gohari
cs.LG · cs.AI · cs.CV
Generative AI models are primarily designed to imitate the data distribution, an objective that neither corrects diversity lost by a learned generator nor defines how generation should extend beyond the diversity of the data itself. We introduce Imaginative Generative AI (IGA), a framework that makes diversity part of the target-distribution design problem: among distributions close to a reference, IGA selects one whose spectral diversity...
-
39
Beyond Binary: Continuous State Optimization with Graph-Structured Objectives
Corinna Cortes, Yishay Mansour, Mehryar Mohri
cs.LG
Large-scale learning systems often face the challenge of balancing multiple, potentially competing objectives, such as fairness, accuracy, and latency. While recent work has formalized this as an optimization problem over binary states, many real-world control parameters, such as fairness thresholds, diversity mixing rates, or resource budgets, are continuous. In this work, we extend the framework to \emph{continuous state spaces}. We model...
-
40
Test-Time Augmentation for LLMs: When Input Diversity Beats Output Diversity at Matched Compute
Nikita Kozodoi, Zainab Afolabi, Jack Butler
cs.LG · cs.AI · stat.ML
Test-time scaling improves LLM accuracy but multiplies inference cost, making the accuracy gained per unit of compute the metric that matters in deployment. Self-consistency is one of the established approaches, which spends this budget entirely on the output side by sampling repeated reasoning paths. We study Test-Time Augmentation (TTA), which extends self-consistency by also perturbing the input, aggregating predictions across transformed...
-
41
In-Context Density Estimation for Tabular Data
Patryk Marszałek, Jacek Tabor, Marek Śmieja
cs.LG
Density estimation underlies many unsupervised tasks on tabular data such as anomaly detection, out-of-distribution detection, and data augmentation. Although all these problems reduce to questions about where probability mass lies, they are typically solved individually by fitting a separate model to each dataset, with its own hyperparameters and tuning budget. We introduce ICED, an in-context, energy-based density estimator that removes...
-
42
Hallucinations and Constraints : Regulating surgical workflow recognition beyond accuracy
John S. H. Baxter, Pierre Jannin
cs.LG
Hallucinations are a major concern for the integration of artificial intelligence into medicine, although less explored in the realm of medical image processing. Unlike problems in natural text understanding and reasoning therewith, determining whether or not predictions derived from biomedical images and signals is less intuitively clear. This article suggests that topological errors could constitute hallucinations in a way that can be more...
-
43
MaxModShift: Model Privacy via Designed Shifts
Nomaan A. Kherani, Urbashi Mitra
cs.LG · cs.IT · eess.SP
Model learning by an eavesdropper is treated as an estimation problem in a federated environment. The Fisher Information Matrix for the eavesdropper's estimation problem is driven to singularity through a signaling design; this ensures that the eavesdropper cannot learn the model. Herein, the innovation of prior designs is that model shifts are designed to maximize the difference in the model learned by Eve and the central server while...
-
44
Targeted Label-Flipping and Oversampling Attacks on Federated Conditional GANs
Panav Shah, Avishek Ghosh
cs.LG
In a federated learning setup for GANs, several adversarial attacks are possible. One such attack is label flipping, in which malicious clients deliberately alter label information during local training in order to manipulate the global generator. The objective of this attack is to skew the learned generation distribution so that samples conditioned on a target label are instead mapped to a source class. In this work, we investigate the...
-
45
Beyond the Capability Boundary: Zeroth-Order Optimization for Self-Evolving LLM Agents
Bingzhen Liu, Xiaomeng Fan, Yuwei Wu, Zhi Gao, Mingyang Gao, Chuanhao Li, Yunde Jia
cs.LG · cs.CL
Self-evolving methods improve the capabilities of LLM agents by sampling trajectories from the underlying LLMs and learning from these trajectories. However, these methods struggle to learn beyond the inherent capability boundary of the agents, since the agents cannot sample correct trajectories on difficult examples for further improvements. In this paper, we propose a zeroth-order self-evolution framework that enables agents to learn beyond...
-
46
VeinCast: Physics-Guided Dynamic Field Graphs with Graph-Conditioned Fusion for Global Medium-Range Weather Forecasting
Zhisheng Chen, Jinhan Li, Yuxuan Li, Yuan Gao, Hao Wu, Zheng Lu, Jinlong Du, Kun Wang, Bo An
cs.LG · cs.AI
Global medium-range weather forecasting requires modeling structured yet state-dependent interactions among heterogeneous atmospheric fields. Existing data-driven models largely learn these interactions implicitly, whereas equation-level physical constraints may inherit approximation and model-form biases. We present VeinCast, a physics-guided dynamic field graph and graph-conditioned fusion framework that jointly forecasts 69 surface and...
-
47
SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation
Jefferson Hernandez, Jaywon Koo, Zilin Xiao, Chen Wei, Vicente Ordonez
cs.LG · cs.AI
Group-based reinforcement learning objectives such as GRPO can allocate learning signal poorly across prompt difficulty: under binary rewards, group normalization induces a divergent weighting on easy prompts. We introduce Softmax Advantage Group Estimation (SoftmaxGRPO), a drop-in alternative that replaces z-score-normalized group advantages with temperature-scaled softmax advantages, keeping weights bounded regardless of prompt difficulty....
-
48
Full-Feature versus Limited-Input Machine Learning for Residential Energy Estimation: A Comparative Analysis of RECS and ResStock Under Realistic Input Constraints
Aditya Ramnarayan, Fatih Evren, Patti Gunderson, Samuel Rosenberg
cs.LG
Residential energy estimates are often needed before detailed envelope characteristics, equipment efficiencies, infiltration, sensor, or billing data are available. This study quantifies the trade-off between predictive accuracy and input accessibility using two nationally representative U.S. residential-energy datasets: the survey-based Residential Energy Consumption Survey (RECS) and the simulation-based ResStock dataset. Full-feature...
-
49
FEAST: Federated Shared-Space Training for Resource-Heterogeneous Clients
Bostan Khan, Masoud Daneshtalab
cs.LG · cs.DC
Federated learning (FL) must serve devices with varying computational capabilities. A fixed model cannot suit all devices, while training one model per deployment limit is costly. Federated supernet training instead learns one elastic model with differently sized subnetworks, then deploys a suitable one to each device. When client inference budgets differ, however, parameters exclusive to high-cost subnetworks are reachable by fewer clients....
-
50
Multimodal Federated Learning under Dual-Axis Modality Missingness
Adiba Orzikulova, Jaehyun Kwak, Jaemin Shin, Yunqi Guo, Xiaomin Ouyang, Guoliang Xing, Steven Euijong Whang, Sung-Ju Lee
cs.LG · cs.AI
Multimodal federated learning (FL) supports collaborative modeling in privacy-sensitive health-sensing and medical settings, but realistic deployments often exhibit dual-axis modality missingness: clients have different modality sets, and individual samples may contain only subsets of the modalities available locally. Existing methods typically address these two axes separately. We propose Flux, a multimodal federated learning framework built...
-
51
Label Granularity Skew in Federated Learning with Hierarchical Image Classification
Jaeheon Kim, Hokeun Kim, Bong Jun Choi
cs.LG
Federated learning enables privacy-preserving collaboration across distributed devices without centralizing local data. However, clients may differ not only in data distributions but also in domain knowledge and annotation capabilities. In this paper, we introduce label granularity skew, a new form of statistical heterogeneity in federated hierarchical classification, in which clients provide taxonomy-consistent labels at different levels of...
-
52
DreOPD: Degraded-Reference Extrapolative On-Policy Distillation for Flow-matching Models
Mingfeng Lin, Chengfei Cai, Lin Xu, Yuxiang Wei, Liang Han
cs.LG · cs.CV
Flow-matching models are now a mainstream method to image generation, but its adaptation to diverse downstream scenarios typically relies on post-training, which may cause conflicts among task-specific optimization objectives. Reinforcement learning enables direct optimization of task-specific rewards beyond the original models, yet trajectory-level optimization may incur high-variance gradients and cross-task interference. On-policy...
-
53
Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation
Yuki Ichihara, Naoto Iwase, Mohammad Atif Quamar, Junpei Komiyama
cs.LG · cs.AI
On-Policy Self-Distillation (OPSD) is commonly interpreted as the transfer of privileged information: a teacher observes the verified solution to the target problem and supervises the student's trajectory. However, this interpretation conflates two effects. The reference solution not only reveals the answer to the current instance but also changes the context under which the teacher provides token-level supervision. We investigate the role of...
-
54
FedTVD: Balancing Data Quality and Quantity for Robust Federated Learning
Radwan Selo, Majid Kundroo, Taehong Kim
cs.LG · cs.AI · cs.CV · cs.DC
Federated Learning (FL) enables collaborative model training across distributed client devices while preserving data privacy. However, FL faces significant challenges due to data heterogeneity, particularly in terms of label distribution skewness and variations in dataset sizes, which can lead to biased model updates and hinder convergence. To address this, we propose FedTVD, a novel FL algorithm that weights client contributions during...
-
55
Online Learning of Scale Parameters in Score-Driven Filters
Fabrizio Lillo, Giulia Livieri, Gianluca Palmari
cs.LG · math.ST · stat.ME · stat.ML
Score-driven filters multiply a scaled log-likelihood score by a gain that controls the update magnitude. We treat this gain as a decision variable and study its online learning. Conditional on the current state, observation, score, and scaling rule, each admissible gain induces a reachable next state and a one-step-ahead predictive density: scalar gains govern distance along a line, while diagonal gains govern coordinatewise transmission....
-
56
Beyond Solvability: Task Learnability as a Static Prior for LLM RL Post-Training
Ting Zhou, Zhenqing Ling, Daoyuan Chen, Qianli Shen, Yilun Huang, Ying Shen, Yaliang Li
cs.LG · cs.AI
Reinforcement learning (RL) has become a central post-training paradigm for eliciting reasoning capabilities in large language models, yet uniform task sampling allocates compute without regard to differences in how tasks respond to optimization. Existing task-valuation methods mostly rely on snapshot-based signals such as current pass rate or reward, which estimate how solvable a task is under the current policy. However, tasks with similar...
-
57
FedA2L: Adaptive layer-wise learning rate adjustment in decentralized federated learning
Van Truong Vo, Khoa Nguyen, Taehong Kim
cs.LG · cs.AI · cs.CV · cs.DC
Decentralized intelligence systems with heterogeneous devices and limited coordination increasingly rely on decentralized federated learning (DFL). However, DFL suffers from convergence inefficiency under data heterogeneity due to the use of a uniform learning rate (LR) that ignores layer-specific optimization needs. Foundational layers are responsible for maintaining network consensus, while specialized layers adapt to local data...
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.