cs.LG · 2026-08-14 · No. 84
Machine Learning, 2026-08-14.
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
Defensive Boosting for Online Probabilistic Forecasting
Georgy Noarov, Aaron Roth
cs.LG · cs.CC · cs.DS · stat.ML
We study online probabilistic forecasting of binary outcomes chosen by an adaptive adversary. Given an online learning algorithm for a weak hypothesis class $H$, we would like to efficiently obtain two incomparable guarantees that existing online boosting techniques provide separately. Online gradient boosting competes in Brier score with the best predictor induced by the span of $H$ on every sequence, but promises nothing when the span does...
-
02
Exponential Convex Calibration Dimension for the Multi-Label Jaccard Measure
Mingyuan Zhang
cs.LG · stat.ML
The per-instance Jaccard score, or intersection over union (IoU), is standard in multi-label classification and binary segmentation. With $s$ labels, its loss matrix has $2^s$ outcomes and reports. Under the convention $\mathrm{Jac}(\varnothing,\varnothing)=1$, we prove that the Jaccard score, shifted-loss, and ordinary loss matrices are nonsingular and that the loss columns have affine dimension $2^s-1$. The proof combines a finite MinHash...
-
03
DARTree: Speculative Diffusion Decoding with Autoregressive Draft Trees
Tianyi Li, Yaxin Luo, Xinyi Shang, Zhiqiang Shen
cs.LG
Speculative decoding losslessly accelerates autoregressive language models by verifying multiple draft tokens in parallel. Diffusion-based drafters further reduce proposal latency by predicting an entire token block in parallel, but their position-wise distributions are marginal rather than conditioned on tokens selected along each draft path. Existing recurrent correction incorporates causal information along a single draft chain, whereas...
-
04
Vero: Can AI Agents Build Formally Verified Software Repositories?
Zhe Ye, Hantao Lou, Yuechun Sun, Peiyang Song, Zhengxu Yan, Timothe Kasriel, Qingyang Zhang, Kaiyu Yang, Soonho...
cs.LG · cs.AI · cs.LO · cs.PL · cs.SE
AI agents are increasingly used for programming, but do not provide any guarantee on the correctness of generated code. Verified code generation, in which an agent produces both an implementation and a machine-checked proof of its specification, offers a stronger path toward trustworthy AI-generated software. Existing benchmarks in this direction either focus on individual functions or only evaluate proof generation with provided...
-
05
The data geometry of masking diffusion: Certified-optimal schedules via unmasking growth complexity
Martin J. Wainwright
cs.LG · cs.AI · cs.IT · math.ST · stat.ML
We study masking diffusion for discrete sampling and introduce a path-resolved measure of data geometry called the \emph{unmasking growth complexity} ({\textsf{UGC}\xspace}). Its local increments directly control Kullback--Leibler (KL) discretization error, yielding a unified analysis of Bernoulli-subset and fixed-cardinality unmasking schemes. In log-reveal-odds coordinates, this structure yields optimized single-block and multi-block...
-
06
Intervention-Aware Clinical World Model for Post-Op Outcome Forecasting in Cardiology
Yunsung Chung, Yingshuo Liu, Abboud F. Hassan, Han Feng, Mary M. Maleckar, Nassir Marrouche, Jihun Hamm
cs.LG · cs.CV
Many clinical prediction models treat post-intervention outcomes as a one-step mapping from baseline measurements to a future endpoint. However, recovery after a procedure often unfolds as an irregular trajectory: clinical observations, medication changes, repeat interventions, and physiological measurements are recorded asynchronously and can change risk assessment over time. We propose an intervention-aware clinical world model that...
-
07
Intern-S2-Preview: Scientific Agentic Foundation Model
Lei Bai, Jiaqi Cao, Chiyu Chen, Guanzhou Chen, Kai Chen, Guangran Cheng, Erfei Cui, Xuanlang Dai, Shengyuan Ding,...
cs.LG · cs.CL · cs.CV
Scientific discovery increasingly requires AI systems that can reason over scientific evidence of heterogeneous modalities, interact with scientific tools and environments, and sustain progress across long task horizons. We present Intern-S2-Preview, a series of scientific agentic foundation models designed to support multimodal scientific understanding, reasoning, generation, and long-horizon tasks. The training pipeline begins with...
-
08
Sparse Orthogonal Regression Technique: A Spectral Framework for Equation Discovery, Approximation, and Integration
Sabin Roman, Ljupco Todorovski, Saso Dzeroski
cs.LG
We develop the Sparse Orthogonal Regression Technique (SORT), a sparse spectral framework for learning orthonormal-basis expansions from noisy and irregularly sampled data. SORT estimates expansion coefficients directly from observations using L1-regularized regression, avoiding explicit quadrature or analytic inner-product evaluation. The central application is data-driven discovery of ordinary differential equations: vector fields are...
-
09
Synthetic Persona Pretraining: Alignment from Token Zero
Julian Minder, Viktor Moskvoretskii, Raghav Singhal, Difan Jiao, Andy Arditi, Shaobo Cui, Yiderigun Borjigin, Kartik...
cs.LG · cs.AI · cs.CL
As language-model-based AI is increasingly deployed in autonomous settings, aligning its goals and values with those of humans becomes critical. Today, alignment, and the assistant identity itself, are typically introduced only after pretraining, once behavioral priors are already established. This can make values a thin overlay, rather than deeply rooted, and facilitate subsequent misalignment. Pursuing a different paradigm, we introduce...
-
10
Active-Trace Complexity Bounds for Moreau--Yosida Unadjusted Langevin Sampling
Yuchen Xin, Zhihua Zhang
cs.LG
We study the Moreau--Yosida unadjusted Langevin algorithm (MYULA) for the nonsmooth composite target \[ π(dx)\propto \exp\{-f(x)-g(x)\}\,dx, \qquad x\in\mathbb R^d, \] where \(f\) is \(m\)-strongly convex with \(L_f\)-Lipschitz gradient and \(g\) is convex and \(G\)-Lipschitz. Let \(g_λ\) be the Moreau envelope of \(g\), \(π_λ\) the corresponding smoothed target, and \(a_λ=\operatorname{tr}H_λ\), where \(H_λ\) is the a.e./weak Hessian of...
-
11
Concept Drift Detection and Adaptive Retraining of Malware Classification Models
Christofer Washington Berruz Chungata, Martin Jurecek, Katerina Potika, William B. Andreopoulos, Mark Stamp
cs.LG · cs.AI · cs.CR
Concept drift refers to changes over time in the statistical properties of data, as compared to the data that was used to train a learning model. Machine learning models for malware detection or classification are particularly susceptible to performance degradation caused by concept drift, as attackers constantly modify existing malware. In this chapter, we analyze two machine learning-based approaches to automated concept drift detection-a...
-
12
Doubly Robust Estimation of Causal Effect on CVR with Targeted Regularization
Jiayi Dan, Bo Li, Lu Deng, Yong Wang
cs.LG
Post-click conversion rate (CVR) is a key metric in various scenarios including e-commerce and advertising, reflecting the efficiency and user experience in the second stage of the conversion process. Estimating the causal effect on CVR is therefore of great practical importance. However, directly applying existing causal inference methods to clicked samples introduces sample selection bias and increased variance due to the exclusion of...
-
13
Symmetry-Breaking De Novo Crystal Generation via Markovian Jump Diffusion
Van Khoa Nguyen, Alexandros Kalousis
cs.LG
Generating crystals has recently attracted significant interest due to their broad applications in materials science. However, existing generative models struggle to produce complete crystallographic specifications, limiting their ability to capture global symmetry and structural dependencies. In particular, current state-of-the-art approaches generate crystals only up to site symmetries and rely on sampling space groups from empirical...
-
14
Reduced Matrix Multiplication: Input-Adaptive Matrix-Product Reduction for LLM Inference
Zixuan Lan, Yanhong Li, Jiawei Zhou
cs.LG · cs.AI · cs.CL
Transformer-based language models achieve strong performance but incur substantial inference cost due to repeated high-dimensional matrix multiplications. We propose Reduced Matrix Multiplication (RMM), a training-free, input-adaptive inference method that reduces Transformer matrix products by selecting informative slices along their contraction dimensions, without modifying model weights. Under a simple retention-ratio control, RMM provides...
-
15
When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation
Shuhan Wang, Yilin Luo, Nan Xu, Chi Wang Cheung
cs.LG
Rotation-based post-training quantisation commonly applies an orthogonal transform across an entire attention head to reduce outlier-induced error. RoPE instead partitions each head into two-dimensional frequency pairs, raising the question of whether a transform respecting this decomposition can improve on full-head mixing. Prior work has established the per-pair rotations that commute with RoPE. We state the converse result that, for...
-
16
Simulation-to-real transfer learning for infrared spectroscopic chemical sensing and analysis from molecules to complex samples
Yusen Tan, Yixuan Chen, Zheng Fang, Pan Liu, Yifan Li, Qinyu Guo, Zhedong Lin, Yuqiang Li, Xiangxiang Zeng, Tong...
cs.LG · cs.AI
Infrared (IR) spectroscopy is widely used for chemical sensing, but extracting reliable chemical information from spectra remains challenging. Conventional interpretation is labor-intensive, relies on prior knowledge and reference spectra, and is difficult to scale, whereas most machine-learning methods are tailored to individual tasks or datasets, require large labeled training sets, and transfer poorly across analytical objectives and...
-
17
Where You Measure Decides What You Measure: Position Selection in Ablation-Based SAE Evaluation
Valentin Noël
cs.LG
Sparse autoencoders are meant to name the things a language model computes, and the usual way to check that a latent matters is to switch it off and see what changes. But a latent fires at many tokens, and the effect has to be measured at one of them. The convention is to measure where the latent fires hardest. That choice is almost never reported, and it is not made by the experimenter: it is made by the dictionary under evaluation. Change...
-
18
Neural Quadratic Forms: A Unified Minimal Model for Sudden Learning and Scaling Laws
Liu Ziyin, Yizhou Xu, Tomaso Poggio, Isaac Chuang
cs.LG · cond-mat.dis-nn · cond-mat.stat-mech
Neural networks trained by gradient descent on a smooth cost function can nevertheless learn in steps: the cost holds on long plateaus and then drops abruptly. Meanwhile, training losses instead follow smooth power laws. Variants of both behaviors occur in architectures with very different microscopic structures, which is the signature of a few relevant collective variables. We show that a symmetry fixes what those variables are: a network...
-
19
Training AI Scientists to Replicate Research
Damon Falck, Samer Sabri, Anja Surina, Thom Foster, Anya Sims, Sam Devlin, Dylan Rogers, Tantum Collins, Kaloyan...
cs.LG · cs.AI
The replicability of papers is a cornerstone of scientific knowledge, ensuring the reliability of existing results and providing a base for further experiments. The act of replication typically illuminates details that were previously underspecified, and thus requires similar hypothesis-driven exploration to open-ended research. In this work, we develop Replica, a scalable task space for paper replication. To provide reward signal, we...
-
20
A Probe Direction Is a Property of Its Prompt
Valentin Noël
cs.LG
A model that behaves differently when it senses it is being tested would undermine the evaluations we rely on, so recent work has sought to read that sense directly from a model's activations. The standard instrument contrasts activations on prompts that announce an evaluation against prompts that do not, and reports how well the resulting direction separates held-out cases. That number is then compared across models and correlated with...
-
21
The Time Value of Evolution
Matthew Siper, Ahmed Khalifa, Julian Togelius
cs.LG
In evolutionary search, a weak child can be a valuable ancestor that makes high-fitness regions reachable. Immediate-return control is blind to this delayed utility, penalizing mutations through their immediate offspring even when they open productive future lineages. We formalize this hidden dynamic as the time value of evolution within a finite-horizon Markov decision process. To exploit it, we introduce Lineage-Value Policy Gradients...
-
22
Large-scale Testing Global Optimization Methods with Black-box Adversarial Attacks
Wojciech Zarzecki, Jarosław Arabas
cs.LG · cs.AI
Existing global optimization benchmark suites are of a moderate size and are based on a small number of analytical functions that date back even to the 1970s. This causes a risk of biasing the development of global optimization methods. We argue that the tasks related to the black-box adversarial attack (BBAA) can serve as valuable global optimization benchmark in many-dimensional space. We demonstrate the efficiency of several types of...
-
23
EEG Decoding Using CNN and LSTM Network
Athanasios Karagounis
cs.LG · cs.HC
Motor imagery (MI) brain--computer interfaces (BCIs) have emerged as a promising approach for establishing flexible communication pathways between the human brain and external devices , particularly for individuals affected by stroke or neurodegenerative disorders. Reliable decoding of motor-imagery electroencephalography (MI-EEG) remains challenging because EEG recordings contain substantial noise and exhibit complex, weakly informative...
-
24
Into the ORBIT for Time Series: Training Regimes for Foundation Models
Hongjie Xia, Yiding Liu, Yifan Hu, Peiyuan Liu, Zewei Dong
cs.LG · cs.AI
Time series foundation models (TSFMs) have advanced primarily through architectural innovation, while training regimes for large-scale heterogeneous corpora remain under-explored. As a result, pre-training distributions are often poorly controlled with respect to domain imbalance, context requirements, prediction horizons, and missingness. We introduce ORBIT (Omni-Range Bootstrap Incremental Training), a training paradigm that makes this...
-
25
Virtual Temperature Sensors in Power Transformers Using Neural Ordinary Differential Equations
Berk Hadzhamolla, Alexander Johannes Stasik, Signe Riemer-Sørensen
cs.LG
Accurate modeling and forecasting of power transformer thermal behavior are critical for reliability, asset lifetime, and optimized power system operation. Numerical approaches such as finite element methods (FEM) and computational fluid dynamics (CFD) offer high fidelity but are computationally expensive, require complex mesh generation, and are often impractical for real-time or large-scale applications, particularly when transformer...
-
26
Novel Knowledge-Guided Generative Methods for Synthetic Transcriptomic Data
Francesca Pia Panaccione, Sofia Mongardi, Marco Masseroli, Pietro Pinoli
cs.LG · cs.AI
As biomedical research increasingly relies on data-intensive tools, the quality and utility of datasets are critical. Challenges such as imbalances, biases, and ethical or legal constraints often limit access to high-quality data. Synthetic data generation can help overcome these limitations. Here, we present a comparative analysis of generative models for transcriptomic data, investigating strategies to incorporate prior biological knowledge...
-
27
Knowledge-guided Pattern Discovery via Coupled Tensor Factorizations
Gaute Johannessen, Geert Roelof van der Ploeg, Evrim Acar
cs.LG
In order to understand complex systems such as the human metabolome or human brain, different sensing technologies are used, generating complex data. These datasets are often multiway, i.e., with more than two axes of variation such as a subjects by metabolites by time array. While tensor factorizations have successfully revealed interpretable patterns from such complex data, they have so far been mainly data-driven. On the other hand, there...
-
28
History-informed Lagrangian Neural Networks
Tianshuo Zhang, Xianglei Xing, Wenzhe Zhai, Jia Gao, He Cao
cs.LG
Forecasting the long-horizon evolution of mechanical systems from position-only observations is a pivotal yet difficult task, as hidden velocities and trajectory-specific physical properties must be inferred simultaneously. Although physics-guided neural networks like Lagrangian Neural Networks (LNNs) guarantee physical plausibility, they generally require complete state inputs and lack adaptability to changing system parameters. To break...
-
29
TANGCO: Learning Topology-Aware Capacity Allocation for Overload-driven Cascading Failures
Orkun Irsoy, Leman Akoglu, Osman Yagan
cs.LG · cs.SI
Networked systems, from power grids to traffic networks and cloud clusters, carry loads across nodes with limited capacity. A node whose load exceeds its capacity fails and sheds its load onto its neighbors, which can trigger a system-wide cascade. We study how to allocate a fixed capacity budget across nodes to resist these cascades under local load redistribution. The problem is difficult because no optimal allocation is known, and the...
-
30
Beyond Simulated Benchmarks: Evaluating Motion Representations for Fall Detection Under Real-World Data Scarcity
Timilehin B. Aderinola, Ilaria D'Ascanio, Luca Palmerini, Lorenzo Chiari, Jochen Klenk, Clemens Becker, Brian...
cs.LG
Falls are a major health concern for older adults, and wearable sensors have been widely explored for detecting falls and enabling timely intervention. However, real-world falls are extremely rare: collecting 100 of them requires an estimated 100,000 days of monitoring, resulting in severely limited labelled data for training machine learning models. Consequently, many approaches rely on simulated datasets, often reporting high laboratory...
-
31
ProME: Prototype-Margin Environments with Repair-Aware Selection for Group-Robust Learning
Qianqian Wang, Yunshan Li, Dawei Huang, Wenwu Gong, Lili Yang
cs.LG · cs.CV
Group-robust learning is crucial for maintaining accuracy on rare subpopulations when training-group labels are unavailable. However, existing methods often infer environments from a separate reference model and select representations before fitting the classifier used at deployment, leaving both decisions misaligned with the deployed predictor. In this work, we formulate group robustness without training-group labels as the endogenous...
-
32
Branch and Bound for Relational Verification of Neural Networks
Kota Fukuda, Zhenya Zhang, Guanqin Zhang, Jianjun Zhao
cs.LG
Verification of neural networks against relational specifications, such as global robustness, is crucial for safety-critical applications of cyber-physical systems (CPS), given their increasing adoption of AI components. Compared to simple trace properties (e.g., local robustness), verifying relational specifications requires reasoning about the relationship between multiple network inferences, which brings significant technical challenges....
-
33
FlowLOB: Efficient and Controllable Limit Order Book Generation with Flow Matching
Zhuohan Wang, Andreea Bacalum, Ollie Olby, Carmine Ventre, Namid Stillman
cs.LG · cs.CE · q-fin.CP · q-fin.TR
Limit order book (LOB) simulators are most useful to practitioners when they combine realistic market dynamics, computationally efficient sampling, controllable scenario generation, and the ability to generalize beyond the instruments seen during training---properties that existing agent-based and deep generative simulators provide only partially. We present \textbf{FlowLOB}, a conditional \textbf{flow}-matching generator of \textbf{LOB}...
-
34
Sampling Luck Masquerades as Allocation Gain: Auditing Test-Time Budget Allocation for Neural Combinatorial Optimization
Jinhyung Bae
cs.LG · cs.AI · math.OC
Neural combinatorial optimization (NCO) solvers report the best of many sampled solutions per instance, and the sample count is, by convention, identical for every instance. Whether a non-uniform allocation of a fixed total budget would buy anything has not been measured. We measure it, and we audit the measurement itself. First, on in-distribution workloads the allocation headroom is not detectable. Across three pretrained solvers (POMO, AM,...
-
35
Learning Discrete Decisions for MIPs with Constraint-Aware Diffusion
Vincenzo Di Vito, Mehdi Taghizadeh, Deepjyoti Deka, Kaarthik Sundar, Ferdinando Fioretto
cs.LG
This paper proposes a novel learning-based approach to approximately solve instances of mixed-integer optimization problems. These problems are computationally challenging, as they require jointly determining discrete and continuous decisions while satisfying complex combinatorial constraints. The proposed method relies on a graph-based generative diffusion model that learns the discrete component of mixed-integer optimization problems while...
-
36
A Multispectral Framework for the Detection of Calcium Carbide-Induced Ripening and Shelf-Life Estimation in Climacteric Fruits
Gurbhit Chaurakoti, Harshit Kumar, Hani Kumar, Anurag Singh, Ram Asrey
cs.LG
Significant health risks are associated with the illegal, yet commonly practiced use of industrial-grade Calcium Carbide (CaC2) for ripening climacteric fruits like mango and banana, which leaves behind trace residues of arsenic and phosphorus. To address this, the proposed study explores a novel, non-invasive multispectral framework for distinguishing safely ripened fruits (naturally ripened and ethephon-induced) from calcium carbide-ripened...
-
37
Latent On-Policy Self-Distillation
Guibin Zhang, Jiayang Lyu, Ran Sun, Xinlei Yu, Haoyu Zhao, Qibing Ren, Shuicheng Yan
cs.LG · cs.CL
Enabling agents to learn from experience and internalize it into their policy has become a central problem in self-evolving AI. On-policy self-distillation (OPSD) offers an effective pathway by using a privileged self-teacher to provide dense supervision on the student's own trajectories; however, existing methods still rely heavily on designer-specified privileged artifacts (e.g., answers, feedback, skills, or trajectories), limiting the...
-
38
On the global feature importance for interpretable and trustworthy heat demand forecasting
Milan Zdravković
cs.LG · eess.SY
The paper introduces the ante-hoc Explainable AI methodology to assess the global feature importance of the Machine Learning models used for heat demand forecasting in intelligent control of District Heating Systems, with motivation to facilitate their interpretability and trustworthiness, hence addressing the challenges related to adherence to communal standards, customer satisfaction and liability risks. Methodology includes use of four...
-
39
Incremental Evaluation and Training in Relational Deep Learning
Jakub Peleška, Gustav Šír
cs.LG · cs.DB
Relational Deep Learning (RDL) models multi-tabular databases as temporal heterogeneous graphs to enable end-to-end representation learning. However, prevailing RDL evaluation practices rely on static, single-episode dataset snapshots, overlooking the continuous, time-evolving nature of real-world databases. Consequently, current RDL benchmarks fail to capture how model performance changes as new data accumulates over time. To address this...
-
40
Balanced Adaptive Prototype Selection for Scalable TabPFN Inference on Large-Scale Tabular Data
Mahboobe Jadid, Melika Rezaye Garkani, Ali Mousavi
cs.LG
Pretrained tabular foundation models have demonstrated strong predictive capability; however, their application to large-scale datasets remains constrained by the limited inference context. This paper introduces Balanced Adaptive Prototype Selection (BAPS), a framework for constructing compact, information-preserving contexts for scalable TabPFN inference. Without modifying or retraining the pretrained model, BAPS jointly preserves...
-
41
Learning the Mathematical Property for Designing Low Mutual Coherence Binary Sensing Matrices
Rekha, Santosh Singh, S. K. Neogy
cs.LG
In this research work, we are constructing the sensing matrix, which is essential for the success of the compressive sensing technique. We have chosen a learning-based technique for the construction of the sensing matrix. The novelty and uniqueness of the proposed technique is that it does not use any data set and also does not use a specific application. It uses the mathematical property/constraint for the construction of the sensing matrix...
-
42
Comment on "Modeling rapid language learning by distilling Bayesian priors into artificial neural networks"
Orr Well, Idan Tarshish, Nur Lan, Roni Katzir
cs.LG · cs.CL
McCoy & Griffiths (2025, henceforth M&G) suggest that a Bayesian prior can be distilled into Artificial Neural Networks (ANNs) through Model-Agnostic Meta-Learning (MAML, Finn et al., 2017). They support this empirically by showing that meta-trained networks demonstrate formal language learning abilities comparable to Yang & Piantadosi (2023)'s Bayesian learner, significantly outperforming standard ANNs. We point out that under the standard...
-
43
Understanding Backdoor Vulnerabilities in Vertical Federated Learning: The Gap Between Research and Practice
Ziqi Zhao, Jialin Lu, Junjie Shan, Junyuan Zhang, Shuya Yang, Ka-Ho Chow
cs.LG · cs.CR
Vertical Federated Learning (VFL) enables organizations holding complementary features of shared entities to collaborate and train models. In this setting, the initiator can withhold information about the learning task, while other contributors participate without exposing their local datasets, creating an asymmetric information structure aligned with growing privacy demands. However, this asymmetry is a double-edged sword. Among various...
-
44
The Objective Is the Bottleneck: Latent World Models Encode What Their Planners Cannot Use
Joyjeet Singh
cs.LG · cs.AI
Latent world models are judged by how well they predict, so when planning fails at long horizons the natural reading is that the predictor degrades. On a reproduction of LeWorldModel on TwoRoom we show the binding constraint is the planner's objective instead. The predictor is not the limit: its imagined state seventy-five environment steps ahead is still only 0.189 as wrong as assuming the world froze, while the planner never imagines beyond...
-
45
I-SDPO: Instance-Level Adaptive Self-Distillation Policy Optimization
Yubo Zhang, Xinhong Ma, Zezhong Tan, Ziqiang Dong
cs.LG · cs.CL
Group Relative Policy Optimization (GRPO) learns from reward differences within a rollout group, but receives no useful relative signal when every sampled response is incorrect. Privileged self-distillation can fill this gap with dense token supervision, yet applying it throughout training creates a different failure mode: the teacher is a biased, low-variance surrogate for the reward objective, so persistent imitation can oppose...
-
46
CardioState-JEPA: Delay-Aware Cross-Modal Learning of a Shared Cardiac Representation
Hamza Shafiq, Hung Manh Pham, Bin Zhu, Pan Zhou, Jun Hu, Aaqib Saeed
cs.LG · eess.IV · stat.ML
Electrocardiography (ECG), photoplethysmography (PPG), and phonocardiography (PCG) provide complementary views of the same cardiac cycle, yet existing cardiac foundation models are trained for a single sensing modality, leaving the shared physiology across sensors unexploited. We introduce CardioState-JEPA, a cardiac foundation model to learn a single shared representation jointly across ECG, PPG, and PCG, built on a physiology-aware...
-
47
Diagnosing JEPA World Models with Action-Conditioned Predictive Consistency
Guo An, Zijing Wu, Honghua Dong, Yuhao Yan, Zixuan Gui, Haochong Chen, Shanzhao Ruan, Xiang Wang, Yurong Ling, Qi Tian
cs.LG
Joint-embedding predictive architectures (JEPAs) learn world models that predict in a compact latent space rather than in pixels, reducing the pressure to model nuisance appearance. Yet this provides no guarantee against visual perturbations: they can still alter the encoded representation and affect subsequent action-conditioned predictions. Bisimulation captures this requirement precisely: two observations should be treated as the same...
-
48
Multi-perspective Imbalance-Conscious 6G Beamforming Optimization and Performance
Chukwunonso Henry Nwokoye, Blessing Oluchi Iloka, Chikwue V. Umeugoji, Christopher Anene Egemba, Nnenna D. Duroha
cs.LG · cs.NI
The study presents a systematic machine learning (ML) study of 6G-IoT beamforming optimization (6GBO) using supervised and unsupervised approaches. We compared the predictive power of network, environmental, device, and vision feature groups for 6GBO. Additionally, it addressed other unsupervised perspectives that can enhance 6GBO, including clustering network scenarios using methods such as K-means, DBSCAN, and hierarchical clustering....
-
49
H-VAEP and H-xT: Valuing Offensive On-the-Ball Actions in Handball by Estimating Probabilities
Julius Broermann, Oliver Müller, Michael Döring, Jochen Baumeister
cs.LG · cs.AI
Traditional player evaluation in professional handball relies on basic box-score metrics or heuristic indices, which fail to credit the multi-player build-up chain. While football (soccer) analytics has adopted Expected Threat (xT) and Valuing Actions by Estimating Probabilities (VAEP), these event-based action valuation frameworks have not yet been adapted to handball. In this paper, we present the first comprehensive adaptation and...
-
50
Momentum as Residual-Driven Multiplier Correction for Deep Learning Optimization
Zhixin Ren, Yau Lyu, Congrong Li, Liping Zhang, Shengbo Eben Li
cs.LG
Momentum-based optimizers are widely used in modern deep learning, yet the relations among momentum recursion, update geometry, and acceleration remain only partially understood. We develop an $\textbf{A}$DMM-$\textbf{I}$nspired $\textbf{M}$omentum (AIM) framework based on residual-penalty variable splitting, which interprets momentum as a multiplier-like correction driven by the splitting residual. AIM recovers the exponential moving average...
-
51
Towards Socially Compliant Navigation in Deep Reinforcement Learning via Proxemics-Based Reward Modeling
Takieddine Soualhi, Jacques Saraydaryan, Laetitia Matignon
cs.LG · cs.RO
Developing effective robot navigation methods in crowded environments is essential for real-world applications. Although recent deep reinforcement learning (DRL) methods have improved navigation performance in crowded environments, they often focus primarily on task-centric objectives and underrepresent social compliance objectives. In this paper, we introduce a novel proxemics-based reward formulation for DRL social navigation that provides...
-
52
Revisiting Overestimation Bias Problem of Q-learning: Settling Large Discrete Action Space via Action Intersection
Pu Li, Tao Tan, Hong Xie, Xiaoyu Shi, Mingsheng Shang
cs.LG
This paper considers the overestimation bias problem of Q-learning in the setting of a large action space, for the purpose of relieving the bottleneck of existing methods. We find that the large action space increases the randomness in Q-value estimation. The randomness makes two paradigms that drive the major literature on the overestimation problem have their own bottlenecks: the coupling paradigm, i.e., the optimal action and its Q-value...
-
53
EGRL: Edge generation-guided relation-aware learning for RNA-protein interaction prediction
Danyu Li, Ling Zhou, Rubing Huang, Xian Zhong, Bin Zou, Kui Jiang
cs.LG · cs.AI
RNA-Protein Interactions (RPIs) are critical for regulating cellular functions. While traditional wet-lab experiments for RPI detection are costly and time-consuming, Deep Learning (DL) methods provide an efficient computational alternative for RPI Prediction (RPIP). In particular, Graph Neural Networks (GNNs) are promising, as they naturally model RPI networks. However, existing GNN-based methods often rely on homogeneous graphs or...
-
54
Adaptive $k$ Nearest Neighbors Classifier via Granular Ball Computing
Xiaoyu Lian, Shuyin Xia, Hongxuan He, Lifeng Shen, Guoyin Wang, Xinbo Gao
cs.LG
The $k$-Nearest Neighbor~(KNN) algorithm is widely used across various tasks. The selection of the $k$ value is a key issue because it significantly impacts performance. In this paper, an adaptive and efficient KNN approach via granular-ball computing is proposed. The method consists of two stages. \textcolor{black}{In the training stage, the dataset is first coarsely partitioned to reduce the complexity of data distributions within a...
-
55
Robust data-driven discovery of fractional differential equations via weak formulations and Pareto-based subset selection
Pongpisit Thanasutives, Yoshinobu Kawahara
cs.LG · math.DS
Fractional partial differential equations describe nonlocal dynamics, but discovering them from noisy data is difficult because fractional differentiation amplifies high-frequency measurement noise and the derivative orders are unknown. We propose Weak-Pareto, which combines an adjoint-consistent weak formulation of fractional terms with Pareto-based subset selection over discrete term types and continuous fractional orders. For linear...
-
56
Sustaining Plasticity via Learnable Wavelet Activations in Continual Learning
Zeyang Zhang, Tieliang Gong, Junyan Lu, Weizhan Zhang
cs.LG
Plasticity loss has emerged as a critical challenge in continual learning that significantly hinders the acquisition of sequential tasks. While optimizing activation designs offers a potential solution, current fixed-form functions suffer from an inherent spectral bias towards low-frequency variations, whereas learnable variants permit unconstrained updates that induce catastrophic forgetting. To address these limitations, we propose a novel...
-
57
A Compositional Theory of Curvature in Probabilistic Circuits
Hrithik Suresh, Sahil Sidheekh, Shelar Parth Vijay, Yasir Z, Sriraam Natarajan, Narayanan Chatapuram Krishnan
cs.LG · cs.AI
Probabilistic Circuits (PCs) are generative models that support exact inference and, unlike deep neural networks, admit an exact and tractable measure of loss-surface curvature: the trace of the Hessian of the log-likelihood. Recent work regularizes this trace globally to bias learning toward flatter, better generalizing optima. We show that treating sharpness as a global regularizer can be misspecified for PCs, whose curvature is inherently...
-
58
Fast A/B/n Testing: Exact Multi-Policy Comparison via Tree-Coupled Feedback Sharing
Yuxiao Wen
cs.LG · cs.AI
Online platforms increasingly compare many adaptive decision policies---ranking systems, recommendation algorithms, pricing rules, and language-model agents---while each reward-bearing interaction can be costly or risky. A direct A/B/n design gives each of $J$ policies its own horizon-$T$ trajectory and therefore uses $JT$ outcomes. We introduce Tree-Coupled A/B Testing (\TCAB), an exact feedback-sharing design for arbitrary history-dependent...
-
59
HiRoute: Hierarchical Routed Prompt Tuning for Safety Alignment of Large Language Models
Fangzhou Chen, Shiji Zhao, Mengyang Wang, Qihui Zhu, Ranjie Duan, Maoxun Yuan, Xingxing Wei
cs.LG
Large language models (LLMs) remain vulnerable to harmful requests and jailbreak attacks. Parameter-efficient safety alignment methods based on prompt tuning typically rely on a single global prompt or externally selected prompt modules. Such static designs struggle to maintain a cross-category safety boundary while generating constructive responses tailored to specific risks and avoiding over-refusal of benign inputs. To address these...
-
60
CoMedBench: A Multi-Source Benchmark of Synthetic Medical Data Fidelity and Downstream Utility
Akanta Das, Al Amin Farhad, Mrinmoy Sarkar Anto, David Rehkopf, Ayin Vala, Tanmoy Sarkar Pias
cs.LG
Access to clinical data is essential for developing reliable healthcare machine learning systems, but direct use of electronic health records is constrained by privacy regulation, institutional review, data-use agreements, and the risk of re-identification. Synthetic data promises a practical alternative: it can preserve useful statistical and clinical structure while reducing exposure of sensitive patient records. Prior studies often...
-
61
Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents
Haoze Wu, Chuqiao Kuang, Tianyi Zhuang, Xiaoguang Li
cs.LG · cs.AI
Deep search agents operate over trajectories spanning dozens of steps, yet standard reinforcement learning provides only a single outcome reward per trajectory, which is far too sparse for effective credit assignment. On-policy self-distillation (OPSD) addresses this by using the model's own logits as dense token-level teachers, but extending it to search agents introduces a fundamental tension: the teacher, having access to privileged...
-
62
Decentralized Multi-Player Q-Learning in Episodic Markov Decision Processes with Information Asymmetry
Larissa Xu, King Bi, William Chang
cs.LG
We study decentralized multi-player reinforcement learning in episodic tabular Markov decision processes (MDPs) under three forms of information asymmetry: (A) unobserved actions with common rewards, (B) observed actions with independent rewards, and (C) unobserved actions with independent rewards. Players cannot communicate during learning but may agree on a protocol a priori. For Problems A and B we propose \texttt{mQ-learning} 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.