cs.LG · 2026-08-17 · No. 87

Machine Learning, 2026-08-17.

58 new papers in cs.LG. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

58 entries
  1. 01

    RecipeNet: A Hierarchical Transformer for Recipe Data

    Pin-Yen Huang, Sachin Chhabra, Prasanth Sai Gouripeddi, Abhinav Kumar, Baoxin Li

    cs.LG · cs.AI

    Recipe data arises in domains such as materials synthesis, pharmaceutical formulation, and industrial manufacturing, where procedures are represented as ordered sequences of steps containing heterogeneous structured fields. Existing tabular learning methods typically flatten this structure into fixed-schema representations, limiting their ability to capture hierarchical field interactions and procedural dependencies. We propose RecipeNet, a...

    arxiv.org/abs/2608.14505 · PDF

  2. 02

    Rollplex: Cross-Phase GPU Spatial Sharing for Vision Language Model Post-Training

    Hanfeng Lu, Tianyu Feng, Suyi Li, Yuheng Zhao, Wei Gao, Shaopan Xiong, Ju Huang, Siran Yang, Jiamang Wang, Lin Qu, Wei Wang

    cs.LG · cs.DC

    Vision-language models (VLMs) enable embodied agents to reason and act from visual observations and language instructions. Reinforcement learning (RL) post-training enhances these capabilities using task feedback, but current on-policy RL runtimes execute rollout, reference scoring, and actor training in strict serial phases. While effective for text-only RL, this phase-granular execution is wasteful for VLMs, where processing dense video...

    arxiv.org/abs/2608.14498 · PDF

  3. 03

    Generating Benchmark Health Data Using a Tabular Diffusion Transformer

    Hao Yan, Lisa Pilgram, Dan Liu, Linglong Kong, Fida Dankar, Khaled El Emam

    cs.LG · cs.AI

    Cross-Tabular Data Generation (CTDG) seeks to learn a generative model from multiple heterogeneous tables and produce new synthetic tabular datasets. However, existing synthetic tabular data generation methods are largely restricted to single-input-table scenarios and struggle to effectively handle multiple heterogeneous tables with diverse feature sets. To address this limitation, we propose a two-stage framework for cross-tabular data...

    arxiv.org/abs/2608.14496 · PDF

  4. 04

    Approximate Muon with low-rank adapters

    Ben Anson, Conor Houghton, Edward Milsom

    cs.LG

    The Muon optimizer shows clear benefits versus alternatives when pretraining neural networks. However, it is used less frequently for parameter-efficient fine-tuning (PEFT). One potential reason is that the most common PEFT method, LoRA, does not naturally combine with Muon since it is not mathematically possible to orthogonalize the weight update given by a low-rank parameterization. In this paper, we address this issue by approximating the...

    arxiv.org/abs/2608.14492 · PDF

  5. 05

    LP-NAS: Linear Programming-based Neural Architecture Search

    Abhishek Shukla, Ankur Sinha, Faiz Hamid

    cs.LG · cs.AI

    Neural Architecture Search (NAS) aims to automate neural network architecture design, reducing reliance on human expertise. Among the various NAS methods, differentiable NAS has gained prominence due to its efficiency and accuracy compared to conventional NAS approaches. Since differentiable NAS relaxes the architecture search space into a continuous domain, it is possible to apply principles from continuous optimization to NAS. In this...

    arxiv.org/abs/2608.14472 · PDF

  6. 06

    Designing Compact Neural Architectures via Neuron Gating and Mixed Activation

    Abhishek Shukla, Ankur Sinha, Faiz Hamid

    cs.LG · cs.AI

    Neural Architecture Search (NAS) is naturally formulated as a bilevel optimization problem, where the upper-level optimizes the architecture using validation performance and the lower-level trains network parameters using training loss. However, NAS is computationally expensive due to discrete architectural decisions, exponentially growing search spaces, and the high cost of training candidate architectures. This work develops a general...

    arxiv.org/abs/2608.14443 · PDF

  7. 07

    Designing Reinforcement Learning for Diffusion Models: A Unified Path-Space View

    Yixian Xu, Yuanrui Zhang, Shengjie Luo, Liwei Wang, Di He

    cs.LG · cs.CV · stat.ML

    Reinforcement learning (RL) post-training provides a direct way to align diffusion models with human preferences and task-specific rewards. However, current RL algorithms for diffusion models remain fragmented: reverse-trajectory methods rely on discretized likelihood ratios, whereas forward-matching methods train on reward-labeled noising versions of the rollout samples. This paper shows that these seemingly different losses arise from a...

    arxiv.org/abs/2608.14430 · PDF

  8. 08

    More Correct Mass, Worse Answers: Why Power Sampling Can Fail and How to Fix It

    Haohui Yang, Jiaxing Sun, Xiujun Ma

    cs.LG

    Power Sampling sharpens a language model's distribution over complete generation trajectories, offering a verifier-free way to improve reasoning at inference time. It also has the potential to serve as a general-purpose front end for a broad range of downstream sampling methods. However, we uncover a striking paradox: Power Sampling can drive more probability mass toward correct trajectories while degrading the downstream inference it is...

    arxiv.org/abs/2608.14420 · PDF

  9. 09

    CytoBERT: A Foundation Model for Cytometry Data

    Syed Abdul Haseeb Qadri, Bjarne C. Hiller, Felix Blanke, Vanja Sophie Cangalovic, Kutalmış Coşkun, Amin Mirzaei, Tom...

    cs.LG

    Cytometry measures the complex characteristics of single cells (e.g., counts and protein expression of immune cells) and is widely used across immunological research and clinical settings. However, cytometry data is highly heterogeneous and unstandardized due to experimental protocols and the choice of measured features. While machine learning methods hold the potential to gain deeper insights into cell biology, these challenges make them...

    arxiv.org/abs/2608.14414 · PDF

  10. 10

    DeaMoE: Efficient MoE Structure for Fast Small-Batch Decoding

    Zewen Jin, Shen Fu, Zeping Duan, Shannon Wang, Weihao Wu, Chengjie Tang, Congkun Ai, Ping Gong, Zijian Dai, Youhui...

    cs.LG · cs.AI

    Mixture-of-Experts (MoE) models have been widely adopted in real-time interactive applications such as coding assistants, real-time audio-video interaction systems. To meet the extremely low response latency requirements of these scenarios, practitioners commonly employ small-batch decoding, under which MoE inference becomes memory-bound and is severely bottlenecked by expert weight loading. However, this bottleneck has received limited...

    arxiv.org/abs/2608.14385 · PDF

  11. 11

    Boosting Data Augmentation with Stochastic Weight Averaging

    Longde Huang, Axel Flinth, Jan E. Gerken

    cs.LG

    The symmetries of a learning task have become an important factor in designing modern deep learning solutions. Data augmentation is a straightforward and effective way of incorporating symmetries into a generic neural network. Recent results show that infinitely large deep ensembles show perfect symmetry when trained on augmented data. However, since training ensembles requires repeating the training process many times, this method is costly....

    arxiv.org/abs/2608.14373 · PDF

  12. 12

    Catching the Imposter: Self-Supervised Learning of Physical Coherence with Cross-Entity Feature Permutations

    Aleksei Rozanov, Arvind Renganathan, Vipin Kumar

    cs.LG

    Scientific data often describe entities whose features are jointly governed by the laws of physics, yet existing self-supervised learning (SSL) objectives largely ignore this physical coherence. We introduce imposter, a discriminative pretext task that replaces subsets of an entity's features with real observations donated by another entity and trains the encoder to identify the swapped features. Because every donated value is individually...

    arxiv.org/abs/2608.14372 · PDF

  13. 13

    Mind the Long Tail: Understanding the Difficulty of Delay Detection in Business Processes

    Keyvan Amiri Elyasi, Lukas Kirchdorfer, Heiner Stuckenschmidt

    cs.LG · cs.AI

    The early detection of delayed cases in business processes is a critical capability for organizations. Predictive process monitoring (PPM) supports this task by using historical event logs to predict the remaining time of ongoing cases, enabling timely interventions to avoid missed deadlines and service level violations. Although remaining time prediction has advanced considerably through sophisticated deep learning architectures, little is...

    arxiv.org/abs/2608.14367 · PDF

  14. 14

    Non-Parametric Spatiotemporal Trajectory Prediction via State-Conditioned Transition Sampling

    Michael Fore, Akshay Jain, Justin Downes, Rohan Pradhan, Duncan Botti

    cs.LG

    We present a training-free method for multi-modal trajectory prediction that achieves comparable accuracy to a 57M-parameter transformer while requiring no GPU and zero learned parameters. The method builds a transition table of historical state-to-next-position pairs and retrieves neighbors using a product kernel over spatial proximity, bearing, speed, and temporal context. Two inference modes operate over this shared representation:...

    arxiv.org/abs/2608.14349 · PDF

  15. 15

    Quantum Multi-Armed Bandits and Linear Bandits: Lower Bounds and Algorithms

    Maoli Liu, Zhuohua Li, John C. S. Lui

    cs.LG · quant-ph

    We study quantum multi-armed bandits (QMAB) and quantum linear bandits (QLB) in the model of Wan et al. [2023], where the learner queries each arm or action through a quantum reward oracle or its inverse. Prior work gives algorithms over horizon $T$ with regret $O(K\log T)$ for QMAB with $K$ arms and $O(d^2\operatorname{polylog} T)$ for $d$-dimensional QLB. This leaves open whether the $K\log T$ scale is unavoidable and whether the $d^2$...

    arxiv.org/abs/2608.14319 · PDF

  16. 16

    Detecting Contaminated Code-Generation Prompt Batches via Influence Functions

    Francesco Quinzan, Noor Munir, Yishun Lu, Stephen Roberts

    cs.LG

    Large language models (LLMs) are increasingly used for code generation, yet they remain vulnerable to prompts that elicit insecure implementations. Existing defenses typically rely on predefined threat models or known vulnerability patterns, limiting their effectiveness against novel attacks. We propose CodeSIFT, a threat-model-agnostic detection method that leverages influence functions to identify batches of prompts that induce anomalous...

    arxiv.org/abs/2608.14303 · PDF

  17. 17

    Convex losses and their applications to SVM, SVR, and Shallow Neural Networks

    Filippo Portera

    cs.LG

    We propose multiple new convex losses for SVM and Neural Networks, applied to binary classification tasks. While there are practical limitations in exploiting them with the dual SVM models, we are able to use them with SVM primal formulation and Neural Networks. In detail, the primal SVM problem with the modified losses has been solved with the Particle Swarm Optimization algorithm. We prove that the proposed losses are a generalization of...

    arxiv.org/abs/2608.14288 · PDF

  18. 18

    Multi-Objective Bayesian Optimization for Model Merging

    Utkarsh Agarwal, Vamshi Bonagiri, Raul Astudillo, Monojit Choudhury

    cs.LG · cs.AI

    Model merging combines trained models directly in weight space, offering a compute-efficient alternative to additional fine-tuning. Selecting merge parameters is nevertheless difficult because downstream evaluations are expensive, gradients are unavailable, and source capabilities can conflict. We formulate merge-parameter selection as a black-box multi-objective optimization problem and introduce MOBO-Merge, a merge-operator agnostic...

    arxiv.org/abs/2608.14264 · PDF

  19. 19

    AutoSchema: Live Schema Grounding for Agentic Text-to-Sparql over Heterogeneous Knowledge Graphs

    Yiming Zhang, Koji Tsuda

    cs.LG

    Life science knowledge graphs make large collections of structured data available through SPARQL, but each resource uses its own schema, identifiers, and links. TogoMCP helps language model agents query these resources by providing curated Metadata Interoperability Exchange files. Creating and maintaining these files still requires language model assisted drafting, validation, and manual review. We study \emph{live schema grounding}, where an...

    arxiv.org/abs/2608.14228 · PDF

  20. 20

    Connected Subspace Clustering: Hardness, a Scalable Heuristic, and an Application to Sea Level Geodesy

    Johanna Hillebrand, Jan Höckendorff, Jürgen Kusche, Kelin Luo, Heiko Röglin, Melanie Schmidt, Christian Sohler, Bernd Uebbing

    cs.LG

    Constrained optimization extends classical optimization by integrating side information, making it widely applicable across scientific and engineering domains. Consider a setting where we measure variables at different physical locations. When grouping these measurements, we often want clusters that are both internally similar and physically coherent. Thus, we have a constrained clustering problem where the constraint models coherence....

    arxiv.org/abs/2608.14215 · PDF

  21. 21

    Training Fair Tabular Foundation Models

    Patrik Kenfack, Jesse C. Cresswell, Anthony L. Caterini, Samira Ebrahimi Kahou, Ulrich Aïvodji

    cs.LG · cs.AI

    Tabular Foundation Models (TFMs) have emerged as leading methods for tabular predictive tasks, leveraging in-context learning to predict on new data without task-specific training. Despite the increased use of TFMs in high-stakes decision-making, their fairness properties remain largely unexplored. In this work, we incorporate fairness constraints directly into TFM training, enabling fair predictions in a single forward pass. Our approach...

    arxiv.org/abs/2608.14211 · PDF

  22. 22

    Adaptive Protection for Evolutionary Feature Construction in Symbolic Regression with Application to Credit Classification

    Hengzhe Zhang, Qi Chen, Bing Xue, Lean Yu, Wolfgang Banzhaf, Mengjie Zhang

    cs.LG · cs.NE

    Evolutionary feature construction has shown strong promise in symbolic regression by automatically discovering informative transformations of input features that enhance a simple base learner. However, existing approaches often lack explicit mechanisms to preserve important constructed features discovered during evolution, and valuable genetic material can be lost when genetic operators disrupt effective features. This paper introduces an...

    arxiv.org/abs/2608.14209 · PDF

  23. 23

    MINT: A Universal Zero-Shot Predictor for Transaction Data

    Parameswaran Kamalaruban, Viktor Drobnyi, Maeve Madigan, Julia Rozanova, David Sutton, Stuart Burrell

    cs.LG · cs.CL

    Banks analyse sequential financial transaction data to perform many tasks, including fraud prevention, credit risk assessment and offer personalization. To improve the predictive accuracy of these tasks, Payments Foundation Models encode transaction sequence data as rich contextual embeddings, which can then be provided to task-specific models as features. However, these Foundation Models are not designed for flexible zero-shot reasoning...

    arxiv.org/abs/2608.14198 · PDF

  24. 24

    KV Cache Compression Through the Lens of Transform Coding

    Hannah Laus, Claudio Mayrink Verdun, Hao Wang, Flavio du Pin Calmon, Felix Krahmer

    cs.LG · cs.CL · eess.SP

    The key-value (KV) cache stores information from past tokens and is a major memory bottleneck in long-context inference. Existing quantization methods address this bottleneck by representing the KV cache uniformly with lower-precision data types and designing quantization schemes to minimize reconstruction error in the cache itself, without accounting for how that error propagates through attention mechanisms. We prove that, under a...

    arxiv.org/abs/2608.14191 · PDF

  25. 25

    Revisiting Energy-based Tabular Anomaly Detection: Energy and Reconstruction are Complementary

    Junichiro Niimi

    cs.LG · stat.ML

    Tabular anomaly detection is dominated by classical density-proxy methods (Isolation Forest, OCSVM, LOF), reconstruction-based detectors (Autoencoders, VAEs), and modern non-parametric scorers (COPOD, ECOD, Deep SVDD), all of which approximate the inlier distribution only indirectly; explicit energy-based models are largely absent. Motivated by the recent revival of EBMs in deep learning (e.g., Energy-Based Transformers, JEPA), we revisit the...

    arxiv.org/abs/2608.14186 · PDF

  26. 26

    Structure-Guided Spatiotemporal Attention Graph Neural Network for Traffic Flow Prediction

    Xuanmian He, Can Li, Wanjing Ma

    cs.LG · cs.AI

    Deep spatiotemporal models integrating graph convolutions and attention mechanisms have demonstrated excellent performance in network-level traffic flow prediction, owing to their exceptional ability to capture complex spatiotemporal dependencies. Despite their predictive success, deployment of such models in safety-critical urban systems remains constrained by their inherent lack of transparency. Existing post-hoc diagnostic methods often...

    arxiv.org/abs/2608.14177 · PDF

  27. 27

    Deep Reinforcement Learning solution for pickup and delivery routing problems with time window and capacity constraints

    Andrew Soroka, Alex Meshcheryakov, Sergey Gerasimov

    cs.LG

    The task of constructing vehicles optimal routes for pickup and delivery of goods is one of most promising tasks in the context of global urban population growth. Although this kind of problems with small size can be solved by various classical approaches, a fast (or realtime) route optimizer under the constraints of the real world (such as capacity and time windows constraints) for medium-large size problems still remains a highly...

    arxiv.org/abs/2608.14156 · PDF

  28. 28

    Smart routes: a system for development and comparison of algorithms for solving vehicle routing problems with realistic constraints

    Andrew Soroka, German Mikhelson, Alexander Mescheryakov, Sergey Gerasimov

    cs.LG

    The problem of route optimization with realistic constraints is becoming extremely relevant in the face of global urban population growth. While we are aware of approaches that theoretically provide an exact optimal solution, their application becomes challenging as the problem size increases because of exponential complexity. We investigate the Capacitated Vehicle Routing Problem with Time Windows (CVRPTW) and compare solutions obtaining by...

    arxiv.org/abs/2608.14140 · PDF

  29. 29

    Overcoming Shortcut Learning in Graph Neural Networks through Active Explanation Guidance

    Taraneh Younesian, Steve Azzolin, Antonio Longa, Francesco Ferrini, Vincenzo Marco De Luca, Stefano Teso

    cs.LG · cs.AI

    Graph Neural Networks (GNNs) can solve prediction tasks by unintentionally exploiting shortcuts---that is, edges, nodes, and features that correlate with but are not causal for the prediction---which compromise their reliability in out-of-distribution tasks. We introduce XIGL, an architecture-agnostic human-in-the-loop strategy for removing such shortcuts from GNNs. Our key insight is twofold. On the one hand, reliance on shortcuts can be...

    arxiv.org/abs/2608.14121 · PDF

  30. 30

    From Fixed Grids to Moving Particles:A Transferable Latent Operator for Fluid Dynamics

    Meng Li, Chuqi Chen, Zhengqing Gao, Xi Zhou, Xiao Sun, Yang Xiang, Huaxi Huang

    cs.LG · cs.AI · cs.GR

    Lagrangian modeling is vital to fluid dynamics, as it characterizes particle transport and complements the Eulerian description.However, Lagrangian trajectories are less commonly available than Eulerian fields, while most neural operators are trained and evaluated primarily in the Eulerian representation. This mismatch motivates a new learning problem: can a model trained solely on Eulerian observations generalize zero-shot from Eulerian...

    arxiv.org/abs/2608.14120 · PDF

  31. 31

    Learning to Run Power Networks: Effective AlphaZero-inspired Topological Control

    Lukas Zetto, Benjamin Schäfer, Qiong Huang

    cs.LG

    As the integration of volatile renewable energy sources increases the strain on modern power grids, the use of Reinforcement Learning (RL) for autonomous topological reconfiguration has emerged as a promising research field to keep strained grids stable and operational. Compared to traditional redispatching measures, topological actions offer a cheaper and more cost-effective way to manage grid congestion. However, their implementation is...

    arxiv.org/abs/2608.14114 · PDF

  32. 32

    Forecast Collapse in Time-Series Foundation Models

    Shu Wan, Miles Ma, Hank Zhu, Guangqi Liu, Stephen Wang, Qingsong Wen, Huan Liu

    cs.LG · cs.AI · cs.CE · stat.AP · stat.ML

    When forecasting hourly returns for 1,000 US equities, we observe an unexpected phenomenon: predictions become nearly flat and show poor stock ranking, as measured by cross-sectional correlation. We call this forecast collapse. Surprisingly, the phenomenon largely disappears when forecasting trading volume under the same setting. We investigate forecast collapse across time-series foundation models (TSFMs), twelve deep-learning forecasting...

    arxiv.org/abs/2608.14106 · PDF

  33. 33

    Sequence prediction under a lying oracle

    Puspabeethi Samanta, Nikhil Karamchandani, Jayakrishnan Nair

    cs.LG · cs.IT

    We consider the problem of sequential prediction of an $m$-ary sequence, where at each epoch, (i) the environment selects an outcome from an $m$-ary alphabet, (ii) the learner selects a probability distribution over the same alphabet (unaware of the outcome generated by the environment), and finally, (iii) the learner incurs a cost that depends on the probability assigned to the outcome. The cost function we consider captures the complexity...

    arxiv.org/abs/2608.14102 · PDF

  34. 34

    Resource-Adaptive Primal-Dual Learning for One-Warehouse Multi-Store Systems with Censored Demand

    Jiameng Lyu

    cs.LG · math.OC

    The one-warehouse multi-store (OWMS) system is a fundamental inventory network in which a nonreplenishable warehouse allocates shared stock across multiple stores over time. Existing OWMS learning policies are built around a fixed target calibrated to the initial average resource rate, but such a fixed-target architecture cannot re-center after realized sales change the remaining resource available per future period. We develop...

    arxiv.org/abs/2608.14096 · PDF

  35. 35

    When Denoising Hurts: Rethinking the Terminal Step of Diffusion Time Series Forecasters -- Extended Version

    Dat Nguyen-Cong, Luong Tran, Tung Kieu

    cs.LG

    Diffusion models offer a natural way to model uncertainty in time series forecasting, yet their iterative sampling process is often treated as a uniformly beneficial refinement procedure. Our study challenges this view by examining how forecast quality evolves throughout reverse diffusion. We find that general temporal structure is often recovered at relatively high noise levels, whereas continued low-noise refinement can introduce...

    arxiv.org/abs/2608.14067 · PDF

  36. 36

    Model-agnostic Retrieval-Augmented Extended Forecasting for time series

    Juan Pablo Villa Serna, Rohan Asthana, Vasileios Belagiannis

    cs.LG

    Time series forecasting with pretrained foundation models has demonstrated strong zero-shot capabilities. However, achieving optimal performance on time series with short or negligible historical data in domain-specific applications typically requires adaptation via either fine-tuning or RAG. While fine-tuning is effective, it incurs substantial computational costs. This work explores RAG within univariate time series (Retrieval Augmented...

    arxiv.org/abs/2608.14054 · PDF

  37. 37

    Adversarial Learning of Classifier-Free Guidance Schedules

    Ashwini Pokle, Alexandre Galashov, Arnaud Doucet, Mauricio Delbracio, Valentin De Bortoli

    cs.LG

    Modern text-to-image diffusion models rely on classifier-free guidance (CFG) to achieve high image fidelity and text alignment. However, CFG typically applies a static, global scale across all timesteps, samples, and conditions -- a choice that is generally suboptimal and can introduce artifacts, as different states may benefit from different levels of guidance. While time-varying schedules are known to improve quality, designing them by hand...

    arxiv.org/abs/2608.14038 · PDF

  38. 38

    When Does More Correct Data Hurt? Insertion-Stability and the Limits of Dimension-Based Theory

    Joseph Sankoorikal Johny

    cs.LG · stat.ML

    Adding data known to be correct ought to be safe. Not always. Larsen, Pabbaraju and Shetty model the failure with a monotone adversary, which reads an i.i.d. training sample and may append as many further examples as it likes, provided the target hypothesis labels them all. Mehrotra has since settled the cost, showing that for classes of VC dimension d >= 2 no learner can guarantee expected error better than Theta((d/n)log(en/d)), a...

    arxiv.org/abs/2608.14020 · PDF

  39. 39

    Identifiability and Order-Dimension Limits of In-Context Learning on Partial Orders

    Faizanuddin Ansari, Debanjan Dutta, Swagatam Das

    cs.LG

    In-context learning is commonly formalized as inference from examples of a function. Partial orders instead combine transitivity, antisymmetry, and incomparability, so a finite prompt may not determine a queried comparison. We develop a theory of in-context learning on partial orders that separates logical identifiability, prompt teaching cost, structural complexity, and the exact capacity of a formal coordinate-decoder class. A version-space...

    arxiv.org/abs/2608.14004 · PDF

  40. 40

    QUASAR: Lowering the Loss Floor of Quantization-Aware Training with Loss-Aware Reconstruction

    Vincent Counathe, Ben Athiwaratkun, Christopher De Sa, Tianyi Zhang

    cs.LG · cs.CL · stat.ML

    As large language model inference shifts toward lower precision, post-training quantization (PTQ) becomes increasingly brittle, making quantization-aware training (QAT) essential for preserving model quality. However, QAT computes the loss and surrogate gradients using a lossy reconstruction of latent full-precision weights, while applying updates to the latent weights themselves. This mismatch can lead to suboptimal training trajectories and...

    arxiv.org/abs/2608.13966 · PDF

  41. 41

    Polar Code Based Federated Learning: Convergence Analysis and Resource Allocation

    Han Xiao, Wei Kang, Nan Liu

    cs.LG

    Federated learning (FL) enables collaborative model training across distributed devices without sharing raw data; however, it faces significant communication bottlenecks and channel impairments in practice. Conventional network layer treatments either idealize the channel as error free or apply equal error protection (EEP) to transmitted model updates, failing to account for the inherently unequal importance of quantization bits within a...

    arxiv.org/abs/2608.13961 · PDF

  42. 42

    Probabilistic indirect models for undrained shear strength: addressing significant data missing and variability with advanced imputation and machine learning techniques

    Haibin Xiong, Shaoheng Dai, Peng Lan, Xuzhen He, Chenxi Tong, Sheng Zhang, Daichao Sheng

    cs.LG · cs.DB

    Accurate prediction of undrained shear strength (su) is crucial for geotechnical design, but is often hampered by substantial uncertainty in traditional empirical methods. This study uses the CLAY/10/7490 global database to develop probabilistic indirect models to predict su based on Atterberg limits and piezocone cone penetration (CPTU) measurements. Firstly, the dataset has a high missing data rate and variability. We test three imputation...

    arxiv.org/abs/2608.13934 · PDF

  43. 43

    Post-training Quantization for Hybrid Iterative Generative Models

    Jing Gao, Junyi Wu, Wei Wang, Yan Yan, Yao Zhao

    cs.LG

    Iterative Generative Models (IGMs) span autoregressive and diffusion paradigms, and hybrid variants that couple them can achieve remarkable image-generation fidelity. However, their iterative inference incurs substantial computational overhead, making Post-training Quantization (PTQ) appealing for acceleration, while directly applying vanilla PTQ to hybrid IGMs can trigger model collapse. By analyzing these failures, we identify two critical...

    arxiv.org/abs/2608.13932 · PDF

  44. 44

    CForce: Boosting Parallel Decoding for dLLMs via Consistency Forcing

    Yuji Ren, Chenkai Xu, Zhuocheng Gong, Jianguo Li, Zhijie Deng

    cs.LG · cs.AI · cs.CL

    Diffusion large language models (dLLMs) accelerate language generation by predicting multiple masks in a single forward pass. However, existing dLLMs can suffer from unreliable predictions in early denoising stages under aggressive parallelism strategies, leading to errors that can propagate to later stages. To tackle this issue, we present Consistency Forcing (CForce) for dLLMs, a distillation method to force the mask predictions of early...

    arxiv.org/abs/2608.13925 · PDF

  45. 45

    High-dimensional nonparametric changepoint detection via low-rank degree-two density projection

    Guoqing Zhang, Zhaixin Chen

    cs.LG · stat.ML

    Detecting distributional changes in high dimension is difficult when neither the pre-change nor post-change density is parametrically specified. We introduce a representation-based approach that retains all degree-at-most-two density information while replacing density estimation by matrix mean estimation. For observations in $[-1,1]^d$, a symmetric feature matrix $H_2(X)\in\R^{(d+1)\times(d+1)}$ is constructed so that $M(f)=\E_f H_2(X)$ is...

    arxiv.org/abs/2608.13922 · PDF

  46. 46

    Hybrid Quantum-inspired Kolmogorov-Arnold Networks for Privacy-Aware Federated Biosignal Learning

    Chun-Hua Lin, Samuel Yen-Chi Chen, Yu-Chao Hsu, Kuo-Chung Peng, Jiun-Cheng Jiang, Chi-Sheng Chen, Tai-Yue Li,...

    cs.LG · cs.AI · cs.DC · cs.ET · quant-ph

    Electrocardiogram (ECG) recordings are sensitive biomedical data, limiting the ability of hospitals and wearable devices to share raw signals for centralized model training. Federated learning addresses this practical privacy constraint by enabling collaborative model training while keeping raw biosignal data at their respective sources. However, federated ECG classification remains challenging due to limited client-side samples, imbalanced...

    arxiv.org/abs/2608.13914 · PDF

  47. 47

    MedMix: Specialization-Consistent Federated Sparse MoEs under Modality Heterogeneity

    Adiba Orzikulova, Dong Min Kim, Jaehong Yoon, Sung-Ju Lee

    cs.LG

    Federated multimodal medical AI faces modality heterogeneity at both the client and sample levels: clients may systematically lack access to specific modality types, while individual records within the same client may contain different partial modality subsets. Sparse Mixture-of-Experts (MoE) architectures are a promising remedy for modality-adaptive computation, but their use in federated learning is fragile under cross-client modality...

    arxiv.org/abs/2608.13911 · PDF

  48. 48

    Fashion Outfit Generation via Unified Sequential Composition Models

    Kaicheng Pang, Xingxing Zou, Ruohan Xu, Waikeung Wong

    cs.LG

    The task of synthesizing stylistically coherent fashion outfits from massive item libraries, known as fashion outfit generation, remains a non-trivial challenge, primarily due to the non-monotonic and implicit nature of aesthetic compatibility, coupled with the exponentially large combinatorial search space. In this paper, we formalize this task as Constrained Ensemble Generation (CEG) and model it as a finite-horizon deterministic Markov...

    arxiv.org/abs/2608.13888 · PDF

  49. 49

    Variation Brownian Kernel Ladders

    Mahdi Mohammadigohari

    cs.LG

    Claims about the benefit of depth depend on the complexity assigned to a representation. We introduce the \emph{Variation Brownian Kernel Ladder} (VBKL), a path-atomic function-space framework that separates nonlinear recursive dictionary construction from linear variation superposition. Starting from linear projections, each atom recursively composes unit-ball profiles from the Brownian reproducing kernel Hilbert space; the full VBKL space...

    arxiv.org/abs/2608.13882 · PDF

  50. 50

    Geometric Filtering of LLM-Generated Samples for Few-Shot Text Classification

    Benjamín Schindler, Gonzalo A. Ruz

    cs.LG · cs.CL

    Large language models (LLMs) can generate synthetic training data for text classification, but the quality of generated samples is heterogeneous: some fall in correct class regions of the embedding space while others land in peripheral or cross-class zones. We propose a geometric filtering framework that evaluates each LLM-generated sample by its Euclidean distance to real class examples in a sentence embedding space, selecting only...

    arxiv.org/abs/2608.13866 · PDF

  51. 51

    Federated Prompt Learning: A Unified Framework, Empirical Analysis, and Future Directions

    Qinglin Yang, Chen Qiu, Hongyuan Zhang, Pengdeng Li, Yuan Liu, Zhihong Tian

    cs.LG · cs.AI · cs.DC

    Large language models (LLMs) have become core components of cloud-based intelligent services in academia and industry, yet their training and deployment are hindered by high computational costs, data centralization, and privacy concerns. Federated learning (FL) offers a decentralized training paradigm that enables clients to collaboratively train a learning model without sharing raw data, making it a promising solution for privacy-preserving...

    arxiv.org/abs/2608.13844 · PDF

  52. 52

    HI-MeshGraphNets: Efficient and Accurate Mesh-based Physics Learning with Hierarchical Multi-scale Graph Neural Networks

    SiHun Lee, Dong-Hyuk Park, Taesoo Bang, Seung-Hoon Kang

    cs.LG

    Machine-learned physical surrogate models have become promising alternatives to mesh-based numerical solvers. Among them, graph neural networks (GNNs) are well suited for representing simulation meshes and learning nodal state evolution through message passing. However, conventional flat message passing becomes inefficient on large, high-fidelity meshes because information propagates only one hop per layer, requiring deep processors for...

    arxiv.org/abs/2608.13827 · PDF

  53. 53

    Stochastic Control Policies for Robust Molecular Transition Path Sampling

    Jingqian Liu, Yu-Hsiang Wang, Yanru Qu, Ge Liu

    cs.LG

    Transition path sampling (TPS) aims to efficiently generate rare molecular transition trajectories between metastable states and is essential for understanding biomolecular mechanisms. Beyond traditional molecular dynamics (MD)-based sampling, machine learning has become central to state-of-the-art TPS. One major class of methods learns control forces during explicit MD rollouts. By preserving the underlying molecular dynamics, these methods...

    arxiv.org/abs/2608.13800 · PDF

  54. 54

    Dynamic Multi-Depot Vehicle Routing with Online Requests: Event-Driven Transformer--DRL and Rolling-Horizon Benchmarking

    Faezeh Ardali, Gerald M. Knapp

    cs.LG

    This paper presents an event-driven learning and benchmarking framework for the Dynamic Multi-Depot Vehicle Routing Problem with progressively revealed requests and evolving vehicle states. Masked MLP and Transformer policies are trained through behavior cloning and proximal policy optimization. Deterministic feasibility masking prevents invalid vehicle--request assignments, while fixed-prefix/flexible-suffix route commitments protect...

    arxiv.org/abs/2608.13799 · PDF

  55. 55

    Recent Advances in Deep Learning-Based Drug-Target Binding Affinity Prediction

    Jafin Khan, Md Hossain Shuvo

    cs.LG

    Computational approaches to drug discovery involve multiple sub-problems, and among them, drug-target binding affinity prediction plays an important role. Despite recent advances, accurately predicting binding affinity remains an open research area. The major objective of our paper is to perform a comprehensive review and comparative analysis of recent machine learning methods for drug-target binding affinity prediction, with a focus on...

    arxiv.org/abs/2608.13797 · PDF

  56. 56

    PPAPlace: Differentiable Cross-Stage Objectives for Chip Placement Optimization

    Ruogu Chen, Jie Han

    cs.LG · cs.AI · cs.AR

    Macro placement significantly affects a chip's post-route performance, power, and area (PPA). Most placement methods optimize half-perimeter wirelength (HPWL) as the primary objective. However, recent benchmarking shows a near-zero correlation between HPWL and post-route timing metrics such as the worst negative slack (WNS) and total negative slack (TNS). As a result, all six evaluated artificial intelligence (AI) placers degraded PPA...

    arxiv.org/abs/2608.13790 · PDF

  57. 57

    CutClean: Neural Network Pruning for Privacy-Preserving Inference

    Leonardo Magliolo, Vito Paolo Pastore, Giuseppe Valenzise, Enzo Tartaglione

    cs.LG · cs.AI

    Neural networks are increasingly deployed in high-stakes applications with growing privacy leakage concerns. We show that this privacy leakage can occur even in the absence of representation imbalances that lead to traditional dataset biases. This poses significant privacy risks when deploying models that process sensitive attributes. In this context, we propose CutClean, a privacy-aware pruning method that allows to reduce privacy...

    arxiv.org/abs/2608.13773 · PDF

  58. 58

    The Integer Alibi: Localizing Cross-Kernel Divergence in INT8-Quantized LLM Inference

    Teng-Ruei Chen

    cs.LG

    Two GPU kernels implementing the same scaled INT8 GEMM interface are usually treated as interchangeable. We test that assumption: holding the checkpoint, prompts, hardware, inference engine, decoding, and quantization configuration fixed, we swap only the INT8 linear kernel (CUTLASS versus Triton) inside vLLM. At 1.7B each arm reproduces itself bit-for-bit across cold restarts, yet the arms agree on no sequence in any end-to-end comparison we...

    arxiv.org/abs/2608.13756 · PDF

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.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.