cs.LG · 2026-08-30 · No. 100
Machine Learning, 2026-08-30.
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-
01
Understanding Evolution Strategies for LLM Reasoning: Broader Reasoning Coverage than GRPO
Yunpeng Ba, Zhi Zheng, Yue Xie, Jiaqing Li, Xialiang Tong, Tao Zhong, Mingxuan Yuan, Zhichao Lu, Xuyang Wu, Zhenkun Wang
cs.LG
Evolution Strategies (ES) have recently emerged as a memory-efficient post-training paradigm for LLM reasoning. However, the optimization behavior of ES remains understudied, making it hard to define its advantage scope compared to mainstream post-training paradigms (e.g., Group Relative Policy Optimization (GRPO)). By systematically investigating ES dynamics and mechanisms, this paper first identifies a performance advantage of ES over GRPO,...
-
02
Beyond Parallel Blindness: Information Floors and Model Gaps in Block Drafting
Xinwei Qiang, Xiang Fang, Chang Chen, Yue Guan, Yufei Ding
cs.LG · cs.CL · cs.IT
Block drafters propose several tokens in one forward pass, before earlier target tokens are realised. Their rejection mixes two losses: missing within-block path information and imperfect modelling of observable information. Accepted length cannot distinguish them. We separate the two with an information floor, the minimum expected rejection at a specified conditioning order; rejection above this floor is the model gap. Estimating both from...
-
03
QuantumBoostNet: A Hybrid Classical-Quantum Architecture for Enhanced Accuracy in Cardiac Ultrasound View Identification
Mihai Udrescu-Milosav, Stefan-Alexandru Jura, Mihai Udrescu, Gerhard-Paul Diller
cs.LG
Accurate identification of the correct view or angle in cardiac ultrasound (echocardiogram) is a critical component of cardiologic imaging. This step is essential for precise anatomical interpretation, reliable measurement, and the reduction of clinical errors. Although computer vision has advanced significantly, most state-of-the-art models perform well on standard benchmarks but often yield suboptimal results in specialized medical imaging...
-
04
MM-Spectrum: Multimodal Multi-spectral Molecular Structural Elucidation with a Stable MoE Framework
Hai-tao Yu, Nan Min, Zheng Fang, Hongyu Zhan, Yusen Tan, Yuhan Wang, Jun Xia
cs.LG
Inferring molecular structures from multimodal spectroscopic measurements requires integrating complementary yet highly heterogeneous signals. However, the common paradigm of directly concatenating multispectral sequences can exhibit anomalous performance degradation, primarily due to pronounced heterogeneity and the resulting multimodal imbalance across modalities. As a remedy, we propose MM-Spectrum, a sparse Mixture-of-Experts framework...
-
05
Making Latent Evolution Explicit: Operator-Structured Transitions for World Action Models
Xiaoxiao Lu, Yunlong Dong, Jiahao Shi, Ye Yuan
cs.LG
World Action Models (WAMs) augment robot policies by predicting how task-relevant scene states may evolve under interaction. Recent WAMs increasingly perform such prediction in latent representation spaces, avoiding full appearance-level generation while preserving control-relevant information. Yet latent transitions are commonly realized with Transformer-based predictors whose inductive structure is centered on token interaction rather than...
-
06
Circuit Condensation: Post-Training that Concentrates a Behavior's Causal Circuit
Sai Adith Senthil Kumar
cs.LG
One approach to mechanistic interpretability explains behavior through circuits: the components and connections that carry it. Frozen discovery often returns hundreds of edges, making them hard to inspect, compare, or verify exhaustively. We introduce Circuit Condensation, which post-trains models to concentrate behaviors into smaller causal graphs. Each round prunes low-attribution edges and trains a low-rank adapter to match the original...
-
07
Importance Scoring of Transformer Attention Heads in Learning Tabular Data
Ahmad Jad Allah, Kazi F. Akhter, Md. Kamrozzaman Bhuiyan, Manar D. Samad
cs.LG
Computationally demanding and opaque deep learning models can be better understood and optimized by analyzing how they transform data. While deep transformers have been widely studied in computer vision and natural language processing, their application in tabular data remains relatively underexplored. This paper presents one of the first applications of an importance-scoring metric to interpret multi-head transformer models in learning from...
-
08
HALO: A Heterogeneity-Aware Language-Aligned IMU Foundation Model for Open-Set Human Activity Recognition
Zihan Ding, Liyu Zhang, Xiaomin Ouyang
cs.LG
Human Activity Recognition (HAR) using inertial measurement units (IMUs) enables a wide range of applications, yet the field still lacks a unified model that can generalize across diverse subjects, devices, and activities. Training such a model is difficult due to two key challenges: sensing heterogeneity -- differences in sampling rates, channel configurations, and sensor placements -- and poor generalization to unseen activities and label...
-
09
Profit based evaluation of machine learning for nitrogen recommendations in winter wheat
Xulong Wang, Po Yang
cs.LG
Nitrogen rates for winter wheat are set before the season, under unknown prices and weather. The standard UK advice does not respond to prices, yet recent price swings moved the most profitable rate by tens of kilograms per hectare. Machine learning is often proposed as the fix. However, it is usually judged on prediction accuracy, and accurate prediction does not by itself make the recommended rate more profitable. Our insight is to score...
-
10
Common Geodesics Do Not Guarantee Fisher Consistency of the Structured SVM: Minimal Counterexamples and a Tree-Metric Classification
Jintao Fei, Jiangying Luo
cs.LG
A known necessary condition for Fisher consistency of the structured support vector machine requires the task loss to be a metric for which every output triple has a common geodesic point. We show that this condition is not sufficient for the canonical coordinate-wise argmax decoder. A four-output unit star admits an exactly optimal score vector whose maximizers are all strictly non-Bayes, and four outputs are minimal among metrics satisfying...
-
11
When Interference Graphs Evolve: Doubly Robust Estimation of Dynamic Peer Effects
Xiaojing Du
cs.LG · cs.SI
Peer effects are difficult to estimate when interaction graphs evolve because pre-assignment network history, dynamic peer exposure, and post-assignment network change have distinct causal roles. We introduce a controlled contrast framework that indexes potential outcomes by own treatment, temporally aggregated peer exposure, and a post-assignment evolution summary. Differences between the resulting means define own-treatment, peer-exposure,...
-
12
TraceBench: Controlled Evaluation of LLM Agents for Time-Series Root-Cause Attribution
Tommaso Bendinelli, Artur Dox, Christian Holz
cs.LG
LLM agents are increasingly applied to anomaly detection and root-cause analysis in time-series observations collected from real-world systems; however, their performance on these tasks has not been systematically evaluated under controlled conditions. We introduce TraceBench, a simulation-based framework for generating controlled root-cause attribution tasks. In each generated task, an agent receives time-series observations produced by...
-
13
Diffusion Policies for Short-Horizon Planning in Robot Crowd Navigation
Wendong Li, Jochen Garcke
cs.LG
Robot crowd navigation requires safe and efficient decision-making under dense, dynamic, and multimodal human--robot interactions. Existing reinforcement-learning methods typically output a single reactive action at each timestep, which limits their ability to represent diverse short-term avoidance strategies. We propose Planning Diffusion Policy Optimization (PDPO), an offline-to-online reinforcement-learning framework that uses a diffusion...
-
14
Inductive Correlation Clustering with Graph Neural Networks
Francesco Paolo Nerini, Francesco Bonchi, Arijit Khan, André Panisson
cs.LG · cs.DS
Correlation Clustering (CC) is a natural formulation of clustering in combinatorial optimization, which uses a graph representation of the input and does not require a pre-specified number of clusters. Given $n$ objects and a pairwise similarity function, the goal is to cluster the objects so that similar objects are put in the same cluster and dissimilar objects are put in different clusters. Despite its versatility, existing CC algorithms...
-
15
Ultra Low-Power, Lightweight, Probabilistic RSS-Based Path Reconstruction: A System for Landscape-Scale Bee Tracking
Christopher J. Noroozi, Joseph L. Woodgate, Michael Mangan, Michael T. Smith
cs.LG
Applications in fields such as movement ecology, Internet of Things or robotics share the need for systems that localize devices that are too small and power constrained to implement GNSS (Global Navigation Satellite Systems). Alternative low-power localization methods often rely on only measurements of RSS (Received Signal Strength) to infer the AoA (Angle of Arrival) of a transmitted radio frequency signal, but are limited by range and the...
-
16
TRACE-CRC: Trajectory-Adaptive Conformal Risk Control for Multi-Step Channel State Information Prediction
Kiarash Rezaei, Mehdi Sattari, Javad Aliakbari, Tommy Svensson, Paolo Monti, Carlos Natalino
cs.LG · stat.ML
Reliable prediction of time-varying channel state information (CSI) is essential for efficient wireless communication. Each CSI frame is a matrix-valued representation of the wireless channel response, and a sequence of CSI frames forms a temporal channel trajectory. Modern deep learning-based CSI predictors, however, often provide only point predictions and lack calibrated uncertainty estimates. This limitation is particularly problematic in...
-
17
Cone Extended Rayleigh Quotients for Directed Graph Learning: Minimax Spectral Certificates, Sensitivity, and Adaptive Control
Yavdat Sh. Il'yasov, Nur F. Valeev
cs.LG
Directed graph learning naturally leads to trainable nonsymmetric propagation operators with distinct right and left spectral structures. Building on the two-sided cone Rayleigh framework for generalized pencils \[ B_θ-λG, \] we develop a learning-oriented methodology for spectral certification, sensitivity analysis, and control without requiring symmetry, nonnegativity, or cone preservation. In the positive-orthant setting, computable lower...
-
18
Tabular Deep Learning for Algorithmic Trading: Cross-Regime Bayesian Optimisation for Equity Signal Generation
Joshua Le Grice
cs.LG · q-fin.CP · q-fin.TR
Algorithmic trading now represents a market exceeding $20 billion, where even marginal gains in signal robustness can translate into economically significant returns. Existing evaluations of equity prediction models do not explicitly target regime robustness during hyperparameter selection. Five model classes are trained on daily observations from approximately 300 large-cap US equities over eleven years, with Bayesian optimisation configured...
-
19
Emotional Preferences as Goal-Priority Regulation
Shiqi Liu, Yihua Tan, Hu Fu, Guanyu Qi
cs.LG · cs.AI
A core question in decision-making for agents is whether the relative priorities of competing lower-level objectives can be determined by emotional preferences autonomously generated by higher-level goals, rather than being externally prespecified. Under changing external environments and evolving internal states, emotions play an important functional role in regulating the relative priorities of competing goals. Inspired by the goal-directed...
-
20
Unifying Detection and Adaptation in Task-Free Continual Learning
Dezheng Han, Anbang Zhang, Zhihao Zhu, Shuaishuai Guo
cs.LG · cs.CL
To mitigate catastrophic forgetting in downstream continual learning (CL) for large language models (LLMs), existing methods typically constrain parameter updates or introduce task-specific adaptation modules. However, these methods often rely on explicit task boundaries during training, limiting their applicability to realistic task-free scenarios. In this paper, we propose a \textbf{Fi}sher-guided \textbf{uni}fied (\textbf{FiUni}) framework...
-
21
Soft Active Electromyography Interface for Machine Learning-Enabled Silent Speech Recognition
Yuta Kurotaki, Shusuke Yamakoshi, Reitaro Yoshida, Yutaka Isoda, Tamami Takano, Yuji Isano, Yusuke Miyake, Kentaro...
cs.LG · cs.HC · cs.SD
Silent speech recognition (SSR) provides an alternative communication pathway in the absence of audible speech. However, conventional approaches are limited by the need for constant facial attachment, privacy concerns, and unstable signal acquisition. Here, we propose a soft, active electromyography (EMG) interface that enables word-level SSR using machine learning. Worn on the hand, the device uses a fingertip electrode that can be...
-
22
Performance Foundations of Parallel & Distributed Reasoning Language Models
Maciej Besta, Leonard Schmidt, Lara Nonino, Robert Gerstenberger, Pierre Pang, Patrik Okanovic, Ales Kubicek,...
cs.LG · cs.AI · cs.DC · cs.PF
Reinforcement Learning with Verifiable Rewards (RLVR) and other RL-style post-training paradigms have been used for aligning large language models (LLMs) with reasoning standards. The resulting recent Reasoning Language Models (RLMs) such as DeepSeek-R1, o3, and Kimi k1.5 show that such RL-style post-training ("RL-for-LLMs") can substantially improve chain-of-thought reasoning, long-horizon planning, and self-correction. However, the...
-
23
Disentangling Optimization Scale from Preference Scale in DPO
Ivan Kruzhilov
cs.LG
Direct Preference Optimization (DPO) is a widely used objective for aligning language models from preference data, with the coefficient $β$ commonly interpreted as controlling the KL constraint to a reference policy. We show that $β$ entangles two distinct roles: it governs the effective inverse preference-noise scale and simultaneously rescales the optimization dynamics, coupling this scale with the effective step size. As a consequence, at...
-
24
Benchmarking_Fast_Domain_Adaptation_for_Unsupervised_Speech_Units
Robin San Roman, Manel Khentout, Tu Anh Nguyen, Paul Michel, Yossi Adi, Emmanuel Dupoux
cs.LG
Representation learning has attracted great atten- tion and managed to reach good performances as a pretraining method for downstream tasks or as a first step towards unsu- pervised speech modeling. Yet, little is known about how such methods deal with out-of-domain speech and how could they be adapted in a few shot to new domains. This is important especially for accented speech where one observes a long tail of accents that diverge from the...
-
25
Decentralized Multitask Learning over Learned Task Graphs
Zirui Wan, Stefan Vlaski
cs.LG · eess.SP · eess.SY
This paper investigates decentralized multitask learning over networks when the underlying task relationships are unknown. While existing graph-regularized multitask frameworks typically assume a known structure, practical settings often require learning inter-task dependencies directly from distributed data. We propose a decentralized two-phase strategy that first estimates a generalized graph Laplacian from noisy non-cooperative stochastic...
-
26
Terrain signatures in Welsh settlement names
Oktay Karakuş, Can Eyupoglu
cs.LG · cs.CL
Landscapes are named, but whether names retain measurable environmental information beyond broad geographic structure is rarely tested. We analysed 3,757 Welsh settlements using a frozen, source-audited 24-element lexical framework, preregistered outcome-specific models and geographically structured validation. The central comparison contrasted 101 settlements carrying high-terrain elements (\textit{bryn} or \textit{mynydd}) with 139 carrying...
-
27
TEMPLAR Wales: A georeferenced environmental and toponymic dataset of Welsh settlements
Oktay Karakuş, Can Eyupoglu
cs.LG · cs.CL
Place names provide persistent records of how landscapes have been described and organised, but their quantitative reuse requires explicit separation between mapped places, lexical annotations and environmental measurements. TEMPLAR Wales is a georeferenced environmental-toponymy dataset comprising 3,757 settlement records across Wales. The resource links a reproducible settlement frame to deterministic lexical screening and settlement-level...
-
28
ClusterAttention: A training-free speedup of bidirectional attention
Kasper Nordenram, Amelie Dittmann
cs.LG · cs.CV
This paper introduces ClusterAttention, a general training-free speedup of bidirectional attention layers. Existing sparse attention methods either rely on structure in the input, such as order in language or spatial proximity in images, or use slow clustering processes amortized over several forward passes. ClusterAttention instead uses a fast recursive clustering method that adapts to the geometry of the keys and queries in each attention...
-
29
Graph-Based Pseudo-multimodal Contrastive Learning for 12-Lead ECG Representations
Mengyu Wang, Kozo Okada, Takafumi Goto, Natsuko Jinba, Hiroki Yamaya, Kiyoshi Hibi, Tomoki Hamagami
cs.LG
12-lead electrocardiogram (ECG) is a standard, non-invasive examination widely used for diagnosing coronary artery disease, where clinical interpretation relies on comparing waveform patterns across multiple leads. However, most existing ECG analysis methods focus on single-lead signals or treat each lead independently, and typically process ECG signals as one-dimensional time-series data using CNNs or RNNs. While effective in modeling local...
-
30
Adversarial Training Without Input Gradients via Low-Rank Householder Expansions
Tiana C. Johnson, Donsub Rim
cs.LG
This work concerns adversarial training against the small-norm adversarial examples that arise from the inherent input instability of a trained deep neural network. Examples in this class are small as measured in the relative $\ell^2$-norm, and therefore lie in the neighborhood of the input on which the model acts approximately linearly, the regime in which the perturbation remains imperceptible. We first show that such examples can be...
-
31
Packora: Systematic Design for Generative Molecular Crystal Structure Prediction
Nayoung Kim, Kiyoung Seong, Sungsoo Ahn
cs.LG · cond-mat.mtrl-sci
Molecular crystal structure prediction (CSP) is important in pharmaceuticals, agrochemicals, and organic electronics, where subtle differences in molecular conformation and packing can strongly affect material properties. We present Packora, a flow-based generative model for molecular CSP that jointly predicts atomic coordinates and the lattice from molecular graphs. Packora supports multi-component and organometallic crystals and can...
-
32
Gromov-Monge Flow Matching for Equivariant Graph Generation
Moritz Piening, Christian Wald
cs.LG · math.OC · stat.ML
Graphs are invariant under node permutations, motivating the use of permutation-equivariant architectures in generative models. In flow matching, however, symmetry may also enter the source--target coupling: once graph pairs are compared up to node relabeling, the natural Wasserstein geometry is that of the graph quotient space. The Euclidean quotient metric of this space coincides with the Gromov--Monge distance, obtained by optimally...
-
33
Scaling Model-Generated Distillation Data Can Make Latent Teacher Traits More Recoverable
Zhichen Dong, Zhixuan Liu, Yuyu Fan, Xiangtian Li, Shuyang Zhang, Chao Yang
cs.LG · cs.CL
Scaling model-generated data is usually viewed as improving distillation: more examples should increase coverage, reduce noise, and produce stronger students. We show a second effect: larger datasets can make subtle teacher-specific signals easier to detect in the trained student, even when examples are off-task and never mention the trait. In a controlled setup inspired by subliminal learning, a teacher induced to express a target trait...
-
34
A Layer Importance Metric for Quantization Accounting for the Speed-Quality Trade-off in Autoregressive Models
Artem Safronov
cs.LG
Small language models (sLLMs) are nowadays hosted on devices with limited memory and computational budget. In an autoregressive setup, inference is memory-bandwidth bound: uniform quantization is often detrimental to such models, since their architecture has limited redundancies and only a few layers are not very sensitive to lower precision. We propose a composite metric that combines two orthogonal criteria: information retention (measured...
-
35
Mitigating Strong-Modality Collapse in Multimodal Learning via Inverted Asymmetric Fusion
Mary Ogbuka Kenneth, Foaad Khosmood, Abbas Edalat
cs.LG · cs.MM
Fusing multiple modalities is expected to improve model performance. However, on the MultiHuSE dataset, early, late, and symmetric attention fusion often fail to outperform the best unimodal baseline (text). Pathway isolation of a symmetric attention fusion model reveals that the text-pathway accuracy drops from 74.9% to 56.4% after fusion in one such setting, indicating that the dominant modality can be degraded during integration. We term...
-
36
When Is the Sharp Covariance Envelope Tight? Feature-Only Geometry for Volume-Sampled Least Squares
Kihun Rhee
cs.LG · stat.ML
Prior analyses by Derezinski and Warmuth established all-size sampling identities, selected-OLS unbiasedness, and inverse moments for ordinary volume sampling, while their exact arbitrary-fixed-response loss and prediction-covariance formulas are at the rank-size endpoint s=d. We establish a Loewner envelope for centered coefficient covariance for every full-rank fixed pool, response, and legal budget d <= s <= m under ordinary indexed...
-
37
Reinforcement Learning-Based Control of CAV Platoon Joining Maneuvers in Mixed Traffic
Biao Yin, Abderrahmane Kasmi, Nadir Farhi
cs.LG · cs.AI · math.OC
Connected and automated vehicle (CAV) platooning offers a promising approach to improving road safety and traffic capacity. However, platoon control in real-world traffic is challenging due to uncertainty and heterogeneous driving behaviors. Reinforcement learning (RL) has strong potential for addressing such control problems, but its practical deployment raises challenges related to safety and learning efficiency. This paper proposes a...
-
38
SAGE: Variate-Wise Semantic Augmentation for Vision-Language Time Series Forecasting
Haizhao Fan, Xinyi Le
cs.LG · cs.CV
Time series forecasting models operate on raw numerical sequences, lacking the semantic knowledge that domain experts implicitly leverage, such as the physical meaning of each variable, its statistical behavior, and its temporal dynamics. Recent efforts to bridge this gap fall into two camps. Some rely on large language models at inference time, which is computationally expensive. Others apply uniform textual prompts at the dataset level,...
-
39
On the Indistinguishability of Human v/s AI Generated Text
Jaee Ponde, Aritra Das, Mihir More, Debayan Gupta
cs.LG
The rapid improvement of LLMs has made distinguishing AI-generated text from human writing a pressing problem. This challenge is further amplified by paraphrasing tools designed to make machine-generated text appear more "human". We study how access to human writing samples can be used to strategically paraphrase machine-generated responses toward the human distribution. Under a multi-sample setting with human and machine responses to the...
-
40
Beyond Client Averaging: A Client-Independent Second-Order Stationary-Bias Component in Stochastic SCAFFOLD
Yi-Ping Tang, Guan-Ju Peng
cs.LG · math.ST
Existing constant-step analysis of stochastic \Scaf{} identifies a leading $O(γ/N)$ stationary mean bias and shows that higher-order bias can persist as the client count increases, but does not identify the first client-independent contribution at coefficient level. For full-participation stochastic \Scaf{} with one-dimensional homogeneous clients, fixed local-step count $H$, and bounded additive gradient noise, we prove, uniformly over...
-
41
Safety by Design: Realized-Cost Constraints for Contextual Bandits with Continuous Actions
Spyros Dragazis, Aldo Pacchiano
cs.LG
Contextual bandits are a standard framework for sequential decision-making under uncertainty, with applications in clinical trials, dosage selection, recommendation systems, and autonomous systems. Safety is central in many of these applications, since a single unsafe decision in settings such as dosage selection or autonomous driving can have catastrophic consequences. A common way to model safety in bandit problems is to associate each...
-
42
Self-Augmented Diffusion Guidance for Physics-Informed Generation
Akira Osaka, Naoya Takeishi, Takehisa Yairi
cs.LG
Diffusion models can be used to generate spatiotemporal signals of physical phenomena, such as time-series images of fluid dynamics. However, a major limitation of standard diffusion models is that they do not incorporate constraints derived from the underlying physical laws. Consequently, generated samples may appear visually plausible while deviating substantially from the true dynamics. In this study, we propose a simple yet effective...
-
43
Rethinking Message Passing as Retrieval for Text-Attributed Graph Learning
Jintang Li, Yuhong Chen, Ruofan Wu, Binli Luo, Jiayi Ji, Hui Li, Rongrong Ji
cs.LG · cs.AI
Graph neural networks (GNNs) are typically conceptualized as message-passing neural networks, yet it remains unclear why neighborhood aggregation reliably outperforms node-wise multilayer perceptrons (MLPs). Despite its empirical success, this paradigm can be computationally expensive and sensitive to imperfect graph structures. In this work, we present a retrieval-augmented view of GNNs: each layer makes predictions by applying an MLP to a...
-
44
Neural Regression with Embeddings for Numerical Attribute Prediction in Knowledge Graphs
Rupesh Sapkota, Louis Mozart Kamdem Teyou, Moshood Yekini, Caglar Demir, Axel-Cyrille Ngonga Ngomo
cs.LG
In recent years, transductive knowledge graph embedding models have been applied to tasks such as link prediction and query answering. Although knowledge graphs often contain rich numerical attributes, most embedding models neglect them, limiting their ability to represent real-world knowledge graphs with diverse information. In this work, we propose a neural regression model (LitEm) that enables transductive knowledge graph embedding models...
-
45
Simple Actors and Deep Critics for Scalable Reinforcement Learning
Guhyeon Kang, Jaehwi Lee, Minhae Kwon
cs.LG
Recent progress in offline reinforcement learning (RL) has been driven by expressive generative actors such as diffusion and flow-matching policies, which capture multimodal behavior in offline datasets. However, these actors require multiple denoising or integration steps per action and thus incur substantial overhead at every decision in deployment. In this work, we revisit where capacity should be invested in an offline actor--critic...
-
46
When Privacy Hurts Mergeability: Geometry-Aware Model Merging under Differential Privacy
Jin Liu, Junkang Liu, Ning Xi, Yinbin Miao, Dawei Wei, Ke Cheng, Jianfeng Ma
cs.LG
Model merging promises to construct a single multi-task model from independently fine-tuned task models without accessing the original task data. This makes it attractive when task data cannot be centralized, but released task models may still leak private fine-tuning data. Differential privacy (DP) provides a principled mechanism for limiting such leakage, yet its effect on model merging remains poorly understood. In this paper, we study the...
-
47
Robust Neural Stimulation Response Modeling Through Meta-Learning and Pretraining
Matthew J Bryan, Daniel C Muir, Felix Schwock, Azadeh Yazdan-Shahmorad, Rajesh P N Rao
cs.LG
Objective: Model-based closed-loop neural stimulation holds promise for therapeutic applications ranging from Parkinson's disease to sensory restoration, but deployment has been limited by two obstacles: 1) forecasting models for predicting the consequences of stimulation fail catastrophically on a meaningful fraction of sessions, and 2) per-session calibration requirements are often incompatible with clinical constraints. We address both by...
-
48
Technical Comparative Benchmarking Study: Advanced AI Hybrid Methods for Renewable Energy Farm Optimization and Forecasting
Majid Masoumi, Asghar Dashtiy, Mohammad Dehghan, Mina Rajabi
cs.LG
This study provides a comprehensive benchmarking of conventional machine learning (ML), ensemble learning, deep neural networks, recurrent architectures, Transformers, graph based models, and hybrid ensemble deep learning approaches under complementary renewable energy scenarios. Three datasets are considered: a large scale WEC dataset, a 16 WEC dataset, and operational 10 min SCADA measurements at the Penmanshiel wind farm. For structured...
-
49
SimCast-S2S: An Efficient Generative Model for Subseasonal Precipitation Forecasting via Transfer Learning from Climate Simulations
Hiep V. Dang, Antonios Mamalakis
cs.LG
Subseasonal-to-seasonal (S2S) precipitation forecasting has substantial financial and societal impact, yet remains challenging because of weak predictive signals, high associated uncertainty, and the computational cost of operational systems, which constrains simulation fidelity. We introduce SimCast-S2S, a generative latent-diffusion framework for probabilistic S2S precipitation forecasting that addresses three major bottlenecks in...
-
50
GRAS: Guided Reduced-Variance Proposals and Adaptive Selection for Training-Free Reward Alignment in Discrete Diffusion
Kwanyoung Kim
cs.LG · cs.CE · q-bio.QM · stat.ML
Discrete diffusion models have become a strong, widely adopted class of generators for sequence data, and steering them toward a downstream reward at inference time, without any retraining, is increasingly important. Such training-free steering is done by gradient guidance, by search, or by combining the two. We study the combined regime and identify two weaknesses in how it is usually run: the guided proposal estimates its gradient from a...
-
51
J-Zero: Unified Challenger--Solver--Judge Co-Evolution from Zero Data
Gyouk Chu, Myeongho Jeon, Eunho Yang
cs.LG · cs.AI · cs.CL
Self-evolving language models have recently emerged as a promising path toward superintelligence, with the advantage of reducing the cost of human supervision. While considerable progress has been made in verifiable domains, self-evolution in unverifiable domains remains substantially less explored. We propose Judge co-adaptation from Zero data (J-Zero), a unified Challenger--Solver--Judge co-evolution framework that supports self-improvement...
-
52
Activation Outliers Matter: Robust Recovery for Quantized Multimodal LLMs
Tanzila Rahman, Mehran Taghian Jazi, Yunke Peng, Zhuang Ma, Anandharaju Durai Raju, Yao Wang, Xing Huang, Hei Yi...
cs.LG
Low-bit quantization offers a promising avenue for reducing the computational and memory demands of Multimodal Large Language Models (MLLMs). Recent hardware support for low-precision formats, ranging from MXFP8 to ultra-low-bit formats such as MXFP4 and HiF4, has accelerated research into efficient MLLM training and deployment. In this work, we present a systematic study of these quantization schemes in representative MLLMs that span both...
-
53
Arrive and Survive: Scaling Safe Goal-Conditioned Policy Learning from One-Bit Failure Signals
Guopeng Li, Yiyang Duan, Yiru Jiao, Chengcheng Xu
cs.LG · cs.RO
Contrastive reinforcement learning (CRL) scales effectively in goal-conditioned tasks by casting policy learning into a self-supervised contrastive objective. However, in a failure-terminated Markov decision process, established CRL considers pre-failure future goals only when constructing positive samples, without accounting for the probability mass removed by failure termination. Our theoretical analysis shows that this omission induces a...
-
54
Chart2SVG: Editable SVG Generation from Raster Chart Images
Jinning Cui, Lu Chen, Haoyan Shi, Yue He, Chenglong Wang, Mengyu Zhou, Weidong Huang, Yunhai Wang
cs.LG
We present Chart2SVG, a multimodal large language model that converts static raster charts into structurally organized, semantically enriched SVGs that support programmatic editing. By incorporating chart-specific semantic tokens into a vision-language model, Chart2SVG captures both geometric primitives and their functional roles. To support robust structural recovery, we introduce Beagle+, a dataset of 33K canonicalized and structurally...
-
55
Predicting Quantifiability from Primary Screens to Prioritize Dose-Response Profiling
Sean Lim
cs.LG · q-bio.BM
High-throughput drug screening relies on low-cost primary assays to prioritize compounds for more expensive dose-response profiling, where potency is ultimately quantified. Current screening strategies largely focus on identifying compounds that will confirm biological activity on follow-up, implicitly assuming that confirmed activity will also yield a usable potency estimate. However, confirmed biological activity in screening does not...
-
56
High Probability Derivative Bounds for Random tanh Neural Networks on a Hypercube
Josef Dick, Michael Feischl, Fabian Zehetgruber
cs.LG · math.NA
We establish high-probability bounds for mixed input derivatives of wide random neural networks whose activation derivatives satisfy a factorial growth bound. Our main result specializes these estimates to $\tanh$ networks with Xavier initialization. A direct deterministic analysis based on Euclidean operator norms of the weight matrices yields derivative bounds that generally grow exponentially with the depth. We show that this growth can be...
-
57
Algorithmic Principles For Multiclass Learning Are Hard To Come By: Limits of Regularization and Proper Learning
Julian Asilis, Shaddin Dughmi, Vatsal Sharan, Alec Sun, Shang-Hua Teng, Chang Wang
cs.LG · stat.ML
Two of the most fundamental questions in statistical learning theory are the following: which prediction problems are learnable, and how should they be learned? For the former, elegant answers often take the form of combinatorial dimensions. The latter question, however, has proved considerably more elusive: all known general-purpose multiclass learners rely on intricate orientations of exponentially large one-inclusion structures, and...
-
58
A Single Suffix to Break Them All: Basin-Aware Jailbreaks for Merged Model Families
Yu Zhe, Yixin Tan, Junhao Wei, Wang Chen
cs.LG · cs.CL
Model merging enables combining multiple fine-tuned models without additional training, but its safety implications remain poorly understood. Prior work primarily attributes merging risks to unsafe constituent models, implicitly assuming that merging individually aligned models preserves safety. In contrast, we show that model merging reveals a previously overlooked jailbreak risk rooted in the pretrained foundation model, even when all...
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.