cs.LG · 2026-05-25 · No. 9
Machine Learning, 2026-05-25.
52 new papers in cs.LG. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
52 entries-
01
LLMs as Noisy Channels: A Shannon Perspective on Model Capacity and Scaling Laws
Xu Ouyang, Deyi Liu, Yuhang Cai, Jing Liu, Yuan Yang, Chen Zheng, Thomas Hartvigsen, Yiyuan Ma
cs.LG · cs.AI · cs.IT
Existing scaling laws for Large Language Models (LLMs), predominantly monotonic power laws, fail to explain emerging non-monotonic phenomena such as catastrophic overtraining and quantization-induced degradation, where performance deteriorates despite increased compute. We propose the Shannon Scaling Law, a unified theoretical framework that models LLM training as information transmission over a noisy channel, grounded in the Shannon-Hartley...
-
02
Leveraging Foundation Models for Causal Generative Modeling
Aneesh Komanduri, Xintao Wu
cs.LG · cs.AI · cs.CV
Causal generative modeling is essential for developing reliable and transparent AI systems capable of counterfactual reasoning. While existing approaches focus on integrating causal constraints during the training of generative models, they often lack a unified framework to leverage the zero-shot reasoning capabilities of pretrained foundation models. We introduce FM-CGM, a modular framework for end-to-end visual causal reasoning using...
-
03
It's the humans, not the data: Geopolitical bias in LLMs originates in post-training, amplified by the language of the prompt
Stuart Bladon, Brinnae Bent
cs.LG · cs.AI
It has generally been assumed that geopolitical bias in language models originates from the training data used during the pre-training phase. We tested seven open-weight LLM pairs consisting of the base model (pre-training only) and the chat model (pre-training and post-training) from seven labs on a paired-scenario forced-choice probe over 28 country pairs in English, French, and Chinese, and found that geopolitical bias originates in...
-
04
Learning Through Noise: Why Subliminal Learning Works and When It Fails
Vincent C. Brockers, Roman D. Ventzke, Valentin Neuhaus, Belén Hidalgo-Ogalde, Viola Priesemann
cs.LG · cs.AI
In the context of artificial neural networks, subliminal learning refers to the transfer of task-relevant knowledge or unintended biases from teacher to student models through distillation on task-unrelated input$\unicode{x2013}$output pairs. Prior explanations tie this effect to shared or closely matched teacher$\unicode{x2013}$student initialization. We show that a closely matched initialization is not necessary. Instead, subliminal...
-
05
DiLaDiff: Distilled Latent-Augmented Diffusion for Language Modeling
Jean-Marie Lemercier, Tomas Geffner, Karsten Kreis, Morteza Mardani, Arash Vahdat, Ante Jukić
cs.LG · cs.AI · cs.CL
Diffusion language models intrinsically fail to capture correlations between decoded tokens, which leads to a harsh trade-off between sampling quality and throughput. To solve this issue, we propose DiLaDiff, a variant of masked diffusion language models with three components: (1) a continuous latent space with semantic capabilities, learned by an auto-encoder fine-tuned from an existing masked diffusion language model; (2) a latent diffusion...
-
06
Preisach Attention: A Hysteretic Model of Sequential Memory
Piotr Frydrych
cs.LG · cond-mat.dis-nn · cs.AI · cs.NE
We introduce the Preisach Attention Layer (PAL), a novel sequence modelling architecture grounded in the classical Preisach hysteresis operator from mathematical physics. PAL replaces the softmax attention mechanism with a binary relay operator parameterised by learned activation and deactivation thresholds, maintaining a stack of local extrema as its internal state. A single-layer PAL-Transformer with O(1) depth is Turing-complete under...
-
07
Cost-Effective Model Evaluation with Meta-Learning
Trinh Pham, Viet Huynh, Hongzhi Yin, Quoc Viet Hung Nguyen, Thanh Tam Nguyen
cs.LG · cs.AI · cs.CV · cs.ET · cs.PF
The rapid growth of machine learning has produced an ever-expanding ecosystem of models, making it increasingly challenging to verify the reliability of newly released models on unseen, unlabeled data. Conventional evaluation pipelines depend on expensive annotation, repeated fine-tuning, or narrow assumptions that fail to transfer across model families. We present MetaEvaluator, a cost-effective, model-agnostic framework for rapid,...
-
08
Understanding Goal Generalisation in Sequential Reinforcement Learning
Jason Ross Brown, Edward James Young
cs.LG · cs.AI
Reinforcement learning agents often exhibit unintended goal-directed behaviour outside their training distribution, but we currently lack a principled understanding of how such agents will generalise to novel environments based on their training history. We address this gap for agents trained sequentially on one or more tasks. We study over 100 sequential training pipelines, evaluating behaviour across over 250 out-of-distribution...
-
09
Goal-Conditioned Agents that Learn Everything All at Once
Michael Matthews, Matthew Jackson, Michael Beukman, Thomas Foster, Alistair Letcher, Scott Fujimoto, Cédric Colas,...
cs.LG · cs.AI
A goal-conditioned reinforcement learning agent exploring an environment will see a wealth of information throughout a trajectory, most of which is discarded when only performing on-policy updates with respect to the commanded goal. All-goals learning, where each transition is used for learning off-policy with respect to every goal, allows agents to extract maximal information, however it is usually computationally infeasible when done via...
-
10
Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models
Jade Zou, Tao Huang, Weijie Kong, Junzhe Li, Yue Wu, Qi Tian, Jiangfeng Xiong, Jianwei Zhang, Liefeng Bo, Zhao Zhong
cs.LG · cs.AI · cs.CV
Reinforcement learning (RL) has become an effective way to improve prompt alignment and perceptual quality in diffusion and flow-matching generators. A critical step for applying online RL to flow matching is turning the deterministic sampling trajectory into a stochastic policy, typically by replacing the reverse-time Ordinary Differential Equation (ODE) with a Stochastic Differential Equation (SDE). The stochastic sampler, controlling the...
-
11
VACE: Learning Geometrically Structured Representations for Time Series Anomaly Detection
Alberto D. Cencillo, Leonardo Concepción, Isaac Triguero, Julián Luengo
cs.LG · cs.AI
Anomaly detection in multivariate time series is a critical task across a wide range of real-world applications, where abnormal behaviour is rare, labels are unavailable, and the cost of a miss is high. The central challenge is learning a characterisation of normality precise enough to flag deviations. Representation self-supervised learning, typically through contrastive approaches, addresses this by embedding temporal patches into a latent...
-
12
CoSPlay: Cooperative Self-Play at Test-Time with Self-Generated Code and Unit Test
Zhangyi Hu, Chenhui Liu, Tian Huang, Jindong Li, Yang Yang, Jiemin Wu, Zining Zhong, Menglin Yang, Yutao Yue
cs.LG · cs.AI · cs.CL
Recently, Reinforcement Learning with Verifiable Rewards (RLVR) and Test-Time Scaling (TTS) have advanced LLM code generation through executable verification. Yet Ground-Truth Unit Tests (GT UTs) remain a bottleneck: SOTA RLVR methods require them for costly training, while existing TTS methods lose competitiveness without them. This motivates GT-free TTS, where existing methods directly use self-generated UTs to refine and select code...
-
13
Automated Random Embedding for Practical Bayesian Optimization with Unknown Effective Dimension
Hong Qian, Xiang Shu, Xiang Xia, Xuhui Liu, Yangde Fu, Bei Liang, Huibin Wang, Liang Dou
cs.LG · cs.AI
Bayesian optimization is widely employed for optimizing complex black-box functions but struggles with the curse of dimensionality. Random embedding, as a dimension reduction strategy, simplifies tasks that possess the effective dimension by optimizing within a low-dimensional subspace. However, determining the effective dimension of a task in advance remains a significant challenge, which influences the selection of the subspace...
-
14
CBANet: A Compact Attention-Based CNN-BiLSTM Network for Aggressive Driving Event Detection
Hanadi Alhamdan, Ghadah Alosaimi, Amir Atapour-Abarghouei, Farshad Arvin
cs.LG · cs.AI
Aggressive driving is a major cause of traffic accidents and poses a serious threat to road safety. Although deep learning methods have shown promising results in detecting risky driving behaviours from vehicle sensor data, their performance in real-world conditions is often limited by severe data imbalance, large variability between drivers, and the lack of physically interpretable vehicle dynamics representations. In this paper, we propose...
-
15
Learning Individual Dynamics from Sparse Cross-Sectional Snapshots
Christian Lagemann, Kai Lagemann, Steven L. Brunton, Sach Mukherjee
cs.LG · cs.AI · cs.CE
Predicting how a dynamical unit evolves over time - how an individual ages, an epidemic spreads, or a physical system degrades - typically requires dense longitudinal tracking. When only extremely sparse or entirely cross-sectional data is available, inferring individualized, continuous-time trajectories is fundamentally ill-posed. Existing methods force a strict compromise: sequence models (e.g. latent ODEs) require dense longitudinal data,...
-
16
Reflex: Reinforcement Learning with Reflection Symmetry Exploitation in State-Based Continuous Control
Shuai Zhen, Yifan Zhang, Yuling Wang, Yanhua Yu
cs.LG · cs.AI
Reinforcement learning has long struggled with poor sample efficiency. One promising approach to mitigate this problem is leveraging group-invariant Markov Decision Processes ($G$-invariant MDPs). Existing works in this direction have primarily focused on image-based RL and rotational symmetry such as $\mathrm{SO(2)}$, leaving state-based RL and reflection symmetry largely underexplored. In this work, we focus on state-based continuous...
-
17
Parametric Prior Mapping Framework for Non-stationary Probabilistic Time Series Forecasting
Jinglin Li, Jun Tan, QI Fang, Ning Gui
cs.LG · cs.AI
Effectively modeling non-stationary dynamics in probabilistic multivariate time series(MTS) forecasting requires balancing expressiveness with robustness. Existing parametric approaches benefit from strong inductive biases but lack flexibility, whereas deep generative models struggle to capture complex temporal dependencies without extensive data and computation. We introduce Parametric Prior Mapping (PPM), a framework that injects parametric...
-
18
Every Component is a Lookup: Token Attribution and Composition from a Single Decomposition
Po-Kai Chen, Niki van Stein, Aske Plaat
cs.LG · cs.AI
Mechanistic interpretability of transformers requires identifying not just which components matter but how they compose into the computational route that produced a prediction. Both attention and MLP follow a shared key-value template $φ(S)U$. We exploit this structure to develop Unpack, a backward recursion that decomposes credit through both sublayers, producing interaction strengths between any two components, named end-to-end paths with...
-
19
Curriculum reinforcement learning with measurable task representation learning
Yongyan Wen, Siyuan Li, Mingjian Fu, Yiqin Yang, Xun Wang, Peng Liu
cs.LG · cs.AI
In curriculum reinforcement learning (CRL), an agent incrementally accumulates knowledge over a sequence of tasks (i.e., a curriculum), and the learning process is aimed at using the accumulated knowledge to finally solve a challenging target task. While early CRL works focus on sequencing candidate tasks, recent research explores automatic curriculum generation. Among the rich CRL literature, the interpolation-based CRL paradigm is a main...
-
20
Score-Based One-step MeanFlow Policy Optimization
Kyungyoon Kim, Donghyeon Ki, Hee-Jun Ahn, Byung-Jun Lee
cs.LG · cs.AI
Diffusion and flow matching have emerged as expressive policy classes in reinforcement learning, but their reliance on multi-step denoising imposes substantial computational overhead at inference time, which is particularly problematic in online RL. MeanFlow offers a promising alternative by learning an average velocity field that maps noise to data in a single network evaluation. However, MeanFlow typically requires samples from the target...
-
21
Reinforcement Learning for Microcanonical Graph Ensemble with Assortativity Constraints
Hoyun Choi, Junghyo Jo, Deok-Sun Lee
cs.LG · cond-mat.stat-mech · cs.AI
How network structure determines function is a fundamental question, and it can be investigated by graph ensembles with precisely controlled structural properties. Canonical approaches, formulated as exponential random graph models (ERGMs), enforce constraints only in expectation, allowing individual realizations to fluctuate around the target. Conversely, microcanonical ensembles impose hard constraints exactly, but practical sampling...
-
22
When Good Equations Get Bad Scores: Improving Symbolic Regression Through Better Parameter Optimization
Boxiao Wang, Kai Li, Zhiwei Chen, Yang Huang, Runxiang Wang, Ziwen Zhang, Yifan Zhang, Jian Cheng
cs.LG · cs.AI
Symbolic Regression (SR) plays a central role in scientific knowledge discovery by distilling mathematical equations from observational data. Most existing SR methods function within a bi-level optimization framework: an outer loop that searches for the discrete equation structure, and an inner loop that optimizes the continuous parameters of that structure. Crucially, parameter-fitting quality directly determines a structure's score and thus...
-
23
Multi-Gate Residuals
Zhizhan Zheng, Feiyun Zhang, Shuchun Liu, Tian Xia, Xi Liu, Dasheng Hu, Hongquan Zhou
cs.LG · cs.AI · cs.CL
While Attention Residuals has shown some effectiveness in addressing the widespread issue of unbounded activation growth across deep residual layers, it inevitably incurs significant communication overhead. To circumvent this bottleneck, we propose Multi-Gate Residuals (MGR), which stabilizes activation scales without additional communication burden. It utilizes a straightforward scoring and gating mechanism to maintain multi-stream context,...
-
24
Enhancing Deep Neural Network Reliability with Refinement and Calibration
Ramya Hebbalaguppe, Ajay Shastry, Soumya Suvra Ghosal, Chetan Arora
cs.LG · cs.AI
Although deep neural networks (DNNs) achieve high predictive accuracy, their confidence estimates are often unreliable, potentially compromising user trust in their decisions. This has motivated research on calibrated models, where calibration measures how well a model's predicted confidence aligns with the empirical probability of correctness. However, calibration metrics can often be improved through post-processing techniques that merely...
-
25
PaP-NF: Probabilistic Long-Term Time Series Forecasting via Prefix-as-Prompt Reprogramming and Normalizing Flows
Minju Kim, Youngbum Hur
cs.LG · cs.AI
Time series forecasting plays a central role in many real-world applications and has been extensively studied. Most existing approaches rely on deterministic models. However, real-world environments exhibit inherently uncertain and complex future behaviors, making single-point predictions insufficient. This highlights the need for probabilistic forecasting methods that can quantify and represent uncertainty. In this work, we propose PaP-NF, a...
-
26
FastKernels: Benchmarking GPU Kernel Generation in Production
Gabriele Oliaro, Yichao Fu, May Jiang, Owen Lu, Junli Wang, Zhihao Jia, Hao Zhang, Samyam Rajbhandari
cs.LG · cs.AI · cs.CL
LLM-based agents for GPU kernel generation are advancing rapidly, yet their progress is fundamentally constrained by the benchmarks they optimize against. Existing benchmarks are poorly aligned with production inference frameworks: they evaluate kernels on a single GPU with synthetic inputs, ignore the surrounding compilation stack, and reward replicating known optimizations rather than discovering new ones. The resulting reward signals are...
-
27
Adaptive Mass-Segmented KV Compression for Long-Context Reasoning
Junzhe Yang, Xiaoyu Shen
cs.LG · cs.AI
The linear growth of the Key-Value (KV) cache is a critical bottleneck in long-form LLM inference. Existing KV compression methods mitigate this by evicting tokens based on importance scores. However, we show that their reliance on global Top-k selection triggers Region Wipe-out: the severe eviction of contiguous reasoning blocks that derails logical coherence. To address this, we propose Adaptive Mass-Segmented (AMS) KV Compression, a...
-
28
Scalable Heterogeneous Graph Foundation Models for Data-Driven Optimal Power Flow in Smart Grids
Massimiliano Lupo Pasini, Yijiang Li, Kibaek Kim, Teja Kuruganti
cs.LG · cs.AI
Fast and reliable optimal power flow (OPF) approximation is essential for reliable smart-grid operation, yet many learning-based surrogates either flatten the native heterogeneous structure of power networks, target a limited set of grid topologies, or lack scalable infrastructure for graph foundation model (GFM) training. This paper presents a scalable heterogeneous graph neural network (GNN) workflow, built on HydraGNN, for data-driven OPF...
-
29
Understanding and Improving Noisy Embedding Techniques in Instruction Finetuning
Abhay Yadav
cs.LG · cs.AI · stat.ML
Recent advancements in instructional fine-tuning have injected noise into embeddings, with NEFTune (Jain et al., 2024) setting benchmarks using uniform noise. Despite NEFTune's empirical findings that uniform noise outperforms Gaussian noise, the reasons for this remain unclear. This paper aims to clarify this by offering a thorough analysis, both theoretical and empirical, indicating comparable performance among these noise types....
-
30
Infra-Bayesian Reinforcement Learning Agents Outperform Classical RL For Worst-Case Robustness
Manish Aryal, Faiyaz Azam, Agnivo Banerjee, Sai Sidhanth Manoharan Jayanthi, Allegra Laro, Clément Legentilhomme,...
cs.LG · cs.AI
Classical reinforcement learning assumes the agent interacts with a fixed environment whose behavior does not depend on the agent's policy. This assumption breaks down in non-realizable settings where other actors might anticipate the agent's behavior, including environments crucial to AI safety, where the agent interacts with predictors, humans, other AI agents, and institutions. In such settings, the agent's model class fails to capture the...
-
31
CALAD: Channel-Aware contrastive Learning for multivariate time series Anomaly Detection
Jaehyeop Hong, Youngbum Hur
cs.LG · cs.AI
Multivariate time series anomaly detection has become increasingly important in real-world applications, where labeled data are often scarce. Many existing approaches rely on unsupervised learning to model normal patterns, but they often treat all channels equally. This design can dilute anomaly-relevant signals, since not all channels contribute equally to anomaly detection. In this paper, we propose CALAD, a channel-aware contrastive...
-
32
Dreaming Smoothly and Sample Efficiently with Gradient Penalized Latent Dynamics
Romil V. Sonigra, P. R. Kumar
cs.LG · cs.AI
Model-based reinforcement learning improves sample efficiency by learning a world model. However, existing latent world models such as DreamerV3 do not explicitly enforce local smoothness in their learned transition dynamics, leaving a useful inductive bias for transition dynamics learning unexploited. We propose GPLD, a gradient-penalized latent dynamics regularizer for DreamerV3 that applies a row-wise Jacobian penalty to the posterior...
-
33
Anytime Training with Schedule-Free Spectral Optimization
Anuj Apte, Pranav Deshpande, Niraj Kumar, Shouvanik Chakrabarti, Junhyung Lyle Kim
cs.LG · cs.AI · math.OC · stat.ML
Standard neural network training relies on learning-rate schedules tied to a fixed horizon, leading to strong path dependence and costly re-tuning as data availability changes. Schedule-Free (SF) methods address this by removing explicit schedules, yet SF-AdamW, the current state-of-the-art anytime optimizer, consistently underperforms well-tuned AdamW baselines. We propose SF-NorMuon, a schedule-free spectral optimizer that closes this gap:...
-
34
Decomposing and Measuring Evaluation Awareness
Changling Li, Terry Jingchen Zhang, Jie Zhang, Zhijing Jin, Sahar Abdelnabi, Maksym Andriushchenko
cs.LG · cs.AI · cs.CL
Frontier language models sometimes recognize that they are being evaluated and adjust their behavior, undermining validity of benchmark results. Yet the field studies it without a shared foundation, conflating properties of the evaluation with properties of the model, and detection with behavioral response. We ground evaluation awareness in social psychology, decomposing it into an environment component (how recognizable the task is) and a...
-
35
Uncovering the Latent Potential of Deep Intermediate Representations
Arnesh Batra, Arush Gumber, Aniket Khandelwal, Jashn Khemani, Anubha Gupta
cs.LG · cs.AI
Foundational Models pretrained on huge amount of data learn representations that evolve across depth, forming a hierarchy of embeddings with distinct semantic content and geometric structure. Contrary to the widespread practice of using only the final layer or shallow mixtures, we show that task-relevant information is distributed non-monotonically across layers and cannot be recovered by naïve aggregation. Through a geometric and empirical...
-
36
Test-Time Training Undermines Safety Guardrails
Simone Antonelli, Sadegh Akhondzadeh, Aleksandar Bojchevski
cs.LG · cs.AI
Test-Time Training (TTT) is an emerging paradigm that enables models to adapt their parameters during inference, improving performance on tasks such as few-shot learning, retrieval-augmented generation, and complex reasoning. However, this dynamic adaptation introduces new vulnerabilities that adversaries can exploit to jailbreak models. We identify three threat models for TTT and demonstrate how attackers can leverage them to bypass safety...
-
37
Worse than Random: The Importance of a Baseline for Unsupervised Feature Selection
Muhammad Rajabinasab, Michael E. Houle, Oussama Chelly, Arthur Zimek
cs.LG · cs.AI
Many novel unsupervised feature selection methods are proposed each year, yet their empirical evaluation is limited to supervised and unsupervised evaluation metrics computed on selected datasets, along with comparisons to existing methods. However, in the absence of an established evaluation baseline, it is difficult to determine the value added to the existing literature by each of these methods, and how effective their underlying...
-
38
A mathematical theory of balancing relational generalization and memorization
Luke Cheng, Samuel Lippl
cs.LG · cs.AI
Humans, animals, and modern machine learning models exhibit impressive abilities to learn complex behaviors and generalize these behaviors to unseen situations. This ability requires us to learn rules and regularities that allow for such generalizations. At the same time, in most complex environments, any rule will have its exceptions. How do learning systems balance between learning general regularities and memorizing exceptions? We argue...
-
39
Human-Centered Learning Mechanics: A Dynamical Framework for Entropy-Regulated Representation Learning
Kim Phuc Tran
cs.LG · cs.AI · stat.ML
Deep learning is increasingly viewed as a dynamical process in parameter space, yet many existing theories still treat training as a closed optimization system. This view is limited for real-world AI, where models operate under uncertainty, resource constraints, distribution shift, downstream decision risks, and human feedback. We propose Human-Centered Learning Mechanics (HCLM), a dynamical and information-theoretic framework for open and...
-
40
Vector Policy Optimization: Training for Diversity Improves Test-Time Search
Ryan Bahlous-Boldi, Isha Puri, Idan Shenfeld, Akarsh Kumar, Mehul Damani, Sebastian Risi, Omar Khattab, Zhang-Wei...
cs.LG · cs.AI · cs.CL · cs.NE
Language models must now generalize out of the box to novel environments and work inside inference-scaling search procedures, such as AlphaEvolve, that select rollouts with a variety of task-specific reward functions. Unfortunately, the standard paradigm of LLM post-training optimizes a pre-specified scalar reward, often leading current LLMs to produce low-entropy response distributions and thus to struggle at displaying the diversity that...
-
41
The Matching Principle: A Geometric Theory of Loss Functions for Nuisance-Robust Representation Learning
Vishal Rajput
cs.LG · cs.AI · stat.ML
Robustness, domain adaptation, photometric and occlusion invariance, compositional generalisation, temporal robustness, alignment safety, and classical anisotropic regularisation are usually treated as separate problems with separate method families. This paper argues that much of their shared structure is one statistical problem: estimate the covariance of label-preserving deployment nuisance, then regularise the encoder Jacobian along a...
-
42
Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models
Dimitrios Damianos, Leon Voukoutis, Georgios Skyrianos, Vassilis Katsouros, Georgios Paraskevopoulos
cs.LG · cs.AI · cs.CL
Generative Vision-Language Models (VLMs) perform well on multimodal reasoning, but how visual inputs are transformed to text remains poorly understood. Existing interpretability work on VLMs uses Sparse Autoencoders (SAEs), which decompose static residual representations and miss the functional updates that drive cross-modal interaction. We adopt a function-centric framework based on Transcoders, sparse approximations of MLP sublayers that...
-
43
SDPM: Survival Diffusion Probabilistic Model for Continuous-Time Survival Analysis
Stanislav R. Kirpichenko, Andrei V. Konstantinov, Lev V. Utkin
cs.LG · cs.AI · stat.CO · stat.ML
Survival analysis aims to estimate a time-to-event distribution from data with censored observations. Many existing methods either impose structural assumptions on the hazard function or discretize the time axis, which may limit flexibility and introduce approximation errors. We propose the Survival Diffusion Probabilistic Model (SDPM), a generative approach to continuous-time survival analysis. SDPM models the conditional distribution of the...
-
44
MambaGaze: Bidirectional Mamba with Explicit Missing Data Modeling for Cognitive Load Assessment from Eye-Gaze Tracking Data
Amir Mousavi, Mohammad Sadegh Sirjani, Erfan Nourbakhsh, Mimi Xie, Rocky Slavin, Leslie Neely, John Davis, John Quarles
cs.LG · cs.AI · cs.HC
Real-time cognitive load assessment from eye-tracking signals could potentially enable adaptive human-centered-AI such as safety-critical applications such as driver vigilance monitoring or automated flight deck assistance, yet two challenges persist: handling frequent data missingness from blinks and tracking failures, and efficiently modeling long-range temporal dependencies. We propose MambaGaze, a framework that addresses these challenges...
-
45
CogAdapt: Transferring Clinical ECG Foundation Models to Wearable Cognitive Load Assessment via Lead Adaptation
Amir Mousavi, Mohammad Sadegh Sirjani, Erfan Nourbakhsh, Mimi Xie, Rocky Slavin, Leslie Neely, John Davis, John Quarles
cs.LG · cs.AI · cs.HC
Real-time cognitive load assessment is essential for adaptive human-computer interaction but remains challenging due to limited labeled data and poor cross-subject generalization. Recent ECG foundation models pre-trained on millions of clinical recordings offer rich representations, but cannot be directly applied to wearable devices due to sensor configuration mismatch and task differences. In this paper, we propose CogAdapt, a framework that...
-
46
Cyber-Physical Anomaly Detection in IoT-Enabled Smart Grids Using Machine Learning and Metaheuristic Feature Optimization
Adis Alihodžić, Eva Tuba, Milan Tuba
cs.LG · cs.AI
Modern smart grids rely on dense measurement infrastructures, communication links, and intelligent field devices. Although this improves supervision and control, it also increases vulnerability to cyber-physical disruptions. Operators must distinguish physical incidents, such as faults or line disturbances, from malicious actions, such as false data injection or unauthorized command execution. This chapter investigates this problem using the...
-
47
Proxy-Based Approximation of Shapley and Banzhaf Interactions
Santo M. A. R. Thies, Hubert Baniecki, R. Teal Witter, Eyke Hüllermeier, Maximilian Muschalik, Fabian Fumagalli
cs.LG · cs.AI · stat.ML
Shapley and Banzhaf interactions capture the complex dynamics inherent in modern machine learning applications. However, current estimators for these higher-order interactions trade off between speed and accuracy. To overcome this limitation, we introduce ProxySHAP. ProxySHAP reconciles the high sample efficiency of tree-based proxy models with a principled path to consistency via residual correction. On a theoretical level, we derive a...
-
48
The Distillation Game: Adaptive Attacks & Efficient Defenses
Youssef Allouah, Mahdi Haghifam, Sanmi Koyejo, Reza Shokri
cs.LG · cs.AI
Distillation attacks create a deployment trade-off for model providers: the same outputs that make a model more useful can also make it easier to imitate. We study this trade-off through a minimax game between a utility-constrained teacher and an adaptive student. Our framework yields tractable one-sided response rules: an adaptive evaluation rule in which the student reweights high-value examples, and a teacher-side defense template that...
-
49
Post-Training is About States, Not Tokens: A State Distribution View of SFT, RL, and On-Policy Distillation
Dong Nie
cs.LG · cs.AI
Large language model post-training methods such as supervised fine-tuning (SFT), reinforcement learning (RL), and distillation are often analyzed through their loss functions: maximum likelihood, policy gradients, forward KL, reverse KL, or related objective-level variants. We study a complementary factor: the state distribution on which supervision is applied. For an autoregressive policy, a state is a prompt plus generated prefix. SFT...
-
50
The Value of Covariance Matching in Gaussian DDPMs and the Lanczos Sampler
Md Sahil Akhtar, Aymane El Gadarri, Vivek F. Farias, Adam D. Jozefiak
cs.LG · cs.AI · cs.IT
A central error measure in Gaussian DDPMs is the path-space KL divergence between the exact reverse chain and the learned Gaussian reverse process. This quantity is especially relevant for procedures such as classifier guidance, which perturb the entire reverse trajectory rather than only the terminal sample. Prior analyses show that standard isotropic reverse covariances suffer an unavoidable $Ω(1/T)$ path-KL error as the number of denoising...
-
51
Abstraction for Offline Goal-Conditioned Reinforcement Learning
Clarisse Wibault, Alexander Goldie, Antonio Villares, Maike Osborne, Jakob Foerster
cs.LG · cs.AI
Markov Decision Processes (MDPs) often exhibit significant redundancy due to symmetries and shared structure across state-goal pairs in real-world Goal-Conditioned Reinforcement Learning (GCRL). While hierarchical policies have been motivated for horizon reduction via temporal abstraction in offline GCRL, we demonstrate that hierarchy also enables absolute abstraction. By introducing relativised options as well as distinct representations for...
-
52
MoSA: Motion-constrained Stress Adaptation for Mitigating Real-to-Sim Gap in Continuum Dynamics via Learning Residual Anisotropy
Jiaxu Wang, Junhao He, Jingkai Sun, Yi Gu, Yunyang Mo, Jiahang Cao, Qiang Zhang, Renjing Xu
cs.LG · cs.AI · cs.GR · cs.RO
Learning real-world dynamics from visual observations is crucial for various domains. A common strategy is to calibrate simulators by estimating physical parameters, yet accuracy is ultimately bounded by the underlying physical models, which often assume materials are homogeneous and isotropic. Even if reasonable, real-world objects typically exhibit mild anisotropy and heterogeneity. After the near-isotropic backbone is well calibrated,...
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.