cs.LG · 2026-09-20 · No. 119
Machine Learning, 2026-09-20.
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
Score Centering Stabilizes Off-policy Reinforcement Learning
Martin Marek, Max Ryabinin
cs.LG
Reinforcement learning (RL) of large language models is notoriously sensitive to small differences between training and inference engines, often referred to as the training-inference mismatch (TIM). However, completely eliminating TIM is impractical, as it would come at a major cost to rollout efficiency. In this paper, we show that the instability of RL under TIM is primarily caused by drift: a persistent bias between training and inference...
-
02
PosteriorBench: From Point Estimates to Posterior Matching in Evaluating Generative Inverse Solvers
Jiachen Yao, Zi-Siang Hsu, Xi Deng, Aditi Gupta, Xin Ju, Sally M Benson, Gege Wen, Anima Anandkumar
cs.LG · cs.CE
Generative models are increasingly used to solve scientific inverse problems, but existing evaluations still focus primarily on whether a method can produce a single plausible reconstruction. This is insufficient for ill-posed problems, where multiple solutions may be consistent with the same sparse or noisy observations. In these settings, a method can achieve strong pointwise accuracy while still failing to capture the true posterior...
-
03
Calibrated RF-Fingerprinting Under Interference With Heterogeneous Transmission Protocols
Tariq Abdul-Quddoos, Xiangfang Li, Lijun Qian
cs.LG
Radio Frequency(RF)-Fingerprinting is a spectrum monitoring technique that identifies specific transmitters based on hardware impairments imprinted within the emitted signal. Although widely researched, studies almost exclusively consider scenarios where only one transmitter is emitting at a time, limiting real world applicability. In this work, we further the study of RF-Fingerprinting by considering co-channel interference, with multiple...
-
04
Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation
Haocheng Xi, Yiming Xie, Hexu Zhao, Yiwen Zhang, Michael Liu, Thomas Creavin, Kurt Keutzer, Xiuyu Li, Zhaoyang Lv,...
cs.LG
Video diffusion models repeatedly process long spatiotemporal token sequences during denoising, making attention a major computational bottleneck. Linear attention offers an appealing alternative and has been widely adopted in recent large language models, but directly applying it to video models often fails to preserve the fine-grained interactions required for high-quality generation. We present Video DeltaNet (VDN), which combines local...
-
05
Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL
Juzheng Zhang, Disha Makhija, Manoj Ghuhan Arivazhagan, Vinayshekhar Bannihatti Kumar, Rashmi Gangadharaiah
cs.LG · cs.AI · cs.CL
Agent trajectories record what an agent does and what happens next. Yet standard supervised fine-tuning (SFT) applies loss only to agent-authored action tokens, using environment observations as context but not as prediction targets. We ask whether this convention provides the best initialization for subsequent reinforcement learning. We introduce ActObs, which also supervises the observation tokens already present in each trajectory....
-
06
RISC-V and machine learning: a survey
Shriman Keshri, Apparna Singh, Chinmaya Kumar Palo, Shreya Adya, Subhankar Mishra
cs.LG · cs.AR
The intersection of open-source processor architectures and machine learning is driving the demand for customizable, efficient, and accessible hardware. This survey examines the state of the RISC-V ISA in machine learning applications, analyzing current capabilities, challenges, and future directions based on recent research. The analysis covers academic and commercial implementations, software frameworks, and real-world applications. The...
-
07
Epidemiological Causal Graph Identification: Challenges, Identifiability and Algorithms
Sambit Mishra, Yingying Wang, Christine K. Johnson, Urbashi Mitra
cs.LG · stat.ME · stat.ML
Causal discovery from observational data is fundamental to statistics and machine learning, yet determining causal direction without interventions necessitates structural assumptions. Existing identifiability research primarily focuses on continuous variables under additive noise models, often neglecting mixed datasets containing ordinal scales, counts, and continuous measurements. This paper investigates causal discovery in Directed Acyclic...
-
08
Multi-center Medical Data Mining with FL-Net - A One-stop Shop for Federated Learning
Simon Süwer, Julian Klemm, Elisa Acitelli, Mathieu Almeida, Lucia Altucci, Zsolt Bagyura, Michelangela Barbieri,...
cs.LG · cs.CR · cs.DC
Federated learning enables collaborative training without sharing patient-level data, but most studies remain simulations. Based on five requirements derived from the literature, we analyzed 14 FL frameworks and found that none fully satisfied these requirements. We present FL-Net, a novel federated clinical research framework to fulfill all requirements. It integrates modular data harmonization, data discovery, disclosure control, securely...
-
09
COIN-GP: Cooperative Online Learning in Networked Distributed Systems with Partial Measurements via Gaussian Process Regression
Zewen Yang, Xiaobing Dai, Zhenxiao Yin, Hang Zhao, Zhijun Li, C. C. Chan
cs.LG · cs.MA · eess.SY
In this paper, we tackle the problem of jointly estimating the system states and partially unknown dynamics within distributed sensor-equipped networks, particularly in scenarios where only partial state observations are available. To address this issue, we propose an observer-based dynamic cooperative learning framework incorporating online distributed Gaussian Process (GP) regression, which enables accurate estimation despite incomplete in...
-
10
Recursive Quantum Long Short-Term Memory for Stable Short-Horizon Temperature Forecasting
Mu-En Lee, Yen-Ku Liu, Samuel Yen-Chi Chen, Yun-Cheng Tsai
cs.LG
Quantum long short-term memory (QLSTM) models extend recurrent sequence learning with variational quantum circuits, but their optimization behavior can vary substantially across random initializations and temporal contexts. This paper evaluates a recursive QLSTM architecture against a standard QLSTM for one-step-ahead prediction of daily minimum and maximum temperature. Using daily weather observations from Toronto and identical training...
-
11
CrystalMO-TuRBO: Multi-Objective Trust-Region Bayesian Optimization for High-precision Joint Crystal Structure Refinement
Joseph Agada, Yishu Wang, Arpan Biswas
cs.LG
Crystal structure refinement is a fundamental inverse problem in materials characterization, where structural parameters are optimized to reproduce experimental diffraction data. Conventional approaches, such as least-squares and likelihood-based optimization, rely on local search and often struggle with non-convex, noisy, and highly correlated parameter landscapes, particularly when integrating multiple diffraction modalities. Joint...
-
12
Mitigating Retaliatory Algorithmic Collusion in Repeated Games
Karthik Sivachandran, Rohan Paleja
cs.LG · cs.AI
Reinforcement learning agents trained to maximize their own reward in repeated interactions can converge to supra-competitive outcomes resembling explicit collusion, without communication or shared design. Existing mitigation approaches are largely tied to specific economic settings, like two-sided platforms and auctions, leaving open how to design interventions for general repeated games. We address this gap by formalizing the connection...
-
13
Parallelism, critical windows, and separations among diffusion language models
Sitan Chen, Liye Wang
cs.LG · cs.DS · math.ST · stat.ML
A popular selling point of diffusion large language models (dLLMs) is their capacity for parallelism: the ability to generate sequences of text far more efficiently than autoregressive models, which require one forward pass per token. Yet among the many competing paradigms for dLLMs, from masked to uniform to Gaussian diffusion, principled understanding of how these different proposals compare in parallelism remains limited. In this work, we...
-
14
When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation
Yuxiao Yang, Tianrun Yu, Shangzhe Li, Kaixiang Zhao, Xuchao Zhang, Chetan Bansal, Huaxiu Yao, Taylor W. Killian,...
cs.LG
We study length inflation in on-policy distillation (OPD), where student responses can become excessively long and even exhaust the generation budget. We identify \emph{termination-token mismatch} between base students and post-trained teachers as an important source of this behavior. Across Qwen3, Llama, and Gemma, the two models can place their stopping probability on different EOS tokens, even when their declared stopping sets are...
-
15
Radio Frequency Detection and Classification of Microplastics in Water
Jaden Tolbert, Md Saiful Islam, Pingshan Wang
cs.LG
Micro- and nano-plastic particles (MPs/NPs) are ubiquitous environmental contaminants whose increasing abundance and potential health impacts have created an urgent need for rapid, label-free detection methods. As particle size decreases to the low-micrometer range, conventional optical and spectroscopic techniques become increasingly challenging because of limited throughput and/or complex sample preparation. In this work, we present a...
-
16
Distributionally Robust Federated Learning with Multi-Source Data
Yingzhu Liu, Zhongkui Li, Pengcheng You, Ashish Cherukuri
cs.LG · math.OC
Federated learning trains a shared model from private client data. In practice, data-generating distributions may differ, and the true mixture across clients is often unknown, making the underlying group distribution difficult to specify. Existing approaches address cross-client mixture uncertainty by optimizing against the worst-case mixture, yet assume accurate client-wise distribution estimates. However, these estimates can be unreliable...
-
17
Deep Learning-Based Classification of Cognitive and Resting States Using Electroencephalography Signals
K. A. Januka S. Fernando, Harshit Srivastava
cs.LG · cs.AI
The categorization of cognitive and resting states derived from electroencephalography (EEG) signals is crucial for comprehending fluctuations in brain activity linked to various mental states. EEG provides a non-intrusive approach for documenting brain function in both resting and task-oriented cognitive conditions, whilst deep learning techniques enable the automatic extraction of significant patterns from intricate EEG data. This study...
-
18
Training Neural Networks to Approach the Optimum Bayes Estimator in Dense Multi-Emitter Localization
Yi Sun, Mona Sharifi, Muzna Yumman
cs.LG
We train neural networks on synthesized frames to approach the optimum Bayes estimator for dense emitter localization. The result justifies the future work on training neural networks to achieve high-throughput large-FOV super spatiotemporal resolution SMLM.
-
19
Seismic Site Response Prediction from Sparse Observations Using Finite-Element-Pretrained Latent Dynamics
Yi Zhu, Su Chen, Xiaojun Li
cs.LG
Numerical site-response predictions often deviate from observations, yet correcting these discrepancies is difficult because records are limited in both sensor coverage and number of events. This study proposes the Transfer-Enabled Forced Latent Autoencoder for Response Equations (FLARE-T) to improve these predictions by learning and calibrating low-dimensional latent dynamics that connect the base acceleration input to acceleration outputs...
-
20
SCGFM-ART: Amortized Relational Transport for Structure-Centric Graph Foundation Models
Xiaodong He, Xincheng Wang, Zhao Kang
cs.LG · cs.AI
Graph foundation models (GFMs) aim to learn transferable representations across severely heterogeneous graph domains. However, severe domain shifts in topology, graph scale, and feature semantics impede the construction of a unified, domain-agnostic representation space. To address this, we propose SCGFM-ART, a structure-centric GFM framework that aligns arbitrary graphs onto a shared relational atlas via Amortized Relational Transport (ART)....
-
21
The Bias of Nonlinear Two-Time-scale Stochastic Approximation under Constant Step-Sizes
Djamel Rassem Lamouri, Dorian Baudry, Nicolas Gast
cs.LG · math.OC · stat.ML
Two-timescale stochastic approximation (TTSA) is a fundamental tool for analyzing coupled iterative algorithms in reinforcement learning, optimization, and stochastic control. However, finite-time guarantees for nonlinear two-timescale schemes remain difficult to obtain, especially under constant step-sizes. In this paper, we study nonlinear TTSA with step-sizes $α\ggβ$. Under standard stability, regularity, and Markovian noise assumptions,...
-
22
Learning Principal-Agent Contracts for Equitable Smallholder Carbon Farming under Moral Hazard and Adverse Selection
Rishi Bharadwaj, Yadati Narahari
cs.LG · cs.GT
Agricultural soils are a major untapped carbon sink. Carbon farming is emerging as a promising practice for tapping this potential. Smallholder farmers, who dominate agriculture across South Asia and sub-Saharan Africa, are key to scaling climate mitigation via carbon farming. It is ironic that real-world carbon programs largely fail to reach them. We study this important gap through the lens of contract design. An aggregator offers a single...
-
23
Minimax-Optimal Online Contract Design with Unrestricted Bounded Contracts
Rui Ai, David Simchi-Levi, Han Zhong
cs.LG
We study repeated contract design when a principal observes outcomes but not the actions that generate them. The principal may use any bounded outcome-contingent payment vector, and the agent's best response can make expected profit discontinuous in those payments. For every fixed number $m\ge2$ of outcomes, the minimax regret over $T$ rounds is of order $T^{m/(m+1)}$, up to logarithmic factors. The upper bound allows arbitrary action spaces...
-
24
COMPASS: Ordered Clustered Routing at 100K Scale
Ido Greenberg, Hugo Linsenmaier, Piotr Sielski, Shie Mannor, Alex Fender, Gal Chechik, Eli Meirom
cs.LG
Large-scale routing often requires visiting clusters of nodes in a prescribed order, giving rise to the Ordered Clustered Traveling Salesman Problem (OCTSP). Optimizing each cluster independently seems natural, but misses non-local dependencies. We introduce the COMPASS algorithm for OCTSP, which combines search with learning-accelerated routing by orchestrating parallel sub-solvers. COMPASS has no quality ceiling and its solutions keep...
-
25
Sharp Reconstruction Bounds for Autoencoders Using the Same Forward Map
Patricia Medina, Hy P. G. Lam
cs.LG · math.DS
We study reconstruction in autoencoders that apply the same forward map before and after setting the observed coordinates to zero. For equal odd input and hidden dimensions $d\geq 3$, among orientation-preserving diffeomorphisms whose Jacobian singular values lie in $[m,M]$, we show that the least uniform reconstruction-derivative error is $\max\{1-M(M-m)/2,0\}$, with affine maps attaining this sharp bound at every prescribed depth. A...
-
26
QUALS: Corpus Equilibrium for Universal Forecasting via Pattern Quantization and Learnability Synchronization
Yujie Li, Zezhi Shao, Chengqing Yu, Yisong Fu, Weijie Zhu, Yifan Du, Jilin Hu, Bin Yang, Yongjun Xu, Fei Wang
cs.LG · cs.AI
Ubiquitous time series data across diverse domains enables critical applications in areas such as transportation systems and power grids. Recently, training foundation models on massive datasets to achieve accurate zero-shot forecasting has emerged as a major research focus. However, current studies predominantly prioritize architectural innovations while insufficiently addressing data diversity, often relying on simple data sampling...
-
27
Fast-varying Natural Frequencies and Damping Ratio Identification for Linear Time-Varying System
Melisa Bozaci, Alice Cicirello
cs.LG
This work proposes a physics-enhanced machine learning approach for the system identification of Linear Time-Varying (LTV) systems under time-varying operating conditions in terms of fast-varying natural frequencies and damping ratios by combining a long short-term memory network with an Extended Kalman Filter (EKF). The proposed approach uses vibration data (displacement and velocity measurements), domain knowledge of modal damping ratios,...
-
28
Local Sparsity Enables Unsupervised LLM Safety Detection
Xin Chen, Gil Kur, Alexander Shevchenko, Andreas Krause
cs.LG · cs.AI
Deployment-time safety methods for large language models (LLMs) are predominantly supervised and assume access to unsafe training data. Nevertheless, new attacks and harm categories regularly arise, not captured by models trained in such a supervised fashion. An alternative approach is to view this problem through the lens of anomaly detection, namely, to rely solely on modeling safe data and flagging out-of-distribution inputs. However, LLM...
-
29
QoS-Aware Federated Learning for Multimodal In-Cabin Interaction in Smart Vehicles
Baran Can Gül, Mert Nakıp, Nasser Jazdi, Michael Weyrich
cs.LG
Modern smart vehicles leverage multimodal sensors, ranging from high-bandwidth vision systems to low-rate physiological monitors, to provide personalized in-cabin services. However, integrating high-fidelity multimodal fusion with collaborative training is often hindered by the heterogeneous and time-varying Quality of Service (QoS) constraints of vehicular networks. Standard Federated Learning (FL) approaches enforce rigid synchronous rounds...
-
30
CARE-VI: Conservative Adaptive Reliability Estimation for Value Improvement in Off-Policy Actor-Critic Learning
Xiang Zou, Shengzhu Shi, Junqi Gao, Zhichang Guo
cs.LG
Reliable temporal-difference targets are central to off-policy actor-critic learning. Direct value improvement refines the next-state target with alternative actions, but the reliability of this refinement depends on how candidate actions are ranked, reviewed, and weighted. Noisy rankings may force premature candidate commitment, reusing selection scores may bias target valuation, and fixed enhancement weights may amplify weak evidence. To...
-
31
SETTer: Sparse-Encoder Transformer for Long-term Multivariate Time Series Forecasting
Abraham Ezema, Chijioke Eze, Ferdinanda Ponci, Antonello Monti
cs.LG
Long-term multivariate time series plays a significant role in many application areas such as power systems, trading, etc. However, their accurate prediction is quite difficult for conventional forecasting methods as they often exhibit high dimensionality and complex relationships. Recent works show that transformer-based approaches are quite effective for long-term forecasting thanks to their attention mechanism. However, in the presence of...
-
32
MATCH: Model-Aware Tool Learning with Curriculum Scheduling and Hierarchically Gated Rewards
Shihao Liu, Hao Yin, Lijun Liu, Zhengzong Chen, Yuanyuan Zhao, Fei Huang
cs.LG · cs.AI · cs.CL
Tool learning enables large language models (LLMs) to use external tools for tasks beyond parametric knowledge. Reinforcement learning can optimize tool-call behavior from feedback, but current methods still face two problems: fixed-threshold curricula can become misaligned with the policy's evolving capability boundary, and additive rewards can leak argument-level credit when the predicted tool is wrong. To address these problems, we propose...
-
33
Evaluating Explanation Methods by the Predictors They Induce
Jacob Selbæk, Hugo L. Hammer
cs.LG
Explanations of machine learning models are usually judged by criteria that are hard to compare. We propose a simpler test: if an explanation really describes how a model uses its features, it should be possible to rebuild the model's predictions from it. We turn each explanation into a predictor by reading each feature's effect and adding them up, and measure how well that predictor reproduces the model on unseen data. Nothing is fitted, so...
-
34
Correct Now, Insufficient Later: Auditing Update Sufficiency in Context Compression
Guangzhe Zhang
cs.LG · cs.AI
A memory can answer a current query correctly while discarding distinctions required by a later update. We investigate this failure with a paired-history audit: two histories have the same current answer, receive a shared future update, and require different subsequent answers. A pilot evaluates 24 history pairs across six synthetic mechanisms, 12 memory conditions, two repeats, and two model backends. A deterministic frontier selector...
-
35
Dynamic Generalized Gromov-Wasserstein Optimal Transport
Junda Ying, Zhiwei Zeng, Peijie Zhou, Lei Zhang
cs.LG · cs.AI · math.OC · q-bio.QM
Gromov--Wasserstein optimal transport (GW-OT) extends classical optimal transport by introducing structure-aware transport cost. This is particularly relevant for spatial transcriptomics, where dynamical reconstruction should preserve tissue structure in addition to matching expression patterns. While static formulations have been widely used for such structure-aware alignment, a general dynamic formulation for reconstructing continuous...
-
36
EPIG-Tree: Compute-Optimal Branching for Gradient-Efficient Reinforcement Learning
Nikita Khomich, Leopold Hermansson, Ido Hakimi
cs.LG · cs.AI
Reward-based reinforcement learning for language models, exemplified by Group Relative Policy Optimization (GRPO), collapses an entire stochastic trajectory into a single scalar reward. This is clean and scalable, but it explores and allocates reward inefficiently: a trajectory may contain many causal decisions, recovery attempts, and environment-randomness events, yet every token or action inherits one trajectory-level advantage. We study...
-
37
Past, Future, All at Once: Mitigating Stability-Plasticity Dilemma via Post-hoc JANUS Rectification
Zhilong Zheng, Letian Tao, Yang Guan, Yujie Yang, Wei Xiong, Kehua Sheng, Bo Zhang, Jingliang Duan, Keqiang Li,...
cs.LG · cs.AI
Fine-tuning foundation models on new tasks inevitably suffer from catastrophic forgetting. While existing works attempt to mitigate this on the basis of parameter-efficient fine-tuning methods, they adopted an overly restrictive Subspace Orthogonality condition. In this paper, we introduce a purely post-hoc and tuning-agnostic weight rectification framework that achieves Parameter Space Orthogonality, which is the necessary and sufficient...
-
38
CellRFT: Reinforcement Fine-Tuning for Single-Cell Perturbation Modeling
Jie Yan, Li Liu, Hanze Guo, Jiaxin Hu, Houxin He, Xiaoning Qi, Haoran Wang, Cong Li, Zhong-Yuan Zhang, Yong Wang
cs.LG
Predicting cellular responses to perturbations supports the study of gene function, disease mechanisms, and therapeutic strategies. Despite advances in single-cell perturbation modeling, existing models typically optimize surrogate losses that do not directly reflect the biological criteria used for evaluation, so better data fitting need not yield better biological predictions. To address this mismatch, we introduce \textbf{CellRFT}, a...
-
39
Graph-Based Stochastic Power-UCT: Monte-Carlo Graph Search with Power Mean Estimation
Tung Tran, Viet Bao Mai, Hoang Ta, Tuan Dam
cs.LG
Tree-based Monte-Carlo Tree Search (MCTS) duplicates the same state when it is reached through different trajectories, which can waste simulations in stochastic MDPs. We introduce Graph-Based Stochastic-Power-UCT (GS-Power-UCT), which shares states reached at the same planning depth while keeping separate values for states reached at different depths. This design applies to general stochastic MDPs, including problems with cycles. We prove...
-
40
One Intervention per Component is Enough: Towards Identifiability in Linear Stochastic Dynamics from Steady State
Saber Salehkaleybar
cs.LG
We study the problem of recovering the parameters of a multivariate Ornstein-Uhlenbeck (OU) process from steady-state observational and interventional data. In many applications, such as large-scale gene perturbation experiments, only stationary "snapshot" measurements are available, making standard stochastic differential equation estimation methods that rely on time-series trajectories inapplicable. We first establish an identifiability...
-
41
Amortizing Physics-Informed Neural Solvers via Graph Hypernetworks
Cheng Jing, Abhishek Verma, Kallol Bera, Yixuan He, Kookjin Lee
cs.LG
Amortizing physics-informed neural networks (PINNs) across related PDEs requires describing each equation to a reusable solver. Coefficient vectors encode numerical parameters in predefined slots, leaving operator and cross-field assignments implicit. We make these relationships explicit in an operator graph, with nodes for fields, derivatives, terms, and residuals and coefficients retained as term attributes. A graph hypernetwork generates...
-
42
Digital Twins for Opinion Dynamics: A Generative LLM Framework for Social Networks
Omran Berjawi, Giuseppe Fenza, Rida Khatoun, Sherali Zeadally
cs.LG
The study of opinion dynamics in social networks is one of the key challenges in computational social science with direct relevance to understanding political polarization, misinformation, and health responses. Current approaches focus on simplified mathematical models that ignore linguistic and contextual factors related to belief updates or use Large Language Model (LLM)-based simulations that have not been validated against real data. We...
-
43
REARL: A Closed-loop Autonomous Driving Simulation Enhancement Framework with Real Traffic Data and Large Language Models
Xiaojun Bi, Jun Jiang, Yiwen Sun, Quanyi Ou, Ke Cheng, Mingjie Bi, Yexin Li
cs.LG
Accurate simulation is crucial for autonomous driving development, yet capturing real-world traffic complexity remains challenging. Existing simulators that rely on predefined rules or static data playback struggle with dynamic traffic. CRITICAL uses real traffic data and a large language model (LLM) to adjust the initial simulation configuration, but the simulated distribution still diverges from real traffic as the rollout evolves. We...
-
44
Online Adaptive Kernel Mixing for Gaussian Process Decision Making
Kavin Aravindan, Mani Tej Sriram, Gautam Dasarathy, Tejas Bodas
cs.LG
Gaussian Processes (GPs) are widely used as surrogates for black-box functions in sequential decision-making problems such as Bayesian optimization (BO), level set estimation (LSE), and Bayesian active learning (BAL). GP performance critically depends on kernels, and standard kernels can lead to suboptimal decisions under misspecification. To address this, we introduce HACK GPs (Hedge Adaptive Cumulative Kernels), a method that views kernel...
-
45
Uni-LaDiR: Latent Diffusion Unifies Multimodal Reasoning
Haoqiang Kang, Yizhe Zhang, Nikki Lijing Kuang, Yian Ma, Lianhui Qin
cs.LG · cs.CL
Multimodal reasoning requires models to draw on information from multiple modalities throughout the reasoning process. Yet existing methods often concatenate modality-specific thought tokens in a single sequence, leaving the model to bridge representational differences as it reasons across modalities. We introduce Uni-LaDiR (Unified Latent Diffusion Reasoner), a framework that brings these thoughts into a shared latent space for reasoning. A...
-
46
AURA: Adaptive Uncertainty-Routed Analysis for Email Threat Detection
Omran Berjawi, Walid fahs, Rida Khatoun
cs.LG
Email spam and phishing attacks remain a critical security threat. Adversaries increasingly exploit large language models to craft contextually convincing malicious messages, and existing spam detection systems often struggle to keep pace. Generalization across diverse and evolving attack scenarios is limited, which reduces effectiveness once these systems are deployed in practice. This paper introduces Adaptive Uncertainty-Routed Analysis...
-
47
Pretrained Medical Representations for the Practical Screening of Drug Repositioning Candidates
Yuhei Fujioka, Daitaro Misawa, Shingo Fukuma
cs.LG
Representation learning from medical code sequences in electronic health records and medical claims data has been successful in various clinical applications, such as those regarding disease prediction. However, significant challenges remain in extending this approach to the discovery of scientific hypotheses. One reason is that many existing BERT-based models fail to adequately capture the hierarchical structure of medical codes and the...
-
48
Expected Hypervolume Maximization for Multiobjective Optimization under Uncertainties
Victor Trappler
cs.LG
The problem of multiobjective optimization under uncertainties is often approached by taking the expectation of each objective. In this work, we propose instead to formulate this as a Bayesian decision problem and to rely on the expected value of the hypervolume, which is to be maximized with respect to a finite set of input points. We show that this can be performed using methods based on gradients in a stochastic optimization framework,...
-
49
Beyond Flattened Tokens: Structure-Preserving EEG Decoding with Reusable TriDim Blocks
Shiyue Su, Song Wang, Zekai Zhan, Junjie Zeng, Ziling Lu, Zongsheng Li, Xinyuan Ye, Zhiyuan Ma, Xinke Shen, Quanying Liu
cs.LG
Effective EEG decoding requires representations that preserve organization among channels, local waveform dynamics, and long-range temporal context. Existing EEG architectures often capture these structures using separate specialized modules or collapse them into a single token sequence, making it difficult to maintain their distinct roles and coordinate their interactions throughout the backbone. We propose TriDim, a reusable block that...
-
50
DeliveryGym: An RL Environment for Long-Horizon Embodied Agent Planning with Adaptive Curriculum
Haoqiang Kang, Yiming Zhang, Yiyang Guo, Chuying Li, Jianzhi Shen, Tianruo Rose Xu, Xiaokang Ye, Lianhui Qin
cs.LG
Executable environments enable LLM agents to learn from the consequences of their actions. For embodied agents, those consequences extend beyond whether the current task succeeds: completing a delivery can consume the time, energy, or money needed for later work. Learning to plan therefore requires environments that preserve these dependencies and turn them into feedback across a complete trajectory. We introduce DeliveryGym, a 3D environment...
-
51
Learning-Based Reconstruction of Optical Properties in Bilayered Media from Single-distance Time-Resolved Reflectance Measurements
Caterina Amendola, Giulia Maffeis, Lorenzo Buffoni, Lorenzo Chicchi, Francesco Coghi, Duccio Fanelli, Raffaele...
cs.LG · physics.optics
The inverse problem of reconstructing optical properties, specifically absorption and scattering coefficients, in layered biological media from time-domain reflectance measurements remains a significant challenge for traditional analytical models. Inverse solvers based on the diffusion equation often struggle with structural heterogeneity, frequently yielding poor accuracy for superficial absorption and deep-layers scattering. In this work,...
-
52
PhyRestore: Physics-Structured Latent-Factor Restoration
Ahmed Shafee, Chayan Lahiri
cs.LG
Estimating temporal soil-loss change is challenging when physically meaningful input factors are noisy or corrupted, particularly because substantial changes are rare relative to the large number of locations exhibiting little change. We study this problem through the Revised Universal Soil Loss Equation (RUSLE) and introduce PhyRestore, a physics-structured latent-factor restoration framework. Rather than directly predicting soil-loss change...
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.