News / #paper Tag Research papers 500 articles archived under #paper · RSS Sign in to follow arXiv — Machine Learning research 3d ago Resolving Multi-Modal Regression by Difference-Quotient-Based Clustering:Fast Coarse Conditional-Label Assignment arXiv:2608.25467v1 Announce Type: new Abstract: Multimodal regression suffers from the mean-collapse pathology: under squared loss, an unconstrained regressor converges to the conditional mean, which for K > 1 lies away from all modes. We attribute this failure to pairwise… 31 arXiv — NLP / Computation & Language research 3d ago A Storage-Retrieval Gap in Parametric Knowledge Graph Memory arXiv:2608.25489v1 Announce Type: cross Abstract: Graph retrieval-augmented generation places retrieved subgraphs into the model's context window at query time, paying a recurring token cost and exposing source data on every call. We study an alternative: compiling a knowledge… 21 arXiv — Machine Learning research 3d ago FedQoS: Federated QoS-Risk Learning for Heterogeneous Indoor-Outdoor Access Selection arXiv:2608.25496v1 Announce Type: new Abstract: Reliable access selection in dynamic and heterogeneous indoor-outdoor environments is challenging because instantaneous radio measurements alone cannot capture future QoS degradation caused by mobility, blockage, traffic load, and… 33 arXiv — Machine Learning research 3d ago Resilient Decentralized Wireless Federated Learning via Gradient Tracking with AdamW arXiv:2608.25535v1 Announce Type: new Abstract: Wireless Internet-of-Things (IoT) edge networks require decentralized learning (DecL) methods that can operate reliably under both heterogeneous local data and communication-constrained wireless links. However, existing… 34 arXiv — NLP / Computation & Language research 3d ago Reflection Steering: Disentangling Reflection from Reasoning in Activation Space for Token-Efficient Inference arXiv:2608.25542v1 Announce Type: cross Abstract: Large reasoning models often produce reasoning traces with verification, revision, and backtracking. When reflection merely re-checks established results, it wastes reasoning tokens and increases latency. Most existing reflection… 18 arXiv — Machine Learning research 3d ago Interpreting Protein Language Model Embeddings via Orthogonal Projection for Protein Fitness Prediction arXiv:2608.25548v1 Announce Type: new Abstract: Recently, there has been a growing adoption of protein language models (PLMs) in biomedical science. Their embeddings provide a rich numerical representation of protein sequences which achieve state-of-the-art performance on… 4 arXiv — Machine Learning research 3d ago Beyond Optimal Rates in Stochastic Optimization: Trajectory-Adaptive Stopping Rules arXiv:2608.25551v1 Announce Type: new Abstract: Stochastic gradient descent (SGD) is typically analyzed at a deterministic horizon chosen before the algorithm is run, even though practical stopping decisions are made adaptively by inspecting the evolving trajectory. This… 22 arXiv — Machine Learning research 3d ago Physics-Informed Foresight Pruning for Sparse PINN Solvers of Nonlinear PDEs arXiv:2608.25564v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) often rely on over-parameterized models to optimize coupled solution and differential-residual objectives, leaving unclear how much capacity is necessary and what pruning should preserve. We… 28 arXiv — Machine Learning research 3d ago Beyond Scaling: Self-Evolving LLM Agents for Hardware Kernel Optimization via an Experience-Driven Workflow and Experience Graph Memory arXiv:2608.25570v1 Announce Type: new Abstract: Hardware kernel optimization requires repeated compilation, correctness testing, profiling, and revision. LLM agents can automate parts of this process, and stronger foundation models, longer context windows, and longer execution… 19 arXiv — Machine Learning research 3d ago Individual Fairness in Hierarchical Clustering arXiv:2608.25586v1 Announce Type: new Abstract: Hierarchical clustering produces ultrametric representations that impose strong global geometric constraints and may distort local similarities in ways that disproportionately affect individual data points. We study hierarchical… 6 arXiv — Machine Learning research 3d ago M-Fibration Theory with Applications to Neural Network Compression arXiv:2608.25598v1 Announce Type: new Abstract: The purpose of this paper is to provide a general, comprehensive, theoretical framework that allows one to deal with fibrations on graphs labelled on a commutative monoid. This is a genuine extension of the theory of graph… 38 arXiv — Machine Learning research 3d ago Frequency-aware forecasting for short-term typhoon gust prediction arXiv:2608.25604v1 Announce Type: new Abstract: Accurate gust forecasting under typhoon conditions remains challenging due to the highly non-stationary and multi-scale characteristics of extreme wind fluctuations. Existing deep learning models often struggle to simultaneously… 38 arXiv — Machine Learning research 3d ago DCEO: Direct Causal Effect Optimization for Long-Term User Value Modeling in E-commerce Search arXiv:2608.25635v1 Announce Type: new Abstract: Industrial e-commerce search systems ultimately aim to optimize the user-level long-term objective, such as n-day cumulative purchases or gross merchandise value (GMV) per user. However, such objectives are defined at the user… 6 arXiv — NLP / Computation & Language research 3d ago A Token-Level Analysis of Sampled-Token Reverse-KL On-Policy Distillation arXiv:2608.25643v1 Announce Type: cross Abstract: On-policy distillation (OPD) supervises a student on its own trajectories with token-level signals from a frozen teacher, yet how a sampled loss allocates updates across tokens remains poorly understood. We analyze the gradient… 29 arXiv — Machine Learning research 3d ago LDAC-Net: A Learnable Multi-Lag Differencing Attention-Convolution Network for Drift-Robust Recognition with Low-Cost MOX Gas Sensors arXiv:2608.25646v1 Announce Type: new Abstract: Portable electronic-nose systems based on low-cost metal-oxide (MOX) gas sensors offer a practical solution for gas and odour recognition, but their signals are affected by slow chemical transients, drifting sensor offsets, scale… 24 arXiv — Machine Learning research 3d ago Adversarial Training of Linear Models under Stealthy Attacks arXiv:2608.25681v1 Announce Type: new Abstract: Predictive models are widely used in many fields, but are vulnerable to false data injection attacks. To address this, detection schemes and adversarial training have been proposed, but such approaches lack guarantees against… 34 arXiv — Machine Learning research 3d ago Modeling spatio-temporal locality in multi-step forecasting of geo-referenced time series arXiv:2608.25698v1 Announce Type: new Abstract: Forecasting future measurements from geographically distributed sensors is essential across many domains. However, the spatial distribution of these sensors raises multiple challenges, primarily due to spatial autocorrelation… 19 arXiv — Machine Learning research 3d ago Tropospheric temperature and humidity profile retrieval from Meteosat Flexible Combined Imager based on deep learning arXiv:2608.25700v1 Announce Type: new Abstract: The Meteosat Third Generation (MTG) Flexible Combined Imager (FCI) offers new opportunities for tropospheric temperature and humidity profiling, at higher spatio-temporal resolutions and expanded spectral coverage relative to its… 7 arXiv — Machine Learning research 3d ago Fairness-Aware Test-Time Prompt Tuning arXiv:2608.25707v1 Announce Type: new Abstract: Vision-language models have displayed remarkable capabilities in multi-modal understanding and are increasingly used in critical applications where economic and practical deployment constraints prohibit re-training or fine-tuning.… 25 arXiv — Machine Learning research 3d ago It's a matter of timescale: non-linear utility in successor features and multi-objective planning and learning arXiv:2608.25723v1 Announce Type: new Abstract: Time is of the essence when dealing with multiple reward signals and non-linear utility. In this paper we argue that the current main approaches in multi-objectiveRL (SER and ESR), and successor features, are insufficient. While… 28 arXiv — Machine Learning research 3d ago Are LLM-Enhanced GNNs Privacy-Safe? arXiv:2608.25727v1 Announce Type: new Abstract: Large language models (LLMs) have recently advanced graph neural networks (GNNs) by enriching node representations with semantic information, giving rise to LLM-enhanced GNNs that achieve substantial performance gains. However,… 7 arXiv — NLP / Computation & Language research 3d ago Why Does Graph Learning Fail to Fully Benefit from a Text Teacher? arXiv:2608.25741v1 Announce Type: cross Abstract: Graph neural networks (GNNs) are widely used to represent complex interactions and relationships among entities. We investigate a multimodal model that combines two complementary ideas: a self-supervised method that enables a GNN… 27 arXiv — Machine Learning research 3d ago A Constitutive Markov Physics-Informed Neural Operator (MPNO) for Autoregressive Stability in Transient Dynamics arXiv:2608.25744v1 Announce Type: new Abstract: Neural operators applied to transient-dynamics PDEs with strong discontinuities exhibit autoregressive instability: in concrete-penetration stress-field prediction, the wavelet neural operator (WNO) diverges in autoregressive… 33 arXiv — Machine Learning research 3d ago Comparing Corrupted Constrained Learning Problems arXiv:2608.25745v1 Announce Type: new Abstract: A key result in statistics is the data processing inequality, originally proved by Blackwell (1951) and later refined by DeGroot (1962) in terms of statistical uncertainty. It states that the Bayes risk of a statistical experiment… 27 arXiv — Machine Learning research 3d ago TailSFT: Filtered Fine-Tuning Improves Post-Training Performance arXiv:2608.25756v1 Announce Type: new Abstract: Reinforcement learning post-training drives reasoning and agentic capabilities in modern AI systems, yet a growing body of work shows that it is most effective when used to fine-tune an already capable base model. We question… 37 arXiv — Machine Learning research 3d ago Learning from waste: Machine Learning for health risk prediction and computer vision-based sorting in Ghana arXiv:2608.25759v1 Announce Type: new Abstract: The inappropriate disposal of solid waste remains a significant public health and environmental concern worldwide, including in Ghana. Poor sanitation and improper waste management practices contribute to substantial economic costs… 15 arXiv — Machine Learning research 3d ago Drift-Aware Multimodal User Representation Learning via Multi-Scale Temporal Modeling and Sparse Mixture-of-Experts arXiv:2608.25773v1 Announce Type: new Abstract: Understanding user preferences from noisy and temporally evolving social media behaviors is fundamentally challenging due to interest drift, where user preferences shift across time and exhibit both multi-scale temporal patterns… 12 arXiv — Machine Learning research 3d ago EXAONE Tabular 1.0 : Technical Report arXiv:2608.25774v1 Announce Type: new Abstract: EXAONE Tabular is a compact tabular foundation model family for classification and regression via in-context learning, producing predictions without dataset-specific gradient updates. Pretrained exclusively on a synthetic… 4 arXiv — Machine Learning research 3d ago Cooperative Multi-Agent Reinforcement Learning for Adaptive Aggregation in Semi-Supervised Federated Learning with non-IID Data arXiv:2608.25794v1 Announce Type: new Abstract: Federated Learning (FL) enables distributed training of machine learning models while preserving data privacy. However, FL struggles with heterogeneous, non-IID client data distributions, resulting in sub-optimal and biased global… 19 arXiv — Machine Learning research 3d ago Geometry-Constrained Kolmogorov-Arnold Networks: Learning Edge Geometry via Banach Duality arXiv:2608.25807v1 Announce Type: new Abstract: Kolmogorov-Arnold Networks (KANs) replace fixed activations in deep architectures with learnable univariate edge functions, making the choice of edge parametrisation central. Existing variants rely on fixed bases such as splines,… 30 arXiv — Machine Learning research 3d ago Canalization Before Generalization: Grokking as a Dynamical Probe arXiv:2608.25813v1 Announce Type: new Abstract: For overparameterized neural networks, many solutions can fit the training data equally well while behaving very differently on unseen samples. Grokking separates training fit from visible generalization, providing a window for… 25 arXiv — Machine Learning research 3d ago Learning Continuous Regional Temperature Fields with Lead-Time and Resolution Queries arXiv:2608.25823v1 Announce Type: new Abstract: Accurate regional near-surface temperature forecasting is fundamental to short-range weather services and downstream risk assessment. Existing deep learning-based regional forecasters commonly produce a fixed set of future frames… 24 arXiv — Machine Learning research 3d ago VINCENT: Validated Interaction Network for Cross-drug Explanation of Therapeutics arXiv:2608.25841v1 Announce Type: new Abstract: Drug synergy prediction estimates whether two drugs produce a stronger joint effect than expected from their individual activities. For drug combination discovery, a single synergy score is often not enough: researchers also need… 14 arXiv — Machine Learning research 3d ago CEDAR: Controlled and Event-Driven Demand Forecasting via Residual Decomposition arXiv:2608.25871v1 Announce Type: new Abstract: Forecasting in large-scale e-commerce marketplaces is increasingly required to support planning: merchants need to evaluate sales outcomes under future action sequences such as budget schedules, rather than passively predicting… 36 arXiv — Machine Learning research 3d ago How Edge of Stability Hinders SCAFFOLD in Federated Optimization arXiv:2608.25873v1 Announce Type: new Abstract: In federated learning, it is well known that heterogeneous data can (in theory) slow down optimization, and much effort has been directed at designing optimization algorithms that are unaffected by data heterogeneity, such as the… 17 arXiv — Machine Learning research 3d ago A General-Purpose Molecular Foundation Model Transfers Across Diverse Olfactory Tasks arXiv:2608.25893v1 Announce Type: new Abstract: Foundation models have transformed molecular property prediction, yet it remains unclear whether a molecular foundation model, fine-tuned on a single canonical olfactory prediction task, can learn representations that transfer… 21 arXiv — Machine Learning research 3d ago Towards A Unified Information Bottleneck Framework for Time Series Explanations arXiv:2608.25897v1 Announce Type: new Abstract: Explaining deep learning models operating on time series data is crucial in various applications that require transparent and interpretable insights into model behavior. {Existing explanation methods generally fall into two… 12 arXiv — Machine Learning research 3d ago Forecasting Multiple Observables with SCROLL: Score-Trained Uncertainty for Stochastic Dynamics arXiv:2608.25898v1 Announce Type: new Abstract: Forecasting a stochastic dynamical system rarely means a single number: one wants several observables---future state, threshold event, regime label---each with its own likelihood. Standard multi-task recipes balance per-task… 24 arXiv — Machine Learning research 3d ago Quantum-Inspired Modeling of Driving Behavior arXiv:2608.25907v1 Announce Type: new Abstract: Driver behavior is heterogeneous, context-dependent, and changes over time, and these properties shape the traffic phenomena we observe. Most models, however, fix in advance which behavioral variables interact and how. Behavior… 34 arXiv — Machine Learning research 3d ago One Symptom, Three Levers: A Critical Review of On-Policy Self-Distillation arXiv:2608.25936v1 Announce Type: new Abstract: On-policy distillation trains a language model on its own generations while a teacher scores them token by token. It combines the dense supervision of imitation learning with the on-policy sampling of reinforcement learning. But it… 32 arXiv — Machine Learning research 3d ago When Pruning Meets Interpretability: Preserving Sparse Autoencoder Robustness in LLMs arXiv:2608.25941v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are widely used to interpret the internal representations of large language models (LLMs), yet their reliability under post-hoc model compression remains poorly understood. We present a systematic study… 17 arXiv — Machine Learning research 3d ago Spectral Allocation: Why Muon Outperforms Adam, and How to Improve Muon arXiv:2608.25990v1 Announce Type: new Abstract: Orthogonal optimisers such as Muon can substantially accelerate large language model pretraining relative to Adam, yet the mechanism remains incompletely understood. We investigate this through an out-of-sample spectral probing… 23 arXiv — Machine Learning research 3d ago DualOPSD: Adaptive Privileged Teachers for On-Policy Self-Distillation arXiv:2608.26019v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) uses a privileged copy of the student model to provide dense supervision without an external teacher. OPSD keeps this privileged teacher fixed, even though the student distribution and output… 36 arXiv — Machine Learning research 3d ago Robust CurveMoE: Multi-Norm Adversarial Defense for Mixture-of-Experts Models via Mode Connectivity arXiv:2608.26043v1 Announce Type: new Abstract: Multi-norm adversarial defense aims to protect neural networks against perturbations defined by different norm constraints, but existing methods typically optimize competing robustness objectives within a single parameter… 25 arXiv — NLP / Computation & Language research 3d ago Detection != Reliable Control: Decodable Empathy Directions Yield at Most Partial Shifts in Automated Empathy Scores arXiv:2608.24901v1 Announce Type: new Abstract: A decodable "empathy" direction is routinely read as a causal lever, conflating decodability, automated-metric control, and human-perceived change. We test this for two EPITOME-derived facets -- Recognition (cognitive) and… 10 arXiv — NLP / Computation & Language research 3d ago Semantic Variability of Replies Across LLMs: Implications for Designing Conversation-Based Assessment arXiv:2608.24920v1 Announce Type: new Abstract: This study examines whether LLM-generated replies remain semantically consistent when the underlying LLM changes. Using messages from real collaborative conversations, we compared the semantic similarity of generated replies across… 31 arXiv — NLP / Computation & Language research 3d ago The Dialect Tax: Dialectal Biases Persist throughout the Language Modeling Pipeline arXiv:2608.24952v1 Announce Type: new Abstract: Systematic dialectal performance gaps in language models (LMs) are well documented, but the source of these disparities within the modern language modeling pipeline remains unclear. Our study traces this "dialect tax" across the… 34 arXiv — NLP / Computation & Language research 3d ago Unsupervised Post-Training of Foundation Models: A Survey arXiv:2608.24982v1 Announce Type: new Abstract: Foundation-model post-training usually relies on human labels, preference data, stronger teachers, or executable verifiers. We study Unsupervised Post-Training (UPT): update-bearing adaptation on unlabeled inputs whose learning… 11 arXiv — NLP / Computation & Language research 3d ago Does Fine-Tuning Undo Activation Steering? Behavioural Recovery Without Weight-Edit Reversal arXiv:2608.24988v1 Announce Type: new Abstract: Activation steering can be embedded directly into a language model's weights, shaping behaviour without inference-time intervention and offering a way to encode alignment prior to release. However, models are routinely fine-tuned… 28 arXiv — NLP / Computation & Language research 3d ago The Imperfective Paradox Is Not Necessarily in Large Language Models: A Benchmark Failure Before a Model Failure arXiv:2608.25005v1 Announce Type: new Abstract: The imperfective paradox provides a useful test of compositional semantic analysis. Recent work constructs an NLI benchmark and reports that models frequently infer completed telic events from progressive descriptions, attributing… 14 Page 6 of 10 · 500 articles ← Newer Older →
