News / #paper Tag Research papers 500 articles archived under #paper · RSS Sign in to follow arXiv — Machine Learning research 5d ago Coverage, Not Difficulty, Sets How Much Synthetic Data an Activation Probe Needs arXiv:2610.10594v1 Announce Type: new Abstract: Activation probes that monitor deployed language models are trained on synthetic conversations, and how many a probe needs is open. We trace learning curves over 10-590 synthetic samples for three monitoring concepts, high-stakes… 7 arXiv — Machine Learning research 5d ago Temporal transformer CAN encoder with federated lightweight heads for anomaly detection arXiv:2610.10613v1 Announce Type: new Abstract: Modern vehicles rely on large numbers of Electronic Control Units (ECUs) that constantly exchange information over the Controller Area Network (CAN) bus. Due to the rapidity, structure, and repetition of this communication, even… 14 arXiv — Machine Learning research 5d ago When Routing Reveals Membership: Privacy Leakage from MoE Router Telemetry arXiv:2610.10616v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) language models produce routing information during inference that may be logged or exposed for monitoring, debugging, load analysis, and safety auditing. Unlike ordinary model outputs, this telemetry… 16 arXiv — Machine Learning research 5d ago Self-Organization from Constrained Geometric Radiation arXiv:2610.10621v1 Announce Type: new Abstract: How does dynamic order emerge spontaneously in closed systems without external driving? Existing paradigms all require external energy flows, temperature quenching, or slow driving. Here we report constraint-induced… 24 arXiv — NLP / Computation & Language research 5d ago Recurrent Self-Improvement: Dynamic Cross-Loop On-Policy Distillation for Looped Language Models arXiv:2610.10623v1 Announce Type: cross Abstract: Looped Language Models (LoopLMs) offer a parameter efficient approach to scaling reasoning by reusing shared parameters across recurrent computation steps. Despite their promise, effective post-training of LoopLMs remains… 14 arXiv — Machine Learning research 5d ago Exact SO(3)-Equivariant Isotropic Kernels for Rotation-Robust Neural Dynamics arXiv:2610.10626v1 Announce Type: new Abstract: Neural surrogates for vector-valued partial differential equations can fit training data yet change their predictions when the same physical state is expressed in a rotated coordinate frame. We study this failure on… 33 arXiv — Machine Learning research 5d ago Sample-Efficiency of Kolmogorov-Arnold Networks arXiv:2610.10627v1 Announce Type: new Abstract: Deep reinforcement learning has achieved substantial performance gains over classical control approaches. Yet, a central challenge to learning in real-world applications is acquiring costly samples. Kolmogorov-Arnold Networks are a… 23 arXiv — Machine Learning research 5d ago Phase-HDC: Replacing Optimizer History with Gradient Thresholds in Discrete Phase Learning arXiv:2610.10630v1 Announce Type: new Abstract: Training a compact model often needs far more memory than storing it, because the optimizer keeps its own records of past gradients. For a hyperdimensional classifier whose learned parameters are low-bit angles, which we call a… 27 arXiv — Machine Learning research 5d ago D-SLR: The Disjoint Row-Sparse plus Low-Rank Decomposition arXiv:2610.10636v1 Announce Type: new Abstract: Compressing a matrix for reconstruction still defaults to the truncated SVD, approximating the data with a single low-rank structure. It is common to reduce the residual further by adding an overlapping row-sparse component, but… 29 arXiv — Machine Learning research 5d ago Visible Reasoning Is Not a Universal Optimizer: Persona- and Thinking-Dependent Effects in Analytics Code Generation arXiv:2610.10639v1 Announce Type: new Abstract: Visible Chain-of-Thought (CoT) is often treated as a broadly useful reasoning instruction, yet analytics code generation combines natural-language ambiguity, schema grounding, target-language constraints, and model-specific… 25 arXiv — Machine Learning research 5d ago Coverage-Aware Reasoning with Medical Tokens for Diagnosis Prediction arXiv:2610.10641v1 Announce Type: new Abstract: Large language models (LLMs) offer promising potential for next-visit diagnosis prediction, owing to their ability to integrate longitudinal clinical evidence and reason over it in natural language. However, reinforcement learning… 11 arXiv — Machine Learning research 5d ago Leakage-Controlled Multimodal Learning for Diagnosis and Progression Prediction in Alzheimer's Disease Research arXiv:2610.10648v1 Announce Type: new Abstract: Alzheimer's disease prediction involves irregular visits, heterogeneous measurements and incomplete modalities. This study presents a multimodal multitask framework combining an adapted SFCN MRI encoder, four causal clinical… 27 arXiv — Machine Learning research 5d ago Beyond the Ergodic Wall: A Discrete Geometric Physics Sandbox for Analysing AI Scaling Limits and Complexity Collapse arXiv:2610.10651v1 Announce Type: new Abstract: This paper exposes the ergodic ceiling and thermodynamic inefficiency of current deep learning, which converges to a statistical average of historic human knowledge. True semantic novelty requires a path-dependent, spatiotemporally… 33 arXiv — Machine Learning research 5d ago PXtal: Learning to Align Powder X-Ray Diffraction and Crystal Structures under Information Asymmetry across Modalities arXiv:2610.10653v1 Announce Type: new Abstract: Scientific multimodal learning commonly assumes that paired views are comparably informative. Powder X-ray diffraction (PXRD) makes this mismatch explicit: compressing a three-dimensional crystal structure into a one-dimensional… 25 arXiv — Machine Learning research 5d ago Nullify: Null-Space Activation Steering for Training-Free LLM Unlearning arXiv:2610.10655v1 Announce Type: new Abstract: Large Language Models (LLMs) inevitably internalize substantial amounts of sensitive or private information during pre-training, while LLM unlearning aims to selectively erase specific knowledge to prevent privacy leakage with… 30 arXiv — Machine Learning research 5d ago Beyond Owls: Subliminal Learning Can Transfer Learned Capabilities and Backdoors arXiv:2610.10657v1 Announce Type: new Abstract: In subliminal learning (SL), a teacher model passes on a trait to a student model by distillation on data semantically unrelated to the trait. So far, SL has been demonstrated for only a limited range of traits, including… 6 arXiv — Machine Learning research 5d ago Teaching PPG How not Who: Fixed-Effects Distillation from ECG arXiv:2610.10662v1 Announce Type: new Abstract: ECG is widely used to teach PPG-only models, yet what it teaches is unexamined. Wearables are valued for tracking how a person's cardiovascular state changes, but ECG-to-PPG distillation mostly learns who the person is. A… 9 arXiv — Machine Learning research 5d ago Explaining the Saliency Map Sparsity of Adversarially-Trained Neural Networks arXiv:2610.10666v1 Announce Type: new Abstract: Understanding why deep neural networks make a given prediction is of great importance for their safe deployment. In computer vision, saliency maps, which highlight the image region most influential for a prediction, remain a… 7 arXiv — Machine Learning research 5d ago Learning infinite context windows in recurrent architectures via spatial neural computing arXiv:2610.10690v1 Announce Type: new Abstract: Recurrent neural networks (RNNs) offer linear-time scaling with sequence length while requiring only constant memory, yet they struggle to capture long-range dependencies due to vanishing gradients and limited receptive fields. To… 35 arXiv — NLP / Computation & Language research 5d ago Conversational Task Disambiguation over Tabular Data: Leakage-Aware Formulation, Benchmark Suite, and Training arXiv:2610.10740v1 Announce Type: cross Abstract: Conversational task disambiguation over tabular data uses dialogue to resolve missing information about a user's intended task before producing a solution over tables or databases. Existing evaluation and training lack a… 18 arXiv — Machine Learning research 5d ago NEMORA: Neural Equivariant Multipole Operators for Long-Range Atomistic Learning arXiv:2610.10776v1 Announce Type: new Abstract: Equivariant graph neural networks have emerged as foundational architectures for machine-learned interatomic potentials, approaching quantum-chemical accuracy at a fraction of the computational cost. These models describe local… 34 arXiv — Machine Learning research 5d ago MemoWM: How World Models Change What Agents Need to Remember arXiv:2610.10778v1 Announce Type: new Abstract: Long-term agents face growing storage demands as they accumulate experience. World models capture reusable regularities that can reduce the information stored for each experience. We formulate the problem of memory allocation… 16 arXiv — Machine Learning research 5d ago How Many Repeated Pairwise Comparisons Are Needed for Ranking under Heterogeneity? arXiv:2610.10795v1 Announce Type: new Abstract: We study ranking models by population-average utility from pairwise comparisons when preferences vary across users and tasks. Prior work shows that a single comparison per user can be insufficient to identify the alternative with… 5 arXiv — Machine Learning research 5d ago Symbolic Density Estimators for Unnormalized Distributions arXiv:2610.10807v1 Announce Type: new Abstract: Estimating the symbolic or analytical form of probability density functions (PDFs) from observed samples is a fundamental challenge in statistical and computational modelling. This process is critical for deriving interpretable and… 7 arXiv — Machine Learning research 5d ago Controlled Acquisition and Abstention in Three-Channel Score Conflicts arXiv:2610.10808v1 Announce Type: new Abstract: When audio, video, and text disagree, accuracy alone does not show whether to acquire another source or abstain. We study these choices in a controlled three-score benchmark: a policy observes two signed scores, may request the… 5 arXiv — Machine Learning research 5d ago Evaluating Rubric Generation with Interventional Transfer arXiv:2610.10809v1 Announce Type: new Abstract: Instance-specific rubrics are common in AI benchmarks where reliable evaluation requires specific expert knowledge. This approach is difficult to scale, prompting research into the generation of rubrics with large language models… 4 arXiv — Machine Learning research 5d ago MotherTree: Meta-learning on synthetic data improves decision tree training arXiv:2610.10832v1 Announce Type: new Abstract: Conventional decision tree algorithms produce effective, transparent models that can be audited, communicated, and deployed independently of the training data, but require learning every new task from scratch. In contrast, tabular… 18 arXiv — Machine Learning research 5d ago Amortized Off-Policy Evaluation for LLMs arXiv:2610.10848v1 Announce Type: new Abstract: Accurate evaluation is central to selecting which LLM to deploy, yet testing a candidate on live traffic exposes real users to an unvetted model. Teams therefore evaluate candidates offline, on data produced by already-deployed… 16 arXiv — Machine Learning research 5d ago Similar Predictive Fit but Different Latent Dynamics: Characterizing Learned Dynamical Structure in Personalized Models of Brain Disorders arXiv:2610.10850v1 Announce Type: new Abstract: As AI models move toward clinical decision-making and personalized treatment, understanding \emph{what} a model learns is important beyond predictive accuracy alone. We investigate whether personalized latent dynamics reveal… 15 arXiv — Machine Learning research 5d ago KDFP: A first-principles approach to knowledge distillation in large language models arXiv:2610.10854v1 Announce Type: new Abstract: Knowledge distillation is an established technique for improving the capabilities of small, efficient student models by training them with the representations of larger, more capable teacher models. Much of the recent work in the… 11 arXiv — Machine Learning research 5d ago Shape irregularity of Life-Like Network Automaton rules as an indicator of classification performance arXiv:2610.10867v1 Announce Type: new Abstract: Complex Network (CN) classification requires high-level structural characterizations that are both scale-invariant and computationally efficient. Methods based on Life-Like Network Automata (LLNA) offer an interesting way to… 23 arXiv — Machine Learning research 5d ago Barron Optimal Transport I: Generative Modeling arXiv:2610.10875v1 Announce Type: new Abstract: Motivated by recent applications in generative modeling and sampling, we introduce a framework for optimal measure transport where cost captures the notion of neural network complexity. In transport-based generative models, samples… 23 arXiv — Machine Learning research 5d ago Gen-PINNs: Generative Adversarial Physics Informed Neural Networks for solving partial differential equations arXiv:2610.10897v1 Announce Type: new Abstract: Physics-Informed Neural Networks (PINNs) are a widely used data-free method for solving Partial Differential Equations (PDEs) using machine learning. With recent advances in Generative Adversarial Networks (GANs), adversarial… 12 arXiv — Machine Learning research 5d ago How Hackable Is Your Speech Quality Metric? A Corrected Protocol, a Benchmark, and What Patching Buys arXiv:2610.10899v1 Announce Type: new Abstract: Speech quality predictors are increasingly used as rewards, yet no agreed measure of their hackability exists. The usual measurement has two flaws. First, the perturbation reaches the predictor through a processing chain -- here a… 31 arXiv — NLP / Computation & Language research 5d ago Language Models for Page-Level Layout Decisions in E-commerce Search arXiv:2610.10920v1 Announce Type: cross Abstract: E-commerce search pages are critical touchpoints for millions of online shoppers. While traditional search engines return a ranked list of results, modern E-commerce search pages increasingly incorporate recommender system… 14 arXiv — Machine Learning research 5d ago Adaptive Multi-Discriminator WGAN Framework for Resource-Constrained Internet of Vehicles Using Reinforcement Learning and Game Theory arXiv:2610.10926v1 Announce Type: new Abstract: Managing machine learning workloads as a network service introduces a resource-orchestration problem distinct from conventional model training; which nodes should be allocated to a task, how communication and computation budgets… 36 arXiv — Machine Learning research 5d ago Coefficient Calibration as Selection Pressure in Symbolic Regression arXiv:2610.10931v1 Announce Type: new Abstract: In memetic symbolic regression, candidate structures are compared after coefficient calibration, so the calibration protocol itself contributes to evolutionary selection. Standard centralized calibration evaluates each structure at… 24 arXiv — Machine Learning research 5d ago World-Model Policy Arbiter for Goal-Conditioned Reinforcement Learning arXiv:2610.10932v1 Announce Type: new Abstract: Offline goal-conditioned reinforcement learning (GCRL) has produced a diverse set of goal-reaching algorithms, yet no single algorithm performs best across environments, goals, and even different phases of the same task. Rather… 8 arXiv — Machine Learning research 5d ago Rethinking the Tradeoff Between Temporal Encoding and Nonlinear Computation in Spiking Language Models arXiv:2610.10933v1 Announce Type: new Abstract: Spiking language models face a tradeoff between representing continuous semantic features over short temporal windows and retaining costly nonlinear attention operations. We introduce Spora, which jointly designs spike encodings… 9 arXiv — Machine Learning research 5d ago RH-Detect: A Unified Benchmark for Reward Hacking Detection arXiv:2610.10947v1 Announce Type: new Abstract: Reward hacking, where a model exploits an evaluation signal without completing the intended task, threatens the reliability of deployed language model systems. Existing datasets use different labels, response formats, and metadata… 16 arXiv — Machine Learning research 5d ago SPD-MetaFormer is what you need for small-data brain decoding arXiv:2610.10952v1 Announce Type: new Abstract: Brain signal decoding is challenging because neural recordings are noisy and vary across individuals, while labeled data are often limited. Recent attention-based models on the symmetric positive definite (SPD) manifold have… 22 arXiv — Machine Learning research 5d ago TRACE: A Governance Framework for Measuring Explainability Debt in Production AI Systems arXiv:2610.10957v1 Announce Type: new Abstract: Production AI systems deployed in high-stakes domains accumulate a governance liability that existing monitoring frameworks fail to detect: the progressive inability to explain individual decisions when regulators, auditors, or… 30 arXiv — Machine Learning research 5d ago Spectrally Targeted Muon arXiv:2610.10965v1 Announce Type: new Abstract: The Muon optimizer orthogonalizes each update matrix, setting all of its singular values to one, and has proven highly effective for training large language models. It remains unclear, however, whether this success comes from… 12 arXiv — Machine Learning research 5d ago ASPIRE: Saddle-Point Discovery through Set Prediction and Physical Refinement arXiv:2610.10969v1 Announce Type: new Abstract: Predicting thermally activated diffusion and defect evolution with event-driven models requires identifying atomic rearrangement mechanisms and their activation barriers. Discovering the associated saddle points is a major… 11 arXiv — Machine Learning research 5d ago Transferability of Learned States in Neural PDE Solvers arXiv:2610.10972v1 Announce Type: new Abstract: Assessing useful reuse in neural PDE solvers is challenging: final accuracy can reflect source learning and target-time computation. Our reuse contract separates solution accuracy, learning contribution, and numerical utility… 4 arXiv — Machine Learning research 5d ago Budgeted Multi-Source Counterfactual Annotation for Off-Policy Evaluation arXiv:2610.10974v1 Announce Type: new Abstract: Off-policy evaluation (OPE) estimates the value of a target policy from logged data, but limited behavior-policy coverage can force high-variance reweighting or reward-model extrapolation. Counterfactual annotations can add… 38 arXiv — Machine Learning research 5d ago Optimizing Large Language Models with Chained LMOs arXiv:2610.10975v1 Announce Type: new Abstract: Muon has motivated a growing family of optimizers that compose multiple matrix normalizations, but these methods remain fragmented and lack a unified perspective. We introduce chained linear minimization oracles (chained LMOs),… 33 arXiv — Machine Learning research 5d ago Multi-Bandwidth Distribution Matching Distillation: On the Equivalence of Distribution Matching Distillation and Drifting Models arXiv:2610.10989v1 Announce Type: new Abstract: Researchers are exploring effective one-step generative model continuously, and, Drifting Models (Deng et al., 2026), demonstrate great potential in one-step generation recently. There are works that reveal the connection between… 18 arXiv — Machine Learning research 5d ago Invariant-Measure Reasoners: Stable Representations for Latent Reasoning arXiv:2610.10996v1 Announce Type: new Abstract: Latent reasoning models repeatedly update a latent state using the same recurrent block. As the recurrent depth increases, the sequence of latent states may converge to a compact subset of the state space without necessarily… 18 arXiv — Machine Learning research 5d ago F$^3$NO: Frequency-Decomposed Finite-Time Flow-map Neural Operators with Cross-Scale Conditioning arXiv:2610.10998v1 Announce Type: new Abstract: Neural operators enable fast PDE forecasting, but repeated predictions accumulate errors and fine-scale structures remain difficult to resolve. We introduce a frequency-decomposed finite-time flow-map neural operator (F$^3$NO) that… 8 Page 5 of 10 · 500 articles ← Newer Older →
