News / #paper Tag Research papers 500 articles archived under #paper · RSS Sign in to follow arXiv — Machine Learning research 4h ago Accelerating Discrete Diffusion Models with Parallel-In-Time Sampling arXiv:2607.00773v1 Announce Type: new Abstract: Discrete diffusion models are widely used for learning and generating discrete distributions. As the generation process is inherently sequential, the acceleration of sampling is of significant importance. In this work, we… 25 arXiv — Machine Learning research 4h ago Which Metric Reflects the Spelling Rate Accuracy in Event-Related Potential-Based Brain-Computer Interfaces? arXiv:2607.00794v1 Announce Type: new Abstract: For predictive models, the often-reported performance metrics are the loss and accuracy. In synchronous Brain- Computer Interface (BCI) systems, these metrics are informative for most BCI paradigms; however, for Event-Related… 36 arXiv — Machine Learning research 4h ago Task-Relevant Representation Decoupling for Visual Reinforcement Learning Generalization arXiv:2607.00796v1 Announce Type: new Abstract: Visual Reinforcement Learning (VRL) has achieved considerable success in solving control tasks. However, generalizing learned policies to new environments remains a major challenge, as agents often overfit to task-irrelevant… 32 arXiv — Machine Learning research 4h ago Local Motion Matters: A Deconstruct-Recompose Paradigm for Reinforcement Learning Pre-training from Videos arXiv:2607.00808v1 Announce Type: new Abstract: Pre-training on large-scale videos to improve reinforcement learning efficiency is promising yet remains challenging. Existing methods typically treat the agent as an indivisible entity, modeling motion patterns globally. Such… 8 arXiv — Machine Learning research 4h ago From Pixels to Temporal Correlations: Learning Informative Representations for Reinforcement Learning Pre-training arXiv:2607.00811v1 Announce Type: new Abstract: Unsupervised pre-training on large-scale datasets has demonstrated significant potential for improving the sample efficiency and performance of Reinforcement Learning (RL). Given the large-scale action-free internet videos,… 13 arXiv — Machine Learning research 4h ago Spectroscopy Analysis with Machine Learning Regression for the Quantification of Carbon and Nitrogen Contents in Inceptisol and Oxisol Soil Types: Comparing Different Preprocessing and Validation methods as well as Feature Importance arXiv:2607.00834v1 Announce Type: new Abstract: Near-Infrared (NIR) spectroscopy has emerged as a promising alternative to traditional soil analysis methods, offering advantages such as speed, low cost, and non-destructive testing. This work proposes a machine learning (ML)… 9 arXiv — Machine Learning research 4h ago Constrained Bayesian Optimisation with Multiple Information Sources arXiv:2607.00865v1 Announce Type: new Abstract: Bayesian Optimisation (BO) under unknown constraints is particularly challenging when feasible regions are small. In such settings, existing methods that typically rely solely on evaluations of the true objective and constraints… 32 arXiv — Machine Learning research 4h ago Beyond Activation Alignment:The Alignment-Diversity Tradeoff in Task-Aware LLM Quantization arXiv:2607.00908v1 Announce Type: new Abstract: Mixed-precision quantization (MPQ) has become a key technique for deploying large language models under stringent memory and compute constraints. We first identify a phenomenon that we term the Perplexity Illusion: layers ranked as… 7 arXiv — Machine Learning research 4h ago Valdi: Value Diffusion World Models arXiv:2607.00917v1 Announce Type: new Abstract: World models can enable Model Predictive Control (MPC), but this requires dynamics prediction that is both fast enough for online use and expressive enough to represent uncertain futures. Diffusion models offer a natural mechanism… 18 arXiv — Machine Learning research 4h ago Human-Machine Collaboration on Generative Meta-Learning: Model and Algorithm arXiv:2607.00926v1 Announce Type: new Abstract: Generalizing machine learning models to environments that differ from their training distribution remains a critical hurdle, particularly when data from the target domain is entirely or partially unavailable. We propose Generative… 33 arXiv — Machine Learning research 4h ago Explainable AI for Cancer Drug Response Prediction: Beyond Univariate Feature Attributions arXiv:2607.00931v1 Announce Type: new Abstract: Predicting cancer drug response from transcriptomic profiles is a cornerstone of precision oncology, yet the scientific value of machine learning models hinges not solely on predictive accuracy, but also on their capacity to… 30 arXiv — Machine Learning research 4h ago Diffeomorphic Optimization arXiv:2607.00947v1 Announce Type: new Abstract: Generative models learn data distributions that reside on a low-dimensional manifold within a higher-dimensional ambient space. Optimizing differentiable objectives on this manifold is challenging: the ambient loss landscape is… 16 arXiv — Machine Learning research 4h ago Aionoscope: Debugging Latent-State Accessibility in Time-Series Representations arXiv:2607.00956v1 Announce Type: new Abstract: Time-series models are often evaluated by what they can forecast or classify, but those scores do not show whether their representations preserve the process state a user may want to inspect: event timing, phase, amplitude,… 7 arXiv — Machine Learning research 4h ago LeNEPA: No-Augmentation Next-Latent Prediction for Time-Series Representation Learning arXiv:2607.00958v1 Announce Type: new Abstract: Time series are central to modern data mining applications, from industrial telemetry and server metrics to finance and physiology, yet time-series self-supervised learning often depends on view and augmentation choices that encode… 14 arXiv — Machine Learning research 4h ago Automatic Detection of Stress from Speech in the Trier Social Stress Test arXiv:2607.00986v1 Announce Type: new Abstract: Automatically detecting stress in speech provides an unobtrusive way to gain insights relevant to behavioral research or clinical assessment. This study investigates the automatic differentiation between a stressful and… 12 arXiv — Machine Learning research 4h ago Generative Model Proposal based Particle Filtering for Data Assimilation arXiv:2607.01012v1 Announce Type: new Abstract: Data assimilation models state dynamics conditioned on sequential observations, and has wide-ranging scientific applications. In the filtering setting, the goal is to model the posterior over the current state given all… 21 arXiv — Machine Learning research 4h ago Seahorse: A Unified Benchmarking Framework for Spatiotemporal Event Modeling arXiv:2607.01022v1 Announce Type: new Abstract: Spatiotemporal point processes (STPPs) model event data in continuous time and space, with applications in mobility, epidemiology, and public safety. Recent neural STPPs span expressive intensity models, conditional density models,… 14 arXiv — Machine Learning research 4h ago The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology arXiv:2607.01033v1 Announce Type: new Abstract: Model organisms (MOs) - language models trained to exhibit undesired or unnatural behaviours - are frequently used as testbeds for evaluating white-box interpretability techniques. Current MOs are typically constructed via post-hoc… 10 arXiv — Machine Learning research 4h ago GSRQ: Gain-Shape Residual Quantization for Sub-1-bit KV Cache arXiv:2607.01065v1 Announce Type: new Abstract: The deployment of Large Language Models (LLMs) with extended context windows is increasingly constrained by the linear growth of Key-Value (KV) cache memory. Vector Quantization (VQ), particularly Residual Quantization (RQ), is a… 36 arXiv — Machine Learning research 4h ago Balancing Expressivity and Learnability in Quantum Kernel Bandit Optimization arXiv:2607.01080v1 Announce Type: new Abstract: We investigate Gaussian process (GP) bandit optimization with quantum kernels, assuming the mean reward function lies in the reproducing kernel Hilbert space (RKHS) induced by the quantum kernel. This setting is motivated by… 6 arXiv — Machine Learning research 4h ago When Context Compensates for Sparse Event History: AlphaEarth for Spatio-Temporal Point-Process Forecasting arXiv:2607.01082v1 Announce Type: new Abstract: Spatio-temporal point-process models must often generalise across space when local event histories are sparse. We study whether exogenous spatial context can compensate in such regimes. Using a fixed log-Gaussian Cox process… 32 arXiv — Machine Learning research 4h ago Staleness-Learning Rate Scaling Laws for Asynchronous RLHF arXiv:2607.01083v1 Announce Type: new Abstract: High-throughput RLHF systems often decouple rollout generation from policy optimization, leading to the use of stale rollouts during learner updates. In this work, we study the effect of such staleness in asynchronous GRPO. We make… 23 arXiv — NLP / Computation & Language research 4h ago CausalMix: Data Mixture as Causal Inference for Language Model Training arXiv:2607.01104v1 Announce Type: cross Abstract: In Large Language Model (LLM) training, data mixing plays a pivotal role in determining model performance. Recent methods optimize mixture weights via proxy models, but they rely on the assumption of static data distributions. As… 31 arXiv — Machine Learning research 4h ago SynLaD: Latent Diffusion for Generating Synthesizable Molecules Conditioned on 3D Pharmacophore Profiles arXiv:2607.01105v1 Announce Type: new Abstract: We present SynLaD, a latent diffusion framework for small-molecule generation that unifies ligand-based drug design objectives (what to make) with synthetic accessibility (how to make it). Current models typically optimize one… 10 arXiv — Machine Learning research 4h ago Muon as a Residual Connection arXiv:2607.01124v1 Announce Type: new Abstract: Muon has recently emerged as one of the most effective optimizers for training large neural networks, yet its empirical success has been explained from several different perspectives. In this paper, we propose a simple mechanistic… 6 arXiv — Machine Learning research 4h ago ZO-Act: Efficient Zeroth-Order Fine-Tuning via One-Shot Activation-Informed Low-Rank Subspaces arXiv:2607.01125v1 Announce Type: new Abstract: Zeroth-order (ZO) optimization enables fine-tuning large language models when backpropagation is unavailable or memory-prohibitive, but existing methods often perturb full model weights or randomly constructed low-dimensional… 4 arXiv — Machine Learning research 4h ago GAIA: Geometry-Adaptive Operator Learning for Forward and Inverse Problems arXiv:2607.01128v1 Announce Type: new Abstract: Operator learning for partial differential equations (PDEs) on arbitrary geometries builds fast neural surrogates for large-scale simulation. Although recent geometry-adaptive neural operators have made substantial progress, they… 17 arXiv — Machine Learning research 4h ago Sequentially-Controlled Interactive Multi-Particle Flow-Maps for Online Feedback-Driven Search arXiv:2607.01144v1 Announce Type: new Abstract: While generative models have enabled training-free reward alignment, current methods typically excel in local exploration within narrow regions of the underlying distribution. These approaches struggle when preferences are unknown… 16 arXiv — Machine Learning research 4h ago A Lightweight Self-Supervised Learning Framework for Multivariate Time Series using Hierarchical-JEPA on ECG Data arXiv:2607.01145v1 Announce Type: new Abstract: Data analysis in the medical domain often encounters scenarios involving a limited target dataset and a large, unannotated dataset with a general distribution. Under such circumstances, self-supervised learning (SSL) methods are… 31 arXiv — Machine Learning research 4h ago Efficient Compression of Structured and Unstructured Volumes via Learned 3D Gaussian Representation arXiv:2607.01164v1 Announce Type: new Abstract: Recent work has shown that implicit neural representations (INRs) can be trained to effectively compress structured and unstructured volume data, allowing for direct data querying with a reduced memory footprint. However, as… 36 arXiv — Machine Learning research 4h ago Decision-Aware Training for Sample-Based Generative Models arXiv:2607.01171v1 Announce Type: new Abstract: Sample-based generative models are increasingly used for probabilistic forecasting in high-stakes decision settings, yet their training objectives are blind to the decision maker's cost structure. These models are commonly trained… 5 arXiv — NLP / Computation & Language research 4h ago QuasiMoTTo: Quasi-Monte Carlo Test-Time Scaling arXiv:2607.01179v1 Announce Type: cross Abstract: Scaling inference compute, by generating many parallel attempts per problem, is a costly but reliable lever for improving language model capabilities. By default these attempts are generated independently, wasting inference… 36 arXiv — NLP / Computation & Language research 4h ago Right in the Right Way: LM Training with Verifiable Rewards and Human Demonstrations arXiv:2607.01181v1 Announce Type: cross Abstract: RL with verifiable rewards (RLVR) has emerged as a powerful paradigm for training LMs on tasks with well-defined success metrics, such as code generation and mathematical reasoning. However, current RLVR methods optimize only… 25 arXiv — Machine Learning research 4h ago Neural Certificate Pricing for Combinatorial Optimization Problems arXiv:2607.01185v1 Announce Type: new Abstract: Combinatorial optimization (CO) problems are difficult because certifiable discrete structure induces exponential search. One needs to search over the set exponentially many candidates to certify optimality, however, the structural… 23 arXiv — Machine Learning research 4h ago Quantum vs. Classical Machine Learning: A Unified Empirical Comparison arXiv:2607.01197v1 Announce Type: new Abstract: Quantum computing has emerged as a promising computational paradigm for machine learning (ML), with the potential to offer computational advantages over classical approaches. At this stage, the evidence supporting the performance… 25 arXiv — Machine Learning research 4h ago TiRex-2: Generalizing TiRex to Multivariate Data and Streaming arXiv:2607.01204v1 Announce Type: new Abstract: We introduce TiRex-2, a recurrent xLSTM-based time series foundation model that generalizes the univariate TiRex to multivariate forecasting with both past and future covariates. Real-world forecasting is inherently sequential:… 17 arXiv — Machine Learning research 4h ago Language-Critique Imitation Learning from Suboptimal Demonstrations arXiv:2607.01225v1 Announce Type: new Abstract: Prior work on imitation learning from suboptimal demonstrations typically relies on compressed supervision signals such as confidence estimates, discriminator scores, or importance weights. These scalar signals are inherently… 32 arXiv — NLP / Computation & Language research 4h ago Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training arXiv:2607.01232v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a central component of post-training large language models (LLMs), yet little is understood about how RL adaptation is distributed across transformer layers. Existing approaches typically… 7 arXiv — Machine Learning research 4h ago Why Advanced Encoders Lag on Sparse Retrieval? The Answer and an Approach to Bridging Vocabulary Gaps arXiv:2607.00004v1 Announce Type: cross Abstract: While advanced foundation models like ModernBERT significantly outperform older architectures in dense retrieval, they surprisingly lag behind the aging BERT-base baseline in learned sparse retrieval (LSR). We identify the root… 16 arXiv — Machine Learning research 4h ago Urban Deceleration Behavior Modes Under Scene Context: An Early-Kinematic Classifier from Argoverse 2 Multi-Agent Trajectories arXiv:2607.00027v1 Announce Type: cross Abstract: Urban deceleration is one of the most empirically studied yet least taxonomically organized behaviors in car-following research. Recent perception-equipped autonomous-vehicle datasets enable trajectory-anchored mode discovery. We… 18 arXiv — Machine Learning research 4h ago Spatio-Temporal Gaussian Process for Building Terrain-Incorporating Wind Power Curves arXiv:2607.00051v1 Announce Type: cross Abstract: Accurate modeling of wind turbine power curves is crucial for optimal wind farm operation. Nearly all existing power curve models focus on temporal variables such as wind speed and temperature while overlooking the influence of… 16 arXiv — NLP / Computation & Language research 4h ago Harnessing the Latent Space: From Steering Vectors to Model Calibrators for Control and Trust arXiv:2607.00083v1 Announce Type: new Abstract: Language models have changed from unreliable text generators to highly-capable large models with trillions of parameters. Capability increases come hand-in-hand with increases in scale, making understanding the internal… 36 arXiv — NLP / Computation & Language research 4h ago CogTax: A Four-Level Cognitive Taxonomy for Command-Line Computing Education arXiv:2607.00140v1 Announce Type: cross Abstract: As computing education expands beyond traditional programming into operational domains such as systems administration and command-line environments, existing pedagogical frameworks struggle to capture a dimension that is critical… 12 arXiv — Machine Learning research 4h ago A Mechanism-Driven Theory of Phase Transitions in Active Learning arXiv:2607.00144v1 Announce Type: cross Abstract: Active learning (AL) performance is known to be budget-dependent, yet regimes are typically defined by heuristic label counts that fail to generalize across datasets or architectures. We characterize AL dynamics by reframing… 12 arXiv — Machine Learning research 4h ago Steal the Patch Size: Adversarially Manipulate Vision-Language Models arXiv:2607.00174v1 Announce Type: cross Abstract: We present a black-box model-stealing attack that recovers private vision-tokenizer configurations of deployed vision-language models (VLMs), including the visual patch size and input preprocessing pipeline. The key idea is a… 34 arXiv — Machine Learning research 4h ago HydraCollab: Adaptive Collaborative-Perception for Distributed Autonomous Systems arXiv:2607.00191v1 Announce Type: cross Abstract: Collaborative-perception enables multi-robot systems to enhance situational awareness by sharing perceptual information. Existing collaborative-perception systems face an inherent trade-off between communication bandwidth… 22 arXiv — Machine Learning research 4h ago Homogenization of $\ell_2$-Adversarial Training in High-Dimensions: Exact Dynamics under Stochastic Gradient Descent arXiv:2607.00207v1 Announce Type: cross Abstract: We develop a framework for analyzing the learning dynamics of $\ell_2$-adversarial training of single-index models on Gaussian mixtures in the high-dimensional limit under streaming stochastic gradient descent (SGD). We derive… 35 arXiv — NLP / Computation & Language research 4h ago SLIM-RL: Risk-Budgeted Random-Masking RL for Diffusion LLMs Without Trajectory Slicing arXiv:2607.00208v1 Announce Type: new Abstract: Reinforcement learning for diffusion large language models (dLLMs) has largely moved to trajectory-aware methods. The current state of the art, TraceRL, holds that random masking is mismatched with the model's inference trajectory,… 19 arXiv — Machine Learning research 4h ago Sample Complexities of Estimating Gumbel--Max Watermark Proportions with and without Reduction to Pivotal Statistics arXiv:2607.00224v1 Announce Type: cross Abstract: Watermarking promises a statistical trace of large language model (LLM) use, but real documents, after editing or paraphrasing, rarely arrive as purely human-written or purely machine-generated. This motivates a quantitative… 38 arXiv — Machine Learning research 4h ago Leveraging Multimodality for Real-Time Classification of Transients and Variables found by the Zwicky Transient Facility arXiv:2607.00228v1 Announce Type: cross Abstract: Modern time-domain surveys such as the Zwicky Transient Facility (ZTF) generate hundreds of thousands of alerts each night, making real-time decisions for follow-up observations a central challenge in time-domain astronomy.… 28 Page 2 of 10 · 500 articles ← Newer Older →
