News / #paper Tag Research papers 500 articles archived under #paper · RSS Sign in to follow arXiv — Machine Learning research 2h ago DiLaServe: High SLO Attainment Serving for Diffusion Language Models arXiv:2606.29094v1 Announce Type: new Abstract: Diffusion language models (DLMs) have recently emerged as a promising alternative to conventional autoregressive language models. By generating multiple tokens in parallel during each denoising step, they offer higher inference… 36 arXiv — Machine Learning research 2h ago Few-Step Boltzmann Generators via Scalable Likelihood Flow Maps arXiv:2606.29110v1 Announce Type: new Abstract: Recent progress in flow-based generative modeling has led to models that output high-quality samples while using only a small number of function evaluations. However, at present, there is a lack of similar advances in estimating… 32 arXiv — Machine Learning research 2h ago A Novel Latent-Class Attack and its Detection by Class Subspace Orthogonalization arXiv:2606.29112v1 Announce Type: new Abstract: Deep learning, which in general relies on voluminous amounts of training data, is vulnerable to data poisoning attacks, including error-generic attacks and backdoors (Trojans). In this work, we propose a new data poisoning attack… 35 arXiv — Machine Learning research 2h ago How Token Influence Decays with Distance: A Green-Function View of Trained Language Models arXiv:2606.29139v1 Announce Type: new Abstract: We study how the next-token prediction of an autoregressive Transformer language model changes under small perturbations of earlier input token embeddings. Motivated by operator learning and iterative solvers for differential… 27 arXiv — Machine Learning research 2h ago On the Nonlinearity of Learning Rate Scaling for LLM Training arXiv:2606.29158v1 Announce Type: new Abstract: Learning-rate transfer can reduce the cost of training large language models: instead of sweeping learning rates at target scale, practitioners extrapolate from smaller runs. Existing approaches often assume that the optimal… 29 arXiv — Machine Learning research 2h ago GLACIER: Rethinking Mass Spectrum Prediction as an Object Detection Problem arXiv:2606.29161v1 Announce Type: new Abstract: Predicting tandem mass spectra (MS/MS) from molecular structures represents a central task in analytical chemistry with direct relevance to clinical metabolomics, systems biology, and adjacent disciplines. In this work, we revisit… 13 arXiv — Machine Learning research 2h ago Invariant Reasoning Directions in Latent Trajectories of Language Models arXiv:2606.29164v1 Announce Type: new Abstract: Latent reasoning models perform multi-step inference directly in hidden-state space, yet the structure of these latent reasoning trajectories remains poorly understood. We show that contrastive refinement signals between stronger… 25 arXiv — Machine Learning research 2h ago Symbolic Mechanistic Data Attribution: Tracing Training Influence to Learned Behavioral Policies arXiv:2606.29171v1 Announce Type: new Abstract: While existing data attribution methods can identify which training examples build specific mechanistic circuits, they cannot explain how training data shapes the high-level behavioral decisions a model learns to make. To bridge… 31 arXiv — Machine Learning research 2h ago Dead-Direction Conditioners: Gauge-Equivariant Preconditioning for Deep Networks arXiv:2606.29176v1 Announce Type: new Abstract: A deep network's loss is invariant to continuous symmetries of its parameters: the logit shift, the ReLU rescaling, the LayerNorm scale, the per-head attention rotation. Adam's per-coordinate preconditioner drifts along each… 27 arXiv — Machine Learning research 2h ago BaRA: Bayesian Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning arXiv:2606.29184v1 Announce Type: new Abstract: While Low-rank adaptation (LoRA) enables highly efficient fine-tuning by constraining task-specific updates to fixed low-rank subspaces, this rigid design limits representational flexibility and often results in overconfident… 15 arXiv — Machine Learning research 2h ago Representational Depth of Evaluation Awareness Shifts With Scale in Open-Weight Language Models arXiv:2606.29196v1 Announce Type: new Abstract: Do language models know when they are being tested? This question matters for AI safety: a model that recognises an evaluation context could alter its behaviour strategically, making downstream benchmarks harder to interpret. Using… 27 arXiv — Machine Learning research 2h ago BrainRiem: Riemannian Prototype Learning for Source-Free Cross-Site Brain Network Diagnosis arXiv:2606.29200v1 Announce Type: new Abstract: Multi-site functional MRI (fMRI) studies are essential for robust neuropsychiatric diagnosis yet suffer severe domain shifts from scanner heterogeneity, demographics, and site-specific acquisition protocols. Traditional domain… 14 arXiv — Machine Learning research 2h ago Bayesian Best-Arm Identification with Abstention: A Polynomial-to-Exponential Phase Transition arXiv:2606.29203v1 Announce Type: new Abstract: We study the Bayesian fixed-budget best-arm identification problem in which a learner can abstain from making a terminal recommendation. Subject to an abstention budget $\alpha$, we analyze the probability of undetected error--the… 36 arXiv — Machine Learning research 2h ago Multi-Block Diffusion Language Models arXiv:2606.29215v1 Announce Type: new Abstract: Block Diffusion Language Models (BD-LMs) improve diffusion-based text generation with KV caching and flexible-length generation. A natural next step is to extend them from Single-Block Diffusion (SingleBD) to Multi-Block Diffusion… 10 arXiv — Machine Learning research 2h ago A Linear Matching Bandit Approach to Online Multi-Human Multi-Robot Teaming arXiv:2606.29221v1 Announce Type: new Abstract: We address the problem of online multi-human multi-robot teaming through the lens of a linear matching bandit framework, where a learner assigns robots with unknown features from a fixed pool to distinct sets of human agents over… 15 arXiv — Machine Learning research 2h ago Depth Exploration for LLM Decoding arXiv:2606.29223v1 Announce Type: new Abstract: Autoregressive LLM decoding evaluates every generated token through the full layer stack, even though many tokens become predictable at intermediate depths. Existing lossless depth-adaptive methods exploit this redundancy by… 34 arXiv — Machine Learning research 2h ago On the Policy Gradient Foundations of Group Relative Policy Optimization: Credit Assignment, Gradient Sparsity, and Rank Collapse arXiv:2606.29238v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) eliminates the learned critic in PPO by using the mean reward of grouped rollouts as a baseline. We provide a rigorous derivation of GRPO from first principles of the policy gradient… 22 arXiv — Machine Learning research 2h ago Blackknife: Hard-Label Query-Limited Black-Box Attacks on Heterogeneous Graph Neural Networks arXiv:2606.29240v1 Announce Type: new Abstract: Heterogeneous graph neural networks (HGNNs) have achieved strong performance in modeling complex graph-structured data with multiple node and relation types. However, their robustness under realistic black-box adversarial settings… 19 arXiv — Machine Learning research 2h ago Towards Evaluating Data Priors for Tabular Foundation Models arXiv:2606.29241v1 Announce Type: new Abstract: Data-generating priors are a central component of tabular foundation models because they define the task distribution used during pretraining. However, priors are rarely evaluated as independent components, making it difficult to… 12 arXiv — Machine Learning research 2h ago KrishokChat: A Citation-Grounded Dataset and Benchmark for Bengali Agricultural Advisory arXiv:2606.29243v1 Announce Type: new Abstract: We present KrishokChat, the first citation-grounded Bengali agricultural instruction-tuning dataset for crop advisory in low-resource settings. We establish a foundation of 290 hierarchical Knowledge Nodes, extracting disease… 30 arXiv — Machine Learning research 2h ago When Prices Double in a Week: Forecasting of Agricultural Volatility in Import-Isolated Markets arXiv:2606.29248v1 Announce Type: new Abstract: Vegetable prices in Sri Lanka are highly volatile because the market is largely import-isolated, so supply disruptions quickly drive prices up. This study develops a machine learning framework to forecast such volatility by… 8 arXiv — Machine Learning research 2h ago Learning to Bid in Discriminatory Auctions with Budget Constraints arXiv:2606.29252v1 Announce Type: new Abstract: We study repeated bidding in multi-unit discriminatory (pay-as-bid) auctions for a single bidder with per-round utility equal to value minus $\alpha$ times payment, where $\alpha\in[0,1]$ is a cost-of-capital parameter. The bidder… 7 arXiv — Machine Learning research 2h ago Nonlinear mixture model motivated subspace clustering arXiv:2606.29261v1 Announce Type: new Abstract: We derive the linear union-of-subspaces (UoS) model for subspace clustering (SC) from the nonlinear mixture model (NMM) used in blind source separation (BSS) to represent a D-dimensional observation vector as an unknown… 7 arXiv — Machine Learning research 2h ago PCGD: Physics-Guided Conditional Graph Diffusion for TCAD Device Simulation arXiv:2606.29272v1 Announce Type: new Abstract: Technology computer-aided design (TCAD) semiconductor device simulation is fundamentally constrained by the high computational cost of iteratively solving coupled drift-diffusion equations. Existing ML surrogates either reduce… 33 arXiv — Machine Learning research 2h ago Adaptive Block Diffusion: Resolving Training-Inference Mismatch in Diffusion Language Models arXiv:2606.29275v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) are typically trained under fixed context structures, restricting denoising to predetermined token subsets. This creates a mismatch between training and inference, where models must operate over… 37 arXiv — Machine Learning research 2h ago Deterministic Decisions for High-Stakes AI. A Zero-Egress Pipeline with the Deployability of RAG and the Accuracy of Machine Learning arXiv:2606.29280v1 Announce Type: new Abstract: We identify intervention bias as a previously unquantified failure mode of zero-shot large-language-model (LLM) educational advisory agents: without task-specific training, they recommend action when a hindsight-optimal oracle… 31 arXiv — Machine Learning research 2h ago Beyond Trajectory Matching: Reflow with Marginal Distribution Alignment arXiv:2606.29287v1 Announce Type: new Abstract: Diffusion and continuous-flow generative models achieve high-quality generation, and their deterministic sampling can be formulated as solving learned ODE dynamics. However, accurate ODE discretization often requires many steps,… 36 arXiv — Machine Learning research 2h ago SP-CACW: Convergence-Aware Client Weighting for Selfish Personalized Learning arXiv:2606.29322v1 Announce Type: new Abstract: Collaborative learning is sustainable only when it benefits each participant. Standard federated learning optimizes a global average objective, which can under perform for clients whose data distributions differ substantially from… 35 arXiv — Machine Learning research 2h ago Deciphering Region-Level Signatures from Latency Measurements in LEO Satellite Internet arXiv:2606.29324v1 Announce Type: new Abstract: Low-Earth orbit (LEO) satellite Internet has become an indispensable infrastructure that provide growing coverage for global users. Despite extensive measurement efforts, the principles underlying region-level performance… 32 arXiv — Machine Learning research 2h ago Sample Complexity of Scientific Discovery: PAC Learnability of Compositional Function Trees arXiv:2606.29331v1 Announce Type: new Abstract: Scientific discovery via symbolic regression is often viewed as statistically and computationally intractable because the hypothesis space of expressions grows combinatorially with depth. This paper revisits the statistical side… 33 arXiv — Machine Learning research 2h ago AMR: Adaptive Modality Routing for Multimodal Polyglot Speaker Identification arXiv:2606.29335v1 Announce Type: new Abstract: Multimodal speaker identification systems face two key challenges in real-world deployment: missing modalities and language mismatch between training and testing conditions. In practical scenarios, background multi-speaker… 14 arXiv — Machine Learning research 2h ago Reliability, Faithfulness, and the Limits of Post-hoc Explanations of Opaque Scientific Models arXiv:2606.29346v1 Announce Type: new Abstract: Post-hoc explanation methods are routinely used to interpret scientific machine learning models, with the deliverable understood to be insight into the phenomenon the model has been trained on. The transition may be taken to be… 22 arXiv — Machine Learning research 2h ago Adaptive Financial Transformer with Regime-Gated Attention for Stock Return Prediction arXiv:2606.29347v1 Announce Type: new Abstract: Adaptive Financial Transformer (AFT) is proposed for stock return prediction under non-stationary financial markets. The model incorporates a Market Regime Encoder, an Adaptive Gate Network, and an Adaptive Financial Context module… 17 arXiv — Machine Learning research 2h ago Interventional Flow Matching: Prospective Dose-Response Forecasting with Velocity-Field Jacobian Regularization arXiv:2606.29386v1 Announce Type: new Abstract: Predicting a patient's physiological trajectory under a planned treatment sequence is a prospective interventional problem, not standard time-series extrapolation. We study this problem in glucose management, where insulin and… 20 arXiv — Machine Learning research 2h ago Temporal Posed and Spontaneous Gesture Recognition from Electromyography in the Rock-Paper-Scissors Game arXiv:2606.29423v1 Announce Type: new Abstract: The importance of gesture recognition has been acknowledged in many domains requiring real-time recognition systems. Two requirements for these are fast recognition in multiuser contexts. Therefore, we explored the temporal… 4 arXiv — Machine Learning research 2h ago Randomized neural operator for parametric PDEs with fast training and conformal uncertainty quantification arXiv:2606.29440v1 Announce Type: new Abstract: Repeatedly solving parametric PDEs is essential for uncertainty quantification, design optimization and inverse problems, but conventional neural operators require expensive non-convex training. We introduce PCA--RaNN, a randomized… 16 arXiv — Machine Learning research 2h ago Interpretable Inverse Design of Metal-Organic Frameworks with Large Language Model Agents arXiv:2606.29459v1 Announce Type: new Abstract: Inverse design of metal-organic frameworks (MOFs) requires searching a combinatorially vast space where property labels are expensive and most machine-learning models reveal little about why a structure succeeds. We introduce… 8 arXiv — Machine Learning research 2h ago Prototype Latent World Model Replay for Class-Incremental Learning arXiv:2606.29465v1 Announce Type: new Abstract: Class-incremental learning requires a model to learn new classes while preserving decision regions for old ones. This is difficult when raw old samples are no longer available. We propose Prototype Latent World Model Replay, a… 8 arXiv — Machine Learning research 2h ago Self-Supervised Calibration of Scientific Instruments Using Physical Consistency Constraints arXiv:2606.29466v1 Announce Type: new Abstract: Calibration remains one of the principal obstacles to the deployment of machine learning in scientific instrumentation because it typically relies on expert intervention, dedicated procedures, and manually labelled data. We… 13 arXiv — Machine Learning research 2h ago Structured Proper Loss Geometries for Multiclass Classification: Theory and Controlled Empirical Evaluation arXiv:2606.29471v1 Announce Type: new Abstract: Strictly proper scoring rules identify the true conditional class distribution at population level, but their curvature can alter optimization and finite-sample behavior. We study three multiclass objectives: a class-aware… 23 arXiv — Machine Learning research 2h ago CRAFT: Counterfactual Credit Assignment from Free Sibling Rollouts for Self-Distilled Agentic Reinforcement Learning arXiv:2606.29476v1 Announce Type: new Abstract: Self-distilled agentic reinforcement learning augments trajectory-level reward with a token-level distillation loss, using as its teacher the same policy conditioned on privileged context. The prevailing recipe gates this loss by a… 24 arXiv — Machine Learning research 2h ago Reported Confidence in LLMs Tracks Commitment More Than Correctness arXiv:2606.29490v1 Announce Type: new Abstract: Confidence is an estimate of the probability that a chosen answer is correct. Verbal confidence reports are widely used as uncertainty measures in large language models, but whether they are best understood as estimates of… 33 arXiv — Machine Learning research 2h ago Reinforcement Learning in Super Mario Bros: Curriculum, Pedagogy, and Optimal Level Design in World 1-1 arXiv:2606.29511v1 Announce Type: new Abstract: World 1-1 of Super Mario Bros is widely celebrated as a masterclass in game design: its progressive structure is credited with teaching players core mechanics through the level itself. We ask whether that structure is empirically… 22 arXiv — Machine Learning research 2h ago A Mathematical Optimization Approach for Expert-Informed Bayesian Best Subset Selection arXiv:2606.29516v1 Announce Type: new Abstract: A central challenge in statistical modeling is identifying the subset of features that belong in the true regression model. The classical best subset selection problem, recently made tractable via mixed-integer optimization (MIO),… 34 arXiv — Machine Learning research 2h ago Anti-Collapse Dynamics and the Emergence of Multi-Time-Scale Learning in Recurrent Neural Networks arXiv:2606.29519v1 Announce Type: new Abstract: Long-range learning is hard for recurrent networks trained with stochastic gradient descent, because the influence of a past input fades with the lag $\ell$, and if it fades too fast the dependence cannot be learned from finite… 28 arXiv — Machine Learning research 2h ago Not All Objectives Are Born Equal: Priority-Constrained Descent for Hierarchical Multi-Objective Optimization arXiv:2606.29521v1 Announce Type: new Abstract: Deep learning problems rarely involve objectives that are equal in importance. A primary objective defines the goal, whilst secondary objectives, such as sparsity, compression, or robustness constrain the solution. While existing… 31 arXiv — Machine Learning research 2h ago Do Models Read What They Write? Causal Registers in Scratchpad Reasoning arXiv:2606.29522v1 Announce Type: new Abstract: A central hope behind process supervision is that models can expose intermediate variables that matter for their later behavior. For this to help with alignment, a scratchpad must be tied to the computation: when the model writes a… 29 arXiv — Machine Learning research 2h ago The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning arXiv:2606.29526v1 Announce Type: new Abstract: Reinforcement learning (RL) has gained growing attention in large language model (LLM) post-training, yet RL training remains fragile and can suffer from instability or collapse. One vital cause is training-inference mismatch: LLM… 17 arXiv — Machine Learning research 2h ago VISTA-DZ: Visual Semantic Trajectory Adaptation for Personalized Dilemma Zone Prediction arXiv:2606.29548v1 Announce Type: new Abstract: Driver decision making in the dilemma zone at signalized intersections is safety critical, as vehicles approaching a yellow signal must decide whether to stop or proceed within limited time and distance margins. Accurate prediction… 38 arXiv — Machine Learning research 2h ago Optimizer Memory Makes Shuffle Order a First-Order Source of Fine-Tuning Noise arXiv:2606.29554v1 Announce Type: new Abstract: Shuffle order can be a larger source of fine-tuning noise than a memoryless analysis predicts: fixed-clock optimizer memory makes local equal-multiset contrasts first order in the learning rate rather than second order, and the… 8 Page 2 of 10 · 500 articles ← Newer Older →
