News / #paper Tag Research papers 500 articles archived under #paper · RSS Sign in to follow arXiv — Machine Learning research 2d ago Personalized Federated Direct Preference Optimization via LoRA Adapters arXiv:2610.12885v1 Announce Type: new Abstract: Federated Direct Preference Optimization (FedDPO) enables privacy-preserving alignment of language models across distributed agents without centralizing sensitive preference data. However, existing FedDPO analysis assumes all… 24 arXiv — Machine Learning research 2d ago GIST: Generator-state-Informed Supervision for Tabular Foundation Models arXiv:2610.12904v1 Announce Type: new Abstract: Tabular foundation models (TFMs) based on prior-data fitted networks typically use sampled hard query labels, leaving avoidable sampling variability in pretraining. A key observation is that intermediate generator states can reveal… 27 arXiv — Machine Learning research 2d ago Controlled-Minimax: Stabilizing Adversarial Optimization via Control Theory arXiv:2610.12915v1 Announce Type: new Abstract: Minimax optimization is fundamental to adversarial learning yet suffers from severe stability challenges, often manifesting as persistent limit cycles or divergence. This paper investigates these instabilities through the lens of… 6 arXiv — Machine Learning research 2d ago DataCupid: Stable Matching Repair for Training Data Acquisition with Delayed Feedback arXiv:2610.12960v1 Announce Type: new Abstract: Matching repair after utility changes can reuse valid observations, but new evaluations must respect matching capacity and may return out of order. We study announced invalidations with bounded, possibly reward-dependent reporting… 33 arXiv — Machine Learning research 2d ago Diffusion Precipitation Generation with Medium-range Weather Forecasting arXiv:2610.12976v1 Announce Type: new Abstract: Accurate daily precipitation forecasts are important for weather-sensitive decisions. Although recent Weather Foundation Models (WFMs) have achieved significant progress, they are trained on reanalysis data, which exhibit regional… 35 arXiv — Machine Learning research 2d ago Gaussian-Width Bounds for Offline-to-Online Linear Bandits arXiv:2610.12990v1 Announce Type: new Abstract: We study how offline data can help online learning in stochastic linear bandits. We focus on partially covered offline data, where only $k$ of the $d$ feature directions are poorly covered. Existing analyses of algorithms based on… 14 arXiv — Machine Learning research 2d ago Evidential Multimodal Transformers with Dempster-Shafer Fusion for Emotion Recognition arXiv:2610.13013v1 Announce Type: new Abstract: Softmax-based multimodal emotion recognition methods often assign high confidence even when sensor data are corrupted or contradictory, for example when facial expressions suggest positive valence while vocal prosody indicates… 35 arXiv — Machine Learning research 2d ago Generalized Proximal Policy Optimization: Unifying LLM RL Algorithms from the Perspective of Divergence arXiv:2610.13015v1 Announce Type: new Abstract: Reinforcement learning has become the foundational paradigm for enhancing the reasoning capabilities of LLMs. Yet the dominant approach, Proximal Policy Optimization (PPO), relies on a geometrically degenerate clipping proxy that… 22 arXiv — Machine Learning research 2d ago Trajectory-Aware Policy Optimization: Closing the State Distribution Gap in Long-Horizon LLM RL arXiv:2610.13020v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a dominant paradigm for enhancing LLMs' reasoning capabilities. Yet long-horizon autoregressive rollouts introduce a fundamental limitation: local policy mismatch can compound into severe… 16 arXiv — Machine Learning research 2d ago Low-Rank Kolmogorov-Arnold Generator Flows for Interpretable Operator Learning arXiv:2610.13028v1 Announce Type: new Abstract: Neural operators that learn physical laws from data should generalize beyond their training distribution and expose the learned law in closed form. The Kolmogorov-Arnold neural operator achieves both for position-dependent dynamics… 20 arXiv — Machine Learning research 2d ago Target-Constrained Pooling for Trajectory Extrapolation arXiv:2610.13034v1 Announce Type: new Abstract: Trajectory extrapolation from a partial target trajectory is underdetermined, but completed related trajectories provide information about the unresolved continuation. We propose target-constrained pooling (TCP), which separates… 5 arXiv — Machine Learning research 2d ago Towards Easier-to-Tune Training Algorithms: New Results from AlgoPerf arXiv:2610.13036v1 Announce Type: new Abstract: Evaluating deep learning optimizer is challenging because confounding factors such as hyperparameter tuning and optimizer-model co-design often obscure true algorithmic performance. We present results of the updated AlgoPerf V1… 31 arXiv — Machine Learning research 2d ago CB-Orchestrator: Adaptive Workflow Optimization for LLM Agents via Contextual Bandits arXiv:2610.13064v1 Announce Type: new Abstract: Large Language Model (LLM) agents have demonstrated remarkable capabilities in tackling complex tasks through agentic workflows. However, manually designing these workflows is labor-intensive and lacks flexibility to adapt to… 23 arXiv — Machine Learning research 2d ago Double-Take: Improving Capacity, Binding, and Selectivity In Long-Context Within Bidirectional Memory arXiv:2610.13073v1 Announce Type: new Abstract: Processing a long sequence does not guarantee that distant information remains usable. As context grows, a fixed-size memory must retain many associations, connect information across positions, and preserve relevant structure… 33 arXiv — Machine Learning research 2d ago Human and LLM Facilitation in Collaborative Design Meetings: A Computational Behavioral Comparison arXiv:2610.13082v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly being explored as facilitators of group discussion and collaborative work, but the behavioral differences between LLM-generated and human facilitation remain insufficiently… 10 arXiv — Machine Learning research 2d ago Can Failed Trajectories Reveal Where Agents Go Wrong? Agentic Failure Attribution Without Step-Level Labels arXiv:2610.13105v1 Announce Type: new Abstract: Failure attribution for LLM agents aims to identify decisive steps responsible for task failure, which is critical for debugging and improving agentic systems. Existing methods rely on costly LLM prompting, step-level error… 15 arXiv — Machine Learning research 2d ago Scaling RNA Foundation Models through Iterative Refinement arXiv:2610.13106v1 Announce Type: new Abstract: Biological function in RNA is encoded across scales, from local sequence motifs to long-range structural dependencies. Conventional RNA foundation models couple parameter capacity and inference depth within a fixed architecture,… 27 arXiv — Machine Learning research 2d ago Continually Post-training Small Models via Synthetic Self-distillation arXiv:2610.13113v1 Announce Type: new Abstract: Continual post-training faces a dual challenge of acquisition and retention: models must learn new capabilities while preserving prior knowledge. While Self-Distillation Fine-Tuning (SDFT) mitigates this using self-supervision with… 25 arXiv — Machine Learning research 2d ago WaSA: Wavelet Scattering Autoencoders for Unsupervised Offline Detection of Malicious Clients in Federated Learning arXiv:2610.13186v1 Announce Type: new Abstract: Federated Learning (FL) enables collaborative model training without exposing raw data, yet remains vulnerable to malicious clients injecting poisoned datasets. Existing defenses are typically reactive (operating during training)… 15 arXiv — Machine Learning research 2d ago Does Learning Recurrent Networks Matter in Partially Observable RL? arXiv:2610.13197v1 Announce Type: new Abstract: Reinforcement learning (RL) under partial observability typically re- lies on recurrent networks to encode temporal information, with the recurrent module trained jointly with the policy or value function. This raises a natural… 29 arXiv — NLP / Computation & Language research 2d ago S$^3$R: Fast and Faithful RL Rollouts via Self-Sparse Speculative Decoding arXiv:2610.13202v1 Announce Type: cross Abstract: Fast rollout generation for long-context reinforcement learning with verifiable rewards (RLVR) requires reducing KV-cache traffic without changing the response groups used for policy optimization. In our profiled RLVR workloads,… 9 arXiv — Machine Learning research 2d ago Rethinking Relative Policy Differences Transfer of On-Policy Distillation arXiv:2610.13205v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a target policy on its own rollouts using token-level supervision from a stronger teacher, but typically relies on the teacher being substantially more capable than the target. Recent work… 37 arXiv — Machine Learning research 2d ago How Much Computation Does Every Forecast Need? Structured Block Skipping in Two Time-Series Foundation Models arXiv:2610.13208v1 Announce Type: new Abstract: Time-series foundation models use the same network depth for every input, although forecasting windows differ in structure and difficulty. We test whether whole Transformer blocks can be removed at inference time in two pretrained… 19 arXiv — Machine Learning research 2d ago Monarch-MoE: Structured Experts for Multimodal Continual Instruction Tuning arXiv:2610.13215v1 Announce Type: new Abstract: Learning new tasks in multimodal continual instruction tuning can cause catastrophic forgetting of previously acquired knowledge. Although multi-expert LoRA distributes learning across experts, updates to a dense low-rank expert… 38 arXiv — Machine Learning research 2d ago Tensor-based Fusion of Multi-modal Data for Predicting Cancer Risk Levels arXiv:2610.13221v1 Announce Type: new Abstract: Cancer diagnosis and treatment increasingly rely on multi-modal diagnostic technologies that generate high-dimensional datasets. Although these datasets are rich in pathological information, they pose considerable challenges in… 9 arXiv — Machine Learning research 2d ago ReSFlow: Rectifying Categorical Flows on Statistical Manifolds for One-Step Generation arXiv:2610.13225v1 Announce Type: new Abstract: Generative modeling for discrete data has been significantly advanced by learning continuous vector fields on the statistical manifolds to transport simple priors to target discrete distributions. However, because these… 5 arXiv — Machine Learning research 2d ago Learning Schwarzschild Geodesic Motion with Lagrangian Neural Networks arXiv:2610.13234v1 Announce Type: new Abstract: Lagrangian Neural Networks (LNNs) learn dynamics from trajectory data by parameterizing a scalar Lagrangian and deriving accelerations through the Euler--Lagrange equation, providing a variational inductive bias that improves… 12 arXiv — Machine Learning research 2d ago State-OPD: State-Grounded On-Policy Distillation for Multi-Turn Agents arXiv:2610.13238v1 Announce Type: new Abstract: On-Policy Distillation (OPD) has emerged as a powerful paradigm for transferring reasoning capabilities from frontier models to smaller models, while extending its success to multi-turn agentic environments remains challenging. We… 17 arXiv — Machine Learning research 2d ago Tabular Foundation Models Are Effectively Shallow arXiv:2610.13253v1 Announce Type: new Abstract: In-context-learning Tabular Foundation Models (TFMs) are uniquely suited to scenarios with limited resources or privacy constraints, as they solve new tasks without additional training. However, their architecture consists of… 37 arXiv — NLP / Computation & Language research 2d ago CAST: Credit Alignment for Cross-Tokenizer On-Policy Distillation arXiv:2610.13257v1 Announce Type: cross Abstract: Cross-tokenizer on-policy distillation (OPD) requires aligning teacher and student sequences before their scores can be compared. Decoded-text alignment provides such correspondence at the chunk level, but leaves a distinct… 12 arXiv — Machine Learning research 2d ago Neural Surrogate Modeling of Ultrasonic Wave Propagation in Heterogeneous Media arXiv:2610.13258v1 Announce Type: new Abstract: Neural surrogates provide computationally efficient auto-regressive modeling of wave propagation, enabling e.g. fast inverse solutions. Despite recent progress, the current surrogates are not yet sufficient for the needs of… 35 arXiv — Machine Learning research 2d ago Data-Adaptive Mahalanobis Metric Learning for Cross-Head Attention in Transformers arXiv:2610.13261v1 Announce Type: new Abstract: In this paper, we propose Data-Adaptive Mahalanobis Cross-Head Attention (DAMCHA), a simple and effective attention mechanism that generalizes Multi-Head Attention (MHA) through the lens of metric learning. Standard MHA implicitly… 38 arXiv — Machine Learning research 2d ago CopRoute: Dependence-Aware Conformal Routing for Language Models arXiv:2610.13276v1 Announce Type: new Abstract: Set-based language model routing aims to increase the coverage of the event where at least one model answers a query correctly while controlling the number of inference calls made. Existing risk-controlled routing policies bound… 5 arXiv — Machine Learning research 2d ago MHR-Router: Multimodal Heterogeneous Retrieval-Enhanced Adaptive Routing for VLM Inference arXiv:2610.13278v1 Announce Type: new Abstract: Vision-language models (VLMs) exhibit complementary capabilities, yet selecting the most suitable expert for a given image-question query remains challenging due to heterogeneous multimodal inputs and varying expert strengths.… 16 arXiv — Machine Learning research 2d ago Recovering Irreducible Three-Body Interactions with Lagrangian Neural Networks arXiv:2610.13292v1 Announce Type: new Abstract: Lagrangian Neural Networks (LNNs) learn mechanical systems from trajectory data by parameterizing a scalar Lagrangian and deriving the dynamics through the Euler-Lagrange equations, biasing the model toward motion that respects the… 37 arXiv — Machine Learning research 2d ago DAG Structure Learning with Node-Varying Heavy-Tailed Disturbances arXiv:2610.13304v1 Announce Type: new Abstract: DAG structures can be learned from observations by incorporating acyclicity via smooth constraints, such as DAGMA's log-determinant function. Typically, observations and the underlying DAG are related through linear structural… 8 arXiv — Machine Learning research 2d ago MORAD: Reinforcement Learning with Multi-Objective Rewards for RNA Inverse Design arXiv:2610.13305v1 Announce Type: new Abstract: We introduce MORAD, an online reinforcement learning framework for backbone-conditioned RNA diffusion models that trains a single shared policy across diverse target backbones. Structure-conditioned RNA inverse design seeks… 5 arXiv — Machine Learning research 2d ago Structure-Aware Numerical Stabilization for Half-Precision Proximal Policy Optimization arXiv:2610.13306v1 Announce Type: new Abstract: Local online training on resource-constrained platforms requires low computational and training-state overhead. We study the numerical stability and computational efficiency of half-precision proximal policy optimization (PPO) on… 8 arXiv — Machine Learning research 2d ago Sustainable Cloud-Fog-Edge Systems for Smart Buildings: Algorithmic Adaptation under Memory Constraints and Dynamic Orchestration Strategies arXiv:2610.13307v1 Announce Type: new Abstract: The escalating environmental footprint of the Information and Communication Technol- ogy (ICT) sectorwith global Data Center electric- ity usage potentially reaching 3% by 2030 and the imperative for real-time responsiveness in… 20 arXiv — Machine Learning research 2d ago SBNO : Schr\"odinger Bridge Neural Operator for the Forward and Inverse Problems under Missing Information arXiv:2610.13317v1 Announce Type: new Abstract: Partial differential equation (PDE) surrogate modeling often relies on either dense observations or access to governing equations/physics constraints. In practice, observations can be sparse and partial, and the underlying physics… 33 arXiv — Machine Learning research 2d ago DuoRate: Two-Rate Per-Expert Precision Allocation for Mixture-of-Experts Serving arXiv:2610.13328v1 Announce Type: new Abstract: Serving a Mixture-of-Experts (MoE) model pays for expert precision twice: the resident footprint pays for every expert the router can reach, while each batch-one decode step pays only for the experts it selects. These are two… 38 arXiv — Machine Learning research 2d ago PDE-PFN: Prior-Data Fitted Neural PDE Solver arXiv:2610.13334v1 Announce Type: new Abstract: Motivated by the success of large language models (LLMs) with broad generalizability and robustness to noisy or unreliable pre-training data, we explore in-context prediction of PDE solution fields using approximate pre-training… 10 arXiv — Machine Learning research 2d ago AgentTune: A Unified Training Lifecycle for Tool-Using LLM Agents arXiv:2610.13335v1 Announce Type: new Abstract: Tool-using agents increasingly require a common substrate for building, training, evaluating, distilling, and maintaining agentic systems, yet existing tooling typically addresses these stages in isolation. We present AgentTune, a… 24 arXiv — Machine Learning research 2d ago Understanding Mamba-3 Through Oscillatory Dynamics arXiv:2610.13341v1 Announce Type: new Abstract: Mamba-3 introduces input-dependent rotations into recurrent state updates, but their contribution beyond state retention remains unclear. We interpret these ro- tations as underdamped second-order dynamics, providing a framework… 33 arXiv — Machine Learning research 2d ago Hidden Data Challenges in Clinical Machine Learning arXiv:2610.13350v1 Announce Type: new Abstract: Widely reused preprocessing pipelines for electronic health records can encode assumptions about when information became available, what clinical episode a label represents, and what missingness means. These assumptions are rarely… 36 arXiv — Machine Learning research 2d ago Opening the Black Box of Classifier-Free Guidance via Information Bottleneck arXiv:2610.13369v1 Announce Type: new Abstract: Classifier-free guidance (CFG) is a standard technique for improving conditional generation in diffusion models, yet its activation schedule is usually selected heuristically. In practice, most existing CFG-based methods rely on a… 9 arXiv — Machine Learning research 2d ago BLOKS: Scaling Kernel Solvers with Sketched Block Preconditioning arXiv:2610.13382v1 Announce Type: new Abstract: Kernel Ridge Regression (KRR) is a theoretically sound algorithm for nonparametric learning, which is also often used to investigate properties of deep learning. However, the exact KRR formulation incurs time and memory costs… 18 arXiv — Machine Learning research 2d ago PlacePulse: Learning Transferable Place Representations from Structural Geographic Data arXiv:2610.13390v1 Announce Type: new Abstract: Geospatial machine learning often depends on task-specific feature engineering over large collections of sociodemographic, business, and environmental variables. Geospatial foundation models offer reusable representations of place,… 19 arXiv — Machine Learning research 2d ago Why Linear Models Can Still Work in a Complex and Changing World arXiv:2610.13404v1 Announce Type: new Abstract: Linear models can predict well in complex domains even when underlying mechanisms are nonlinear. We argue that this can occur because the complexity of the world exceeds the complexity that can be learned reliably from finite,… 38 arXiv — Machine Learning research 2d ago Accelerating Linear Bandits with Persistent Candidate Sets arXiv:2610.13407v1 Announce Type: new Abstract: Exhaustive optimistic scoring can make action selection costly in linear bandits with a large fixed set of $K$ actions, requiring $\mathcal{O}(K)$ score evaluations per round. We introduce Persistent Candidate LinUCB… 23 Page 2 of 10 · 500 articles ← Newer Older →
