News / #paper Tag Research papers 500 articles archived under #paper · RSS Sign in to follow arXiv — Machine Learning research 3d ago MacroAgent: Regularity-Aware Macro Legalization with LLM-Agent-Designed Contour Algorithms arXiv:2608.24946v1 Announce Type: new Abstract: Macros constitute a large part of the core area in modern very large-scale integration (VLSI) designs. Moreover, macro positions have a significant impact on the final quality of result (QoR), and macro legalization is typically… 18 arXiv — Machine Learning research 3d ago CAT-GS: Balanced Multimodal Learning via Calibrated Gating and Fusion Surgery arXiv:2608.24947v1 Announce Type: new Abstract: End-to-end training of multimodal neural networks often exhibits unstable neural dynamics characterized by three coupled failure modes that degrade learning: (i) modality imbalance, where one branch dominates gradient-based… 35 arXiv — NLP / Computation & Language research 3d ago Demystifying Reinforcement Learning Post-Training of Language Models arXiv:2608.24949v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training has emerged as a powerful framework for enhancing the capabilities of large language models (LLMs), enabling impressive reasoning, math, and coding capabilities. Yet for many researchers… 15 arXiv — Machine Learning research 3d ago AFDBench: A Reasoning-First AI Scientist for NationalWeather Service Forecast Discussions arXiv:2608.24954v1 Announce Type: new Abstract: Large language models (LLMs) hallucinate numerical values when generating high-stakes meteorological text, posing risks for weather communication. We present AFDBench, an AI meteorologist that generates professional Area Forecast… 22 arXiv — Machine Learning research 3d ago Why and When Neural Networks Improve Local Approximation in Optimization arXiv:2608.24963v1 Announce Type: new Abstract: Published experience with neural surrogates in derivative-free optimisation is contradictory: the same family of models that cuts the evaluation count of one solver leaves another unchanged, or makes it worse. We show that the… 17 arXiv — Machine Learning research 3d ago Physics-Informed Error Field Learning: A Post-Training Optimization Framework for Physics-Informed Neural Networks arXiv:2608.24970v1 Announce Type: new Abstract: Physics-Informed Neural Networks (PINNs) have emerged as an important class of numerical methods for solving partial differential equations (PDEs). However, during the late-stage optimization process, further parameter updates… 32 arXiv — Machine Learning research 3d ago Resource-Efficient Pruning for Transformer via Low-Rank Importance Estimation arXiv:2608.24973v1 Announce Type: new Abstract: With the rapid development of large-scale pre-trained language models based on Transformer architectures, their high computational and memory costs have become a major obstacle to deployment, especially in resource-constrained… 30 arXiv — Machine Learning research 3d ago Clearing the Underbrush: AI-Enhanced RF Interference Suppression arXiv:2608.24974v1 Announce Type: new Abstract: AI-based structured interference rejection has grown more popular because deep learning approaches can outperform traditional methods by jointly considering the signal of interest (SOI) and the signal mixture (SOI plus… 19 arXiv — Machine Learning research 3d ago MSR-IVA: Masked Structural Residual Independent Vector Analysis for State-Aware Fusion of Structural MRI and Dynamic Functional Network Connectivity arXiv:2608.24978v1 Announce Type: new Abstract: Multimodal fusion of structural MRI (sMRI) and dynamic functional network connectivity (dFNC) can reveal how brain structure relates to changing functional states. When the same structural latent representation is coupled with… 35 arXiv — Machine Learning research 3d ago D$^3$-MOPD: Adaptive Dynamic Domain ScheDuling for Efficient Multi-Teacher Distillation arXiv:2608.24987v1 Announce Type: new Abstract: Multi-teacher on-policy distillation (MOPD) distills several domain-expert teachers into a single student by minimizing per-domain reverse-KL divergence on the student's own rollouts. Existing approaches typically fix the… 28 arXiv — Machine Learning research 3d ago Rollout-Decoded Reconstruction for Long-Horizon Prediction in Latent World Models arXiv:2608.25017v1 Announce Type: new Abstract: A latent world model trains its decoder on latents anchored to observations, then deploys it on the model's own free-running rollout, hundreds of steps past the last observation. Rollout-Decoded Reconstruction (RDR) closes this gap… 18 arXiv — Machine Learning research 3d ago On the Representational Geometry of Dynamic Programs arXiv:2608.25034v1 Announce Type: new Abstract: Standard neural architectures often fail to generalize to longer inputs for dynamic programming (DP) targets. We investigate what makes this hard geometrically. Every finite min-plus DP is a shortest path on a DAG, which is… 37 arXiv — Machine Learning research 3d ago DeMMO: Longitudinal and Cross-Disease Modelling of Digital Mobility Outcomes via Multi-Task Learning arXiv:2608.25073v1 Announce Type: new Abstract: Digital mobility outcomes (DMOs) derived from wearable sensors characterise mobility in daily life and offer a promising means of monitoring disease progression. Yet most DMO studies examine one disease at one visit; they do not… 30 arXiv — Machine Learning research 3d ago NVExplain: Explaining Time Series Forecasting with Latent Trajectory Analysis and Structure-Preserving Surrogates arXiv:2608.25080v1 Announce Type: new Abstract: Time series forecasting models are widely used in high-stakes settings, yet their predictions remain difficult to interpret because existing post-hoc methods often ignore temporal dependence and fail to provide horizon-specific… 20 arXiv — Machine Learning research 3d ago The Frame Kernel Method for Multiscale Operator Learning arXiv:2608.25084v1 Announce Type: new Abstract: We present a natively multiscale operator learning method for the surrogate modeling of (numerical solvers for) multiscale partial differential equations (PDEs). The primary novelty of our method lies in a novel multiscale kernel… 6 arXiv — Machine Learning research 3d ago The Von-Neumann State-Space Transformer for neural decoding arXiv:2608.25088v1 Announce Type: new Abstract: Cortical computation is strikingly low-dimensional: a handful of latent variables, carried in a neural population's activity, steer the higher-dimensional responses of individual neurons. Our aim is sample efficiency-models that… 19 arXiv — Machine Learning research 3d ago Understanding the Energy Scaling of Large Language Model Inference Across Context Lengths and Attention Architectures arXiv:2608.25096v1 Announce Type: new Abstract: The growing adoption of large language models (LLMs) has raised increasing concerns about the energy consumption and environmental impact of inference. This paper presents a systematic empirical study of decode-phase energy… 27 arXiv — Machine Learning research 3d ago Flower Hub: A Reproducible Benchmarking Platform for Federated Learning in Simulation and Deployment arXiv:2608.25114v1 Announce Type: new Abstract: Federated learning (FL) has emerged as a key approach for training models across decentralized data, yet benchmarking in FL remains difficult to reproduce, compare, and extend. Existing evaluations are often tied to custom… 7 arXiv — Machine Learning research 3d ago GRAPE: Gradient Refinement and Progress-Aware Exploitation for Query-Efficient High-Dimensional Bayesian Optimization arXiv:2608.25116v1 Announce Type: new Abstract: Optimizing expensive, high-dimensional black-box functions remains a central challenge in modern machine learning and scientific discovery. While local Bayesian optimization mitigates the curse of dimensionality, existing… 12 arXiv — Machine Learning research 3d ago Toward Machine Learning with the Unit as a Primitive: Learning from Unit-Linked Events arXiv:2608.25118v1 Announce Type: new Abstract: Machine learning is usually formalized through samples, while the persistent individual to which multiple observed or possible events refer often remains implicit. We propose the \emph{unit} as an explicit primitive at the level of… 31 arXiv — Machine Learning research 3d ago Multimodal Injury Risk Prediction in Tennis arXiv:2608.25126v1 Announce Type: new Abstract: Machine learning has had a significant positive impact on the prediction of athlete performance and injury risk. Most works in this field rely on subjective observations and expert assessments, which restrict their effectiveness.… 29 arXiv — Machine Learning research 3d ago When Does Context Routing Help? A Systematic Study of Multi-Modal Fusion in Time Series Forecasting arXiv:2608.25128v1 Announce Type: new Abstract: Multi-modal time series forecasting methods integrate auxiliary context into temporal predictions through increasingly sophisticated fusion mechanisms. A growing body of work reports substantial gains, yet it is often unclear… 20 arXiv — Machine Learning research 3d ago Rethinking the Transferable Adversarial Attacks and Robust Defense in Federated Learning arXiv:2608.25133v1 Announce Type: new Abstract: The development of federated learning (FL) techniques has helped improve the privacy preservation of users' data and extended the applications of machine learning models. However, the involvement of a large number of users in FL… 29 arXiv — Machine Learning research 3d ago Drift Variation Autoencoder: Unifying Generation and Representation Learning through Conditional Posterior Flow Matching arXiv:2608.25138v1 Announce Type: new Abstract: Stochastic masking, cropping, or modality removal makes deterministic reconstruction an incomplete target: one observation can admit many clean completions. This work takes the corresponding posterior $P(X\mid C)$ as the common… 5 arXiv — Machine Learning research 3d ago SNAP-KG: Streaming Node Assignment via Projection for Knowledge Graph Entity Integration arXiv:2608.25149v1 Announce Type: new Abstract: Knowledge graph (KG) construction pipelines must continuously integrate newly arriving entities into a growing graph. Unlike inserting triples between existing nodes, a newly arriving entity has no graph connectivity: it emerges… 6 arXiv — Machine Learning research 3d ago Bayesian Flow Networks for Offline Trajectory Planning arXiv:2608.25163v1 Announce Type: new Abstract: Offline reinforcement learning (RL) leverages static datasets to learn decision policies without real-time environment interaction. While recent sequence-modeling approaches rely on continuous diffusion models for trajectory… 25 arXiv — Machine Learning research 3d ago Simultaneous inference of environmental and interaction forces in collective dynamics arXiv:2608.25181v1 Announce Type: new Abstract: Collective dynamics arise in a wide range of physical, biological, and engineering applications. Examples include cell migration, swarm robotics, social dynamics, and animal behavior. A defining characteristic of these systems is… 15 arXiv — Machine Learning research 3d ago Transforms for LLM Quantization: The Great Inversion and Format Co-Design arXiv:2608.25188v1 Announce Type: new Abstract: Most competitive 4-bit LLM research pipelines now open the same way: apply a linear, function-preserving transform (rotation, scaling, permutation, non-orthogonal affine) so the outlier mass sits more favorably against the group… 12 arXiv — Machine Learning research 3d ago What Should a Large Language Model See? Physical Invariants as a Data Representation for PDE Discovery arXiv:2608.25189v1 Announce Type: new Abstract: Understanding how molecular interactions govern macroscopic behaviour is a central challenge in molecular sciences. However, conventional theory building cannot keep pace with the vast datasets modern experimentation routinely… 12 arXiv — Machine Learning research 3d ago Hyperbolic Latent Geometry for Tree-Structured Prototype Networks: A Local-vs-Global Trade-off arXiv:2608.25199v1 Announce Type: new Abstract: We study a tree-structured regularizer over class-prototype layouts in a hierarchical-classification model and ask whether the choice of latent manifold for the prototypes (Euclidean R^d vs. the Poincare ball B^d_c) affects how… 20 arXiv — NLP / Computation & Language research 3d ago Learning Mixtures of Plackett-Luce Models for Multi-Objective Alignment arXiv:2608.25200v1 Announce Type: cross Abstract: We consider the problem of learning a mixture of $k$ Plackett-Luce models given multi-way ranking responses from annotators that may represent heterogeneous underlying preferences. This problem has many applications in AI… 30 arXiv — NLP / Computation & Language research 3d ago LibriBrain100: One Hundred Hours of Broad and Deep MEG Data for Neural Speech Decoding at Scale arXiv:2608.25204v1 Announce Type: cross Abstract: We introduce LibriBrain100, a large-scale MEG dataset for speech decoding designed from the ground up for reproducible, standardised evaluation. LibriBrain100 more than doubles the size of the original LibriBrain release,… 15 arXiv — Machine Learning research 3d ago Representing MAX functions using two-hidden-layer ReLU networks arXiv:2608.25221v1 Announce Type: new Abstract: We study exact representations of $\mathrm{MAX}_N(x)=\max{x_1,\ldots,x_N}$ using two-hidden-layer ReLU neural networks. This problem has been studied in recent years in an attempt to characterize the exact number of hidden layers… 17 arXiv — NLP / Computation & Language research 3d ago Trust the Mass: Forced Weights in KV-Cache Eviction arXiv:2608.25230v1 Announce Type: cross Abstract: Every deployed sparse-attention or KV-cache-eviction rule keeps a subset of the keys, discards the rest, and renormalizes the attention weights over the kept set. Enumerating the exact best subset under that constraint on… 36 arXiv — NLP / Computation & Language research 3d ago Output Dilution: Redundant but Fragile Representations in MoE Models arXiv:2608.25231v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models appear to encode moral content as robustly as dense models, yet prove far more fragile in their encoding. In OLMoE-1B-7B, linear probes recover moral valence from nearly every expert-layer… 27 arXiv — Machine Learning research 3d ago Long-Term Behavioral Evaluation for Trusted Collaborator Selection via Bidirectional Mamba arXiv:2608.25232v1 Announce Type: new Abstract: Effective selection of trustworthy collaborators is crucial to ensuring the successful completion of collaborative tasks, which requires accurate assessments of both long-term device behavior and short-term collaborative dynamics.… 16 arXiv — Machine Learning research 3d ago ShuttleArena: Interpretable Self-Play in Physics-Based Badminton arXiv:2608.25246v1 Announce Type: new Abstract: Badminton is a compact but challenging domain for game AI: a player must choose a physically feasible shuttle trajectory, anticipate the opponent's interception, and recover to a court position whose value depends on the opponent's… 21 arXiv — Machine Learning research 3d ago Neural-Bayesian Structure Learning for Discrete Choice Modeling arXiv:2608.25258v1 Announce Type: new Abstract: Conventional discrete choice and machine learning models are estimated primarily from observational data and typically treat explanatory covariates as parallel inputs, providing no internal mechanism for determining how related… 18 arXiv — Machine Learning research 3d ago Mitigating LLM sycophancy with RL-based fine-tuning: Bayesian Truth Serum approach arXiv:2608.25267v1 Announce Type: new Abstract: Large language models (LLMs) frequently exhibit \emph{sycophancy}: they adapt their answers to a user's stated beliefs or preferences instead of reporting what they hold to be true, which lowers factual accuracy and can amplify… 22 arXiv — Machine Learning research 3d ago SHSP: Structure-Aware Hierarchical Solution Prediction for Mixed-Integer Linear Programming arXiv:2608.25282v1 Announce Type: new Abstract: Mixed-Integer Linear Programming (MILP) is a fundamental optimization paradigm in combinatorial optimization and has been widely applied across real-world domains. Due to its NP-hard nature, obtaining optimal solutions for… 21 arXiv — Machine Learning research 3d ago InsightSR: Refining Symbolic Regression Search Spaces via Parallel Semantic and Structural LLM Guidance arXiv:2608.25291v1 Announce Type: new Abstract: Symbolic regression (SR) seeks to discover parsimonious mathematical laws from observational data, yet conventional approaches often struggle with the vast combinatorial search space of physically meaningful expressions. We present… 32 arXiv — Machine Learning research 3d ago Prefix-Denoising Consistency: Test-Time Verification for Diffusion Language Models arXiv:2608.25311v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) have recently become increasingly competitive with autoregressive (AR) models, and even outperform them on certain tasks. Unlike AR models, DLMs produce output through iterative denoising without a… 20 arXiv — Machine Learning research 3d ago Activation-Space Order-Swap Geometry: A Site-Asymmetry Audit arXiv:2608.25315v1 Announce Type: new Abstract: Order-dependent activation statistics are often interpreted as evidence of interaction, but that interpretation can be confounded by where interventions enter the network. We introduce a no-fit site-asymmetry audit. For a… 36 arXiv — Machine Learning research 3d ago Two Dimensions Govern Agnostic Multiclass Transductive Learning arXiv:2608.25326v1 Announce Type: new Abstract: In transductive classification, an adversary fixes a labeled population, one label is hidden uniformly, and the learner sees all remaining labels. For binary classes, agnostic transductive and PAC learning have the same minimax… 4 arXiv — Machine Learning research 3d ago Neither Precision Nor Architecture Alone: Controlled Tests of Failure Remedies for Physics-Informed Neural Networks arXiv:2608.25327v1 Announce Type: new Abstract: Physics-Informed Neural Networks (PINNs) frequently fail on stiff or advection-dominated PDEs, and two recent accounts offer competing remedies: switching from FP32 to FP64 to repair an L-BFGS stopping artifact, or replacing the… 7 arXiv — Machine Learning research 3d ago Beyond Pairwise Feedback: Listwise Vision-Language Supervision for Preference-Based Reward Learning arXiv:2608.25350v1 Announce Type: new Abstract: Vision-language models (VLMs) have emerged as a powerful source of supervision for reinforcement learning, enabling agents to leverage rich semantic knowledge during training. Inspired by the success of preference-based reward… 29 arXiv — NLP / Computation & Language research 3d ago Escaping Low-Dimensional Overlap: Multi-Task Model Merging via High-Dimensional Sparse Disentanglement arXiv:2608.25354v1 Announce Type: cross Abstract: Model merging provides an efficient way to construct multi-task generalist models without additional training, but its performance often degrades under severe task interference. Task interference in model merging primarily stems… 17 arXiv — Machine Learning research 3d ago PaSta: Noisy Node Classification with Partial Label Learning arXiv:2608.25365v1 Announce Type: new Abstract: Noisy node classification problem is a fundamental yet challenging task for real-world graph-related web services, where node labels are often corrupted or unreliable due to weak supervision or automatic annotation. However,… 16 arXiv — Machine Learning research 3d ago Refusal geometry reflects refusal training: diverse refusal prefixes can raise stable rank and weaken refusal vector ablation attacks arXiv:2608.25390v1 Announce Type: new Abstract: Refusal training protects AI models from jailbreaks by training models to decline unsafe queries, reducing the risk of misuse. Recent work finds that refusal behavior in aligned language models can be mediated by a single… 32 arXiv — Machine Learning research 3d ago Joint Initialization of Flux Networks and Effective Multiplication Factor for Physics-Informed Neural Networks Solving Neutron Diffusion Problems arXiv:2608.25443v1 Announce Type: new Abstract: Efficient determination of the effective multiplication factor (keff) is an important computational task in reactor core neutronics analysis. Physics-informed neural networks (PINNs) incorporate neutron diffusion equations and… 10 Page 5 of 10 · 500 articles ← Newer Older →
