News / #paper Tag Research papers 500 articles archived under #paper · RSS Sign in to follow arXiv — NLP / Computation & Language research 7d ago Just for FUNS: LLM-Guided Spatio-Temporal Graph Node Generation for Forecasting Unobserved Node States arXiv:2610.08818v1 Announce Type: cross Abstract: Spatio-temporal forecasting is a cornerstone of logistics, urban planning, and intelligent transportation systems. However, constrained by deployment costs and maintenance resources, sensor networks often lack comprehensive… 7 arXiv — Machine Learning research 7d ago HydroSphere: A Framework for Governed, Self-Healing Wastewater Infrastructure arXiv:2610.08819v1 Announce Type: new Abstract: Rapid industrialization and urban growth are increasing pressure on water quality and wastewater treatment systems, while conventional treatment plants often rely on static monitoring and control strategies that cannot easily adapt… 33 arXiv — Machine Learning research 7d ago Task-Oriented Key-Layer KV Communication for Efficient Latent Multi-Agent Collaboration arXiv:2610.08820v1 Announce Type: new Abstract: Large language model-based multi-agent systems improve complex problem solving through collaboration, while latent communication directly transmits model internal states to avoid the high inference costs of natural language.… 16 arXiv — Machine Learning research 7d ago A Vehicle-Integrated Approach to Digital Twin Deployment for Bridges Through Drive-By Sensing arXiv:2610.08822v1 Announce Type: new Abstract: Ageing bridge infrastructure is a growing global concern, yet conventional Structural Health Monitoring (SHM) systems are costly and difficult to scale, and routine visual inspections remain subjective. Drive-by, or indirect,… 13 arXiv — Machine Learning research 7d ago HCPN-GCN: Scaling Hierarchical Prototype Networks with Cone Geometry for Continual Graph Learning arXiv:2610.08823v1 Announce Type: new Abstract: Continual Graph Learning (CGL) aims to incrementally learn from graph-structured data while preserving knowledge acquired from previous tasks. A major challenge in this setting is catastrophic forgetting, where learning new tasks… 10 arXiv — NLP / Computation & Language research 7d ago FinVector-Market-4B: A Controlled Study of LoRA Adaptation for Structured Financial Tasks arXiv:2610.08882v1 Announce Type: cross Abstract: FinVector-Market-4B adapts Qwen/Qwen3.5-4B with rank-16 LoRA on a 22,000-example corpus for structured financial tasks. We evaluate the base and adapted models on the same 600-example benchmark under implicit and explicit… 8 arXiv — Machine Learning research 7d ago GraphOPD: Graph-Augmented On-Policy Distillation for LLM Agents arXiv:2610.08959v1 Announce Type: new Abstract: On-policy distillation post-trains large language model agents by supplying dense, step-level guidance from a teacher policy when the reinforcement-learning reward is sparse and arrives only once per trajectory. Existing… 35 arXiv — Machine Learning research 7d ago Directed Temporal Representations for Offline Visual Control arXiv:2610.08960v1 Announce Type: new Abstract: Predictive world models provide compact visual representations for control. Control requires a latent geometry aligned with temporal reachability rather than predictive similarity alone. We introduce Directed Temporal… 24 arXiv — NLP / Computation & Language research 7d ago On KL-Regularized Policy Optimization arXiv:2610.08963v1 Announce Type: cross Abstract: Asynchronous reinforcement learning (RL) for large language model (LLM) agents trains one policy on trajectories generated by another: rollouts come from stale checkpoints, and the inference engine's probabilities differ from the… 4 arXiv — Machine Learning research 7d ago Work While They Sleep: Exploiting Evaluation Latency for Fully Bayesian Optimization arXiv:2610.08969v1 Announce Type: new Abstract: Black-box optimization problems are ubiquitous across science and engineering, often dealing with expensive objective functions. This objective latency has two consequences during optimization: (i) the objective evaluation… 31 arXiv — Machine Learning research 7d ago The Best Optimizer Depends on Batch Size arXiv:2610.08975v1 Announce Type: new Abstract: A plethora of new adaptive optimizers are designed to efficiently estimate and use minibatch gradient statistics to shape parameter updates, but they are typically benchmarked at a single batch size. Hyperparameter scaling rules… 34 arXiv — Machine Learning research 7d ago SNR-Gated LSTM-Conditioned Diffusion Model for MIMO Channel Estimation arXiv:2610.08977v1 Announce Type: new Abstract: Accurate and low latency channel estimation is critical for modern MIMO systems, particularly under mobility, where channels exhibit structured sparsity and strong temporal correlation. This paper proposes a time-series conditioned… 36 arXiv — Machine Learning research 7d ago LASER: Latent Space Adjoint Matching for Support-Constrained Entropy-Regularized Offline RL arXiv:2610.08989v1 Announce Type: new Abstract: While offline reinforcement learning (RL) enables policy optimization from static datasets without costly online interaction, it remains bottlenecked by the risk of executing out-of-distribution (OOD) actions. Recent approaches… 5 arXiv — Machine Learning research 7d ago REFIT: Recognize, Fix, and Test Wearable Sensor Placement Shifts without Labels arXiv:2610.08991v1 Announce Type: new Abstract: We present REFIT, an input calibration for frozen activity-recognition models whose inertial sensors are worn differently at deployment than in training. When users move a watch to the other wrist or put a strap sensor back on… 29 arXiv — Machine Learning research 7d ago Algorithmic Scratchpads and Curriculum Staging for Arithmetic Reasoning in Tiny Transformers arXiv:2610.09003v1 Announce Type: new Abstract: Autoregressive Large Language Models (LLMs) frequently struggle with deterministic multi-step algorithmic tasks such as multi-digit multiplication and long division. In this paper, we investigate the mechanics of multi-step… 7 arXiv — Machine Learning research 7d ago Removing Information Content Does Not Certify Tamper Resistance in Open-Weight Models arXiv:2610.09004v1 Announce Type: new Abstract: Does removing harmful information make open-weight models resistant to fine-tuning attacks? We show that mutual information at release alone cannot universally certify slow recovery. Function-preserving reparameterizations leave… 8 arXiv — Machine Learning research 7d ago Neighborhood Smoothing for Calibration arXiv:2610.09020v1 Announce Type: new Abstract: Modern neural networks are often miscalibrated, with a tendency to overconfidence. Existing train-time calibration methods largely modify task losses or calibration penalties, leaving neighborhood structure in learned… 33 arXiv — Machine Learning research 7d ago SPIN: Shadow Predictive Indexer for Sparse Attention arXiv:2610.09025v1 Announce Type: new Abstract: Indexer-based sparse attention reduces the cost of core attention by passing only a fixed, small number of important tokens to it. However, the indexer must still score the entire KV cache at every decoding step. This scoring… 11 arXiv — Machine Learning research 7d ago ORACLE: Optimizer-Relative Alignment for Constrained LEarning arXiv:2610.09040v1 Announce Type: new Abstract: Constraint handling methods typically intervene before the optimizer acts, by modifying the objective or the gradient. Yet momentum, adaptive scaling, and structured preconditioning can substantially reshape that signal before it… 38 arXiv — Machine Learning research 7d ago Towards Financial World Modeling arXiv:2610.09048v1 Announce Type: new Abstract: Building a world model requires a state representation useful for planning and decision-making---potentially over tasks unknown at training time. In the context of financial markets, planning and decision-making may require a model… 6 arXiv — Machine Learning research 7d ago A Self-Pruning Transformer: Extreme KV-Cache Compression with Universal Attention arXiv:2610.09051v1 Announce Type: new Abstract: The large KV-cache size of modern LLMs creates a barrier to efficient deployment. Recent work has explored replacing attention layers' RoPE positional embeddings with alternative decay-based mechanisms, which can then be used to… 30 arXiv — Machine Learning research 7d ago BeatFlow-ECG: Rectified Flow for ECG Reconstruction from Indirect Wearable Signals arXiv:2610.09052v1 Announce Type: new Abstract: Continuous cardiac monitoring outside clinical settings requires signals that are both informative and practical to collect during daily life. Electrocardiography (ECG) provides rich information about cardiac rhythm and waveform… 6 arXiv — Machine Learning research 7d ago A Geometry-Based Capacity Theory for Finite-Feature Associative Memory arXiv:2610.09056v1 Announce Type: new Abstract: We develop a geometry-based capacity theory for exact-key retrieval in compressed finite-feature Hebbian associative memory. For random or approximately isotropic values, retrieval interference separates into finite-feature noise,… 24 arXiv — Machine Learning research 7d ago Learning Cross-Model Activation Alignments with Explicit Many-to-Many Layer Maps arXiv:2610.09058v1 Announce Type: new Abstract: LLMs are released at a rapid pace, raising a natural question: how do two independently trained models relate, both in which layers correspond and in how features transform between them? We study this by learning an activation… 19 arXiv — Machine Learning research 7d ago EDiS: Edge Disjoint Subgraph Sparsification Framework for Graph Neural Networks arXiv:2610.09059v1 Announce Type: new Abstract: Sparse GNN training reduces computation, but deciding which edges to keep can be costly. Reusing one sparse graph is cheap, but locks training to a fixed topology, while varying it across epochs can require repeated sampling or… 38 arXiv — NLP / Computation & Language research 7d ago Multi-Label Topic Assignment via LLM Distillation: A Comparative Analysis of Generative vs. Discriminative Student Models arXiv:2610.09063v1 Announce Type: cross Abstract: Multi-label topic assignment for user-generated content (UGC) -- including product reviews and buyer-seller conversations -- poses unique scalability challenges in large-scale e-commerce due to informal language, extreme label… 21 arXiv — Machine Learning research 7d ago TAP: Efficient Long-Horizon Agent Pruning via Trajectory-Anchored Recovery arXiv:2610.09074v1 Announce Type: new Abstract: Emerging long-horizon agentic tasks require repeated model calls, worsening the inference cost of already-costly language models. While narrow agentic tasks suggest potential for aggressive model pruning without performance drop,… 9 arXiv — Machine Learning research 7d ago Tucker Bottleneck Attention for Multi-Dimensional Sequence Modeling arXiv:2610.09090v1 Announce Type: new Abstract: The quadratic cost of self-attention limits scalability to long sequences from multidimensional data. We introduce Tucker bottleneck attention (TuBA), which exploits low-rank tensor structure for efficient global token mixing. TuBA… 29 arXiv — Machine Learning research 7d ago FedRSPO+: A Heterogeneity-aware Algorithm for Decision-focused Federated Learning arXiv:2610.09091v1 Announce Type: new Abstract: Decision-focused learning (DFL) trains predictive models for downstream optimization, but existing methods largely assume centralized data. In cross-silo settings, federated learning offers a natural alternative, yet standard… 7 arXiv — Machine Learning research 7d ago MaRK: Markov-adapted Recurrent Kernels for Dynamic Operator Conditioning in State Space Models arXiv:2610.09092v1 Announce Type: new Abstract: State Space Models (SSMs) offer an efficient alternative to Transformers for sequence modeling, yet conditioning pre-trained SSMs for iterative generation typically operates outside the recurrent operator, through input injection… 21 arXiv — Machine Learning research 7d ago Are We Really Benchmarking Forecasting Models? The Impact of Preprocessing on Time Series Performance arXiv:2610.09096v1 Announce Type: new Abstract: While established literature underscores the pivotal role of preprocessing in forecasting accuracy, this stage remains largely overlooked in current research. Modern benchmarks typically resort to simple scaling, failing to account… 37 arXiv — Machine Learning research 7d ago Convex-Concave Reinforcement Learning arXiv:2610.09108v1 Announce Type: new Abstract: Policy learning drives many of the most consequential and heavily-invested applications of reinforcement learning today. Yet the core optimization problem it rests on (maximizing expected return) is notoriously non-convex, even… 4 arXiv — Machine Learning research 7d ago Breaking Adversarial Transferability in Fine-Tuned Speech Recognition arXiv:2610.09109v1 Announce Type: new Abstract: Many organizations fine-tune publicly available pretrained Automatic Speech Recognition (ASR) models and deploy them in black-box settings, assuming limited access provides protection. We show this assumption is fragile:… 31 arXiv — Machine Learning research 7d ago The Deceptive Bandit Problem: Exploratory Coupling and the Fragility of Multi-Agent Learning arXiv:2610.09120v1 Announce Type: new Abstract: Randomized exploration is central to bandit learning, multi-agent reinforcement learning, and zeroth-order policy search, yet its independence and privacy are usually only treated as technical assumptions. We show that these… 11 arXiv — Machine Learning research 7d ago Are Parameter-Efficient Fine-tuning Methods Really Different? arXiv:2610.09122v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) offers many parameterizations, yet their methodological and functional differences remain unclear. We compare six methods in language and diffusion models to examine how their… 35 arXiv — Machine Learning research 7d ago Spatial Induction Heads: In-Context Learning of Multidimensional Cellular Automata arXiv:2610.09124v1 Announce Type: new Abstract: Induction heads provide a mechanistic account of in-context learning in sequential data, but existing theory largely assumes that the context relevant to a prediction forms a contiguous block. In multidimensional data,… 36 arXiv — Machine Learning research 7d ago Domain-informed Adaptive Sampling for Generalizable PINNs in Metal Additive Manufacturing via Conditional Flow Matching arXiv:2610.09126v1 Announce Type: new Abstract: Accurate thermal modeling is essential in metal additive manufacturing (AM) for understanding the process-structure-property chain. Physics-informed neural networks (PINNs) offer effective surrogate thermal modeling by minimizing… 29 arXiv — Machine Learning research 7d ago Directional Evidence Guided Search-Space Reduction for Exact DAG Learning arXiv:2610.09136v1 Announce Type: new Abstract: Learning a directed acyclic graph (DAG) from observational data is a challenging combinatorial problem due to the exponential growth in the number of candidate parent-set configurations. Existing exact score-based methods often… 33 arXiv — Machine Learning research 7d ago A Cognitive-Aware QML-CRL Framework for Detecting Affinity and Romance-Investment Fraud arXiv:2610.09141v1 Announce Type: new Abstract: We present a hybrid quantum-classical framework that detects affinity and romance-investment fraud by modelling the cognitive biases in a manipulative conversation. In our proposed framework, cognitive biases central to this fraud… 37 arXiv — NLP / Computation & Language research 7d ago Noise Your Prompt: Noising Conditioning Tokens in Continuous Diffusion Language Models arXiv:2610.09145v1 Announce Type: cross Abstract: We revisit a standard accepted practice in the continuous diffusion language model literature of fixing conditioning prompt tokens clean during training. We make a very simple modification: also noise the conditioning prompt… 9 arXiv — Machine Learning research 7d ago Context-aware Attention-based Gaussian Mixture Models for Vehicular Trajectory Prediction arXiv:2610.09174v1 Announce Type: new Abstract: Reliable and interpretable trajectory prediction is critical for cooperative and autonomous driving in complex and uncertain environments. This paper introduces a Context-Aware Attention-based Gaussian Mixture Model (CAA-GMM) for… 30 arXiv — NLP / Computation & Language research 7d ago LayerRoPE: Dynamic Depth-wise Magnitude & Angular Superposition arXiv:2610.09179v1 Announce Type: cross Abstract: As data propagates through a Transformer, the norm of its hidden states grows by orders of magnitude with depth, a phenomenon framed as 'curse of depth' and nearly universally treated as a pathology to be suppressed. We take the… 35 arXiv — Machine Learning research 7d ago Q-PACE: Dynamic Precision Allocation for Quantization-Aware Training arXiv:2610.09183v1 Announce Type: new Abstract: Quantization-aware training (QAT) leverages lower-precision arithmetic to reduce the cost of LLM deployment, but aggressive quantization degrades final model performance. A common remedy is mixed-precision training, in which high… 22 arXiv — Machine Learning research 7d ago The Dichotomy Between Pattern Recognition and Step-by-Step Reasoning arXiv:2610.09186v1 Announce Type: new Abstract: We argue that pattern recognition and step-by-step reasoning are two ends of a spectrum. A large language model (LLM) learns to reason step-by-step when data is structured such that the next token depends on a small amount of… 14 arXiv — Machine Learning research 7d ago Patient, Place, Prior (P$^3$): What Counts as Personalization in Medical World Models? arXiv:2610.09194v1 Announce Type: new Abstract: Longitudinal models forecast how a patient's imaging state evolves, but accuracy does not show whether the patient's observed trajectory drives the prediction. A population-average forecast may be useful but cannot establish a… 36 arXiv — Machine Learning research 7d ago Exact Dynamics and Finite-Sample Trajectory Recovery of Linear Recursive Feature Machines arXiv:2610.09196v1 Announce Type: new Abstract: Recursive feature machines (RFMs) learn representations of data by alternating between fitting a predictor to a dataset and updating features of that predictor using the average gradient outer product (AGOP). Connections between… 7 arXiv — Machine Learning research 7d ago An Accuracy--Information Tradeoff for Loss-Difference Conditional Mutual Information arXiv:2610.09206v1 Announce Type: new Abstract: Loss-difference conditional mutual information (ld-CMI) uses the smallest of the standard observations in the supersample hierarchy of generalization bounds: it measures what a learner's loss differences reveal about which… 10 arXiv — Machine Learning research 7d ago CurveTQ: Rotation-Free Trellis Quantization of LLM Weights via Curvature-Weighted Search arXiv:2610.09212v1 Announce Type: new Abstract: The best two-bit weight quantizers for large language models, such as QTIP and Proteus, rotate each weight matrix by a random orthogonal transform, which must be undone at every decoding step, then encode it with a trellis or… 6 arXiv — Machine Learning research 7d ago Consistent Distribution Matching for Data-Free Diffusion Distillation arXiv:2610.09221v1 Announce Type: new Abstract: Flow and diffusion models suffer from slow inference due to computationally expensive numerical integration. Distillation provides a promising way for a student model to learn from a teacher's dynamics, enabling one-step or… 7 arXiv — Machine Learning research 7d ago Conditional Accuracy Profiles: Diagnosing LLM Judges across Deployment Conditions arXiv:2610.09229v1 Announce Type: new Abstract: LLM-as-judge is now a standard tool for scalable evaluation, but judge performance is still often summarized by a single accuracy number. This aggregate view hides the deployment conditions under which a judge succeeds or fails. We… 22 Page 9 of 10 · 500 articles ← Newer Older →
