Machine Learning
Papers on learning algorithms, neural networks, deep learning, and optimization.
cs.LG · 1353 papersEVA-Bench: A New End-to-end Framework for Evaluating Voice Agents
EVA-Bench is a new end-to-end framework for evaluating voice agents using realistic bot-to-bot audio simulations and novel composite metrics.
What is Learnable in Valiant's Theory of the Learnable?
This paper characterizes learnability in Valiant's original model, showing membership queries expand learnable classes and providing a new algorithm for halfspaces.
R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow
R-DMesh solves pose misalignment in video-guided 3D animation using a novel VAE and rectification offset for high-fidelity 4D mesh generation.
Topology-Preserving Neural Operator Learning via Hodge Decomposition
This paper introduces a topology-preserving neural operator learning method using Hodge decomposition to model physical field equations on geometric meshes.
QLAM: A Quantum Long-Attention Memory Approach to Long-Sequence Token Modeling
QLAM introduces a quantum long-attention memory, extending state-space models to efficiently capture long-range dependencies using quantum superposition.
Quantifying Sensitivity for Tree Ensembles: A symbolic and compositional approach
This paper introduces a novel symbolic and compositional method to quantify sensitivity in decision tree ensembles, efficiently identifying misclassification risks.
Negation Neglect: When models fail to learn negations in training
LLMs finetuned on documents that flag claims as false often learn to believe those claims are true, a phenomenon called Negation Neglect.
Reducing cross-sample prediction churn in scientific machine learning
This paper introduces "cross-sample prediction churn" in scientific ML and proposes data-side methods, including "twin-bootstrap," to significantly reduce it.
Harnessing Agentic Evolution
AEvo introduces a meta-editing framework that steers agentic evolution by dynamically revising the evolution process, outperforming existing methods.
Uncertainty-Driven Anomaly Detection for Psychotic Relapse Using Smartwatches: Forecasting and Multi-Task Learning Fusion
This paper introduces a smartwatch-based system for early psychotic relapse detection, combining cardiac forecasting and multi-task learning with uncertainty estimation.
Provable Quantization with Randomized Hadamard Transform
This paper introduces dithered quantization with randomized Hadamard transforms, offering provable, near-optimal MSE with high efficiency.
Parallel Scan Recurrent Neural Quantum States for Scalable Variational Monte Carlo
Introducing Parallel Scan Recurrent Neural Quantum States (PSR-NQS), this work demonstrates how RNNs can efficiently simulate large quantum many-body systems.
Min-Max Optimization Requires Exponentially Many Queries
Min-max optimization for nonconvex-nonconcave functions demands exponentially many queries to find an approximate stationary point.
Improving Reproducibility in Evaluation through Multi-Level Annotator Modeling
This paper introduces a multi-level bootstrapping method to improve AI evaluation reproducibility by modeling annotator behavior and analyzing data tradeoffs.
Di-BiLPS: Denoising induced Bidirectional Latent-PDE-Solver under Sparse Observations
Di-BiLPS is a neural framework that solves PDEs efficiently under extremely sparse data, outperforming SOTA with zero-shot super-resolution.
ENSEMBITS: an alphabet of protein conformational ensembles
Ensembits is the first tokenizer for protein conformational ensembles, capturing dynamic motions and alternative states for protein language modeling.
Force-Aware Neural Tangent Kernels for Scalable and Robust Active Learning of MLIPs
This paper introduces force-aware Neural Tangent Kernels and a scalable acquisition framework for robust active learning of MLIPs.
Interpretable Machine Learning for Antepartum Prediction of Pregnancy-Associated Thrombotic Microangiopathy Using Routine Longitudinal Laboratory Data
Machine learning predicts pregnancy-associated thrombotic microangiopathy (P-TMA) antepartum using routine longitudinal lab data with high accuracy.
Attention Once Is All You Need: Efficient Streaming Inference with Stateful Transformers
This paper introduces stateful transformers for efficient streaming inference, reducing query latency to O(|q|) by moving prefill off the critical path.
MinT: Managed Infrastructure for Training and Serving Millions of LLMs
MinT is a managed infrastructure system for efficiently training and serving millions of LoRA-adapted LLMs over shared base models.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.