Machine Learning

Kimi bad at tool calling? [D]

So I've tried using kimi 2.5 in a personal project through AWS Bedrock. For simple tasks it does quite well. But when it comes to tool ca...

UMKC Announces New Master of Science in Artificial Intelligence

UMKC announces a new Master of Science in Artificial Intelligence program aimed at addressing workforce demand for AI expertise, set to l...

A Machine Learning Engineer Thought He Was Safe From AI Layoffs. Then He Got Some Depressing News

[2604.05257] Extending Tabular Denoising Diffusion Probabilistic Models for Time-Series Data Generation

Abstract page for arXiv paper 2604.05257: Extending Tabular Denoising Diffusion Probabilistic Models for Time-Series Data Generation

[2604.05250] DualDiffusion: A Speculative Decoding Strategy for Masked Diffusion Models

Abstract page for arXiv paper 2604.05250: DualDiffusion: A Speculative Decoding Strategy for Masked Diffusion Models

[2604.05248] Improving Sparse Memory Finetuning

Abstract page for arXiv paper 2604.05248: Improving Sparse Memory Finetuning

[2604.05230] Curvature-Aware Optimization for High-Accuracy Physics-Informed Neural Networks

Abstract page for arXiv paper 2604.05230: Curvature-Aware Optimization for High-Accuracy Physics-Informed Neural Networks

[2604.05217] On the Geometry of Positional Encodings in Transformers

Abstract page for arXiv paper 2604.05217: On the Geometry of Positional Encodings in Transformers

[2604.05185] Cross-fitted Proximal Learning for Model-Based Reinforcement Learning

Abstract page for arXiv paper 2604.05185: Cross-fitted Proximal Learning for Model-Based Reinforcement Learning

[2604.05181] General Multimodal Protein Design Enables DNA-Encoding of Chemistry

Abstract page for arXiv paper 2604.05181: General Multimodal Protein Design Enables DNA-Encoding of Chemistry

[2604.05164] Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reasoning

Abstract page for arXiv paper 2604.05164: Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reasoning

[2604.05134] Reasoning Through Chess: How Reasoning Evolves from Data Through Fine-Tuning and Reinforcement Learning

Abstract page for arXiv paper 2604.05134: Reasoning Through Chess: How Reasoning Evolves from Data Through Fine-Tuning and Reinforcement ...

[2604.05112] Vintix II: Decision Pre-Trained Transformer is a Scalable In-Context Reinforcement Learner

Abstract page for arXiv paper 2604.05112: Vintix II: Decision Pre-Trained Transformer is a Scalable In-Context Reinforcement Learner

[2604.05077] Feature-Aware Anisotropic Local Differential Privacy for Utility-Preserving Graph Representation Learning in Metal Additive Manufacturing

Abstract page for arXiv paper 2604.05077: Feature-Aware Anisotropic Local Differential Privacy for Utility-Preserving Graph Representatio...

[2604.05072] Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling

Abstract page for arXiv paper 2604.05072: Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Mo...

[2604.05064] Dynamic Linear Coregionalization for Realistic Synthetic Multivariate Time Series

Abstract page for arXiv paper 2604.05064: Dynamic Linear Coregionalization for Realistic Synthetic Multivariate Time Series

[2604.05057] Blind-Spot Mass: A Good-Turing Framework for Quantifying Deployment Coverage Risk in Machine Learning Systems

Abstract page for arXiv paper 2604.05057: Blind-Spot Mass: A Good-Turing Framework for Quantifying Deployment Coverage Risk in Machine Le...

[2604.05045] PCA-Driven Adaptive Sensor Triage for Edge AI Inference

Abstract page for arXiv paper 2604.05045: PCA-Driven Adaptive Sensor Triage for Edge AI Inference

[2604.05042] Energy-Based Dynamical Models for Neurocomputation, Learning, and Optimization

Abstract page for arXiv paper 2604.05042: Energy-Based Dynamical Models for Neurocomputation, Learning, and Optimization

[2604.04999] PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities

Abstract page for arXiv paper 2604.04999: PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities

[2604.04998] El Nino Prediction Based on Weather Forecast and Geographical Time-series Data

Abstract page for arXiv paper 2604.04998: El Nino Prediction Based on Weather Forecast and Geographical Time-series Data

[2604.04996] Learning-Based Multi-Criteria Decision Making Model for Sawmill Location Problems

Abstract page for arXiv paper 2604.04996: Learning-Based Multi-Criteria Decision Making Model for Sawmill Location Problems

[2604.04988] Prune-Quantize-Distill: An Ordered Pipeline for Efficient Neural Network Compression

Abstract page for arXiv paper 2604.04988: Prune-Quantize-Distill: An Ordered Pipeline for Efficient Neural Network Compression