Machine Learning

Serious question. Did a transformer just describe itself and the universe and build itself a Shannon limit framework?

The Multiplicative Lattice as the Natural Basis for Positional Encoding Knack 2026 | Draft v6.0 Abstract We show that the apparent tradeo...

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...

Improving AI models’ ability to explain their predictions

[2512.16917] Generative Adversarial Reasoner: Enhancing LLM Reasoning with Adversarial Reinforcement Learning

Abstract page for arXiv paper 2512.16917: Generative Adversarial Reasoner: Enhancing LLM Reasoning with Adversarial Reinforcement Learning

[2512.04000] Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understanding

Abstract page for arXiv paper 2512.04000: Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understanding

[2511.21542] E0: Enhancing Generalization and Fine-Grained Control in VLA Models via Tweedie Discrete Diffusion

Abstract page for arXiv paper 2511.21542: E0: Enhancing Generalization and Fine-Grained Control in VLA Models via Tweedie Discrete Diffusion

[2511.20888] Deep Learning as a Convex Paradigm of Computation: Minimizing Circuit Size with ResNets

Abstract page for arXiv paper 2511.20888: Deep Learning as a Convex Paradigm of Computation: Minimizing Circuit Size with ResNets

[2510.12728] Data-Prompt Co-Evolution: Growing Test Sets to Refine LLM Behavior

Abstract page for arXiv paper 2510.12728: Data-Prompt Co-Evolution: Growing Test Sets to Refine LLM Behavior

[2510.10223] You only need 4 extra tokens: Synergistic Test-time Adaptation for LLMs

Abstract page for arXiv paper 2510.10223: You only need 4 extra tokens: Synergistic Test-time Adaptation for LLMs

[2510.04607] From Imperative to Declarative: Towards LLM-friendly OS Interfaces for Boosted Computer-Use Agents

Abstract page for arXiv paper 2510.04607: From Imperative to Declarative: Towards LLM-friendly OS Interfaces for Boosted Computer-Use Agents

[2508.02046] NaviMaster: Learning a Unified Policy for GUI and Embodied Navigation Tasks

Abstract page for arXiv paper 2508.02046: NaviMaster: Learning a Unified Policy for GUI and Embodied Navigation Tasks

[2507.00629] Generalization performance of narrow one-hidden layer networks in the teacher-student setting

Abstract page for arXiv paper 2507.00629: Generalization performance of narrow one-hidden layer networks in the teacher-student setting

[2506.20334] Recurrent neural network-based robust control systems with regional properties and application to MPC design

Abstract page for arXiv paper 2506.20334: Recurrent neural network-based robust control systems with regional properties and application ...

[2505.20714] Wideband RF Radiance Field Modeling Using Frequency-embedded 3D Gaussian Splatting

Abstract page for arXiv paper 2505.20714: Wideband RF Radiance Field Modeling Using Frequency-embedded 3D Gaussian Splatting

[2504.03486] Structured Legal Document Generation in India: A Model-Agnostic Wrapper Approach with VidhikDastaavej

Abstract page for arXiv paper 2504.03486: Structured Legal Document Generation in India: A Model-Agnostic Wrapper Approach with VidhikDas...

[2502.02861] Algorithms with Calibrated Machine Learning Predictions

Abstract page for arXiv paper 2502.02861: Algorithms with Calibrated Machine Learning Predictions

[2502.01754] Evaluation of Large Language Models via Coupled Token Generation

Abstract page for arXiv paper 2502.01754: Evaluation of Large Language Models via Coupled Token Generation

[2411.15087] Phrase-Instance Alignment for Generalized Referring Segmentation

Abstract page for arXiv paper 2411.15087: Phrase-Instance Alignment for Generalized Referring Segmentation

[2408.03404] Set2Seq Transformer: Temporal and Position-Aware Set Representations for Sequential Multiple-Instance Learning

Abstract page for arXiv paper 2408.03404: Set2Seq Transformer: Temporal and Position-Aware Set Representations for Sequential Multiple-In...

[2404.04265] Accelerating Matrix Factorization by Dynamic Pruning for Fast Recommendation

Abstract page for arXiv paper 2404.04265: Accelerating Matrix Factorization by Dynamic Pruning for Fast Recommendation

[2402.08151] Perturbative adaptive importance sampling for Bayesian LOO cross-validation

Abstract page for arXiv paper 2402.08151: Perturbative adaptive importance sampling for Bayesian LOO cross-validation

[2312.00357] A Generalizable Deep Learning System for Cardiac MRI

Abstract page for arXiv paper 2312.00357: A Generalizable Deep Learning System for Cardiac MRI

[2603.13334] Lipschitz-Based Robustness Certification Under Floating-Point Execution

Abstract page for arXiv paper 2603.13334: Lipschitz-Based Robustness Certification Under Floating-Point Execution