George Karypis

When LLMs get significantly worse: A statistical approach to detect model degradations

Knowledge Distillation for Large Language Models through Residual Learning

When Does Multimodality Lead to Better Time Series Forecasting?

MaxCode: A Max-Reward Reinforcement Learning Framework for Automated Code Optimization

Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models

MLZero: A Multi-Agent System for End-to-end Machine Learning Automation

AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents

Open Materials Generation with Stochastic Interpolants

AutoG: Towards automatic graph construction from tabular data

GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning

PROXSPARSE: REGULARIZED LEARNING OF SEMI-STRUCTURED SPARSITY MASKS FOR PRETRAINED LLMS

A Proximal Operator for Inducing 2:4-Sparsity

From Demonstrations to Rewards: Alignment Without Explicit Human Preferences

MoTE: Mixture of Task Experts for Embedding Models

Long-context Protein Language Model

Zero redundancy distributed learning with differential privacy