Irina Rish

GitChameleon 2.0: Evaluating AI Code Generation Against Python Library Version Incompatibilities

arXiv 2025

Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training

arXiv 2025

RedPajama: an Open Dataset for Training Large Language Models

arXiv 2024

Context is Key: A Benchmark for Forecasting with Essential Textual Information

arXiv 2024

VFA: Vision Frequency Analysis of Foundation Models and Human

arXiv 2024

Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning

arXiv 2024

Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale

arXiv 2024

GitChameleon: Unmasking the Version-Switching Capabilities of Code Generation Models

arXiv 2024

Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting

arXiv 2023

APP: Anytime Progressive Pruning

arXiv 2022

Diganta Misra

Alexandre Drouin

researcher

Andrew Robert Williams

Arjun Ashok

Justine Gehring

Massimo Caccia

researcher

Md Rifat Arefin

Mohammad Javad Darvishi Bayazi

Nicolas Chapados

researcher

Nizar Islah