collaborators

6 papers

cs.LG2026

LLM Pretraining Shapes a Generalizable Manifold: Insights into Cross-Modal Transfer to Time Series

Alexis Roger, Prateek Humane, Zhenghan Tai +4

Can language-pretrained transformers become effective time-series forecasters, and why? In this paper, we show that cross-modal transfer arises because language pretraining precond…

cs.CV2025

Image Tiling for High-Resolution Reasoning: Balancing Local Detail with Global Context

Anatole Jacquin de Margerie, Alexis Roger, Irina Rish

Reproducibility remains a cornerstone of scientific progress, yet complex multimodal models often lack transparent implementation details and accessible training infrastructure. In…

cs.CL2025

Multilingual VLM Training: Adapting an English-Trained VLM to French

Jules Lahmi, Alexis Roger

Artificial intelligence has made great progress in recent years, particularly in the development of Vision--Language Models (VLMs) that understand both visual and textual data. How…

cs.LG2025

Small Vocabularies, Big Gains: Pretraining and Tokenization in Time Series Models

Alexis Roger, Gwen Legate, Kashif Rasul +2

Tokenization and transfer learning are two critical components in building state of the art time series foundation models for forecasting. In this work, we systematically study the…

cs.CV2025

CHIRP: A Fine-Grained Benchmark for Open-Ended Response Evaluation in Vision-Language Models

Alexis Roger, Prateek Humane, Daniel Z. Kaplan +7

The proliferation of Vision-Language Models (VLMs) in the past several years calls for rigorous and comprehensive evaluation methods and benchmarks. This work analyzes existing VLM…

cs.CL2025

Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting

Roland Riachi, Kashif Rasul, Arjun Ashok +5

Recent works have demonstrated the effectiveness of adapting pre-trained language models (LMs) for forecasting time series in the low-data regime. We build upon these findings by a…