# Changelog

All notable changes to this project will be documented in this file.

## [2.0.0] - 2025-06-03

### Added
- **Expanded Modality Support**: VLM2Vec now supports unified training and evaluation on three modalities: images, videos, and visual documents.
- **VLM2Vec v2**: Initial release of the V2 model and framework.
- **MMEB-v2 Benchmark**: Introduced a new comprehensive benchmark for evaluating performance across all supported modalities.

## [1.1.0] - 2025-02-11

### Changed
- Refactored the sub-batch splitting logic within GradCache and the VLM processor to simplify future extensions.