activity
20242026
collaborators
Showing cs.CVShow all

10 papers · 1 filter

cs.CV2026

LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training

Andreas Hochlehnert, Marianna Nezhurina, Mehdi Cherti +9

We present LAION-BVD, a large-scale open video dataset for multimodal learning, which contains 1.3B platform-specific video URLs collected from CommonCrawl. From these, we download…

cs.CV2026

DataComp-VLM: Improved Open Datasets for Vision-Language Models

Matteo Farina, Vishaal Udandarao, Thao Nguyen +34

Building performant Vision-Language Models (VLMs) requires carefully curating large-scale training datasets, yet the community lacks systematic benchmarks for evaluating such curat…

cs.CV2026

Personalizing Text-to-Image Generation to Individual Taste

Anne-Sofie Maerten, Juliane Verwiebe, Shyamgopal Karthik +3

Modern text-to-image (T2I) models generate high-fidelity visuals but remain indifferent to individual user preferences. While existing reward models optimize for "average" human ap…

cs.CV2025

Concept-Aware Batch Sampling Improves Language-Image Pretraining

Adhiraj Ghosh, Vishaal Udandarao, Thao Nguyen +7

What data should a vision-language model be trained on? To answer this question, many data curation efforts center on the quality of a dataset. However, most of these existing meth…

cs.CV2025

Solving Spatial Supersensing Without Spatial Supersensing

Vishaal Udandarao, Shyamgopal Karthik, Surabhi S. Nath +3

Cambrian-S aims to take the first steps towards improving video world models with spatial supersensing by introducing (i) two benchmarks, VSI-Super-Recall (VSR) and VSI-Super-Count…

cs.CV2025

A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks

Vishaal Udandarao, Mehdi Cherti, Shyamgopal Karthik +3

We investigate 17 benchmarks (e.g. SugarCREPE, VALSE) commonly used for measuring compositional understanding capabilities of vision-language models (VLMs). We scrutinize design ch…