The NeurIPS 2024 Preshow: What matters when building vision-language models?
35:17
The NeurIPS 2024 Preshow: Creating SPIQA: Addressing the Limitations of Existing Datasets for VQA
17:47
The NeurIPS 2024 Preshow: A Label is Worth a Thousand Images in Dataset Distillation
1:16:34
[EEML'24] Jovana Mitrović - Vision Language Models
22:44
The NeurlPS 2024 Preshow NaturalBench Evaluating Vision Language Model on Natural Adversarial Sample
47:35
Towards Reusability and Reproducibility of Research
57:45
Visualizing transformers and attention | Talk for TNG Big Tech Day '24
33:28
How Do We Build a General Intelligence?
45:04