[cvpr 2024] multiflow: shifting towards task-agnostic vision-language pruning
Published 4 months ago • 15 plays • Length 5:00Download video MP4
Download video MP3
Similar videos
-
3:54:28
mllm series tutorial @ cvpr 2024
-
![[cvpr 2024] laa-net: 5 min presentation](https://i.ytimg.com/vi/WCSiuNOYWRk/mqdefault.jpg)
5:44
[cvpr 2024] laa-net: 5 min presentation
-
![[cvpr 2024] superprimitive: scene reconstruction at a primitive level](https://i.ytimg.com/vi/hKYgAf6MoB8/mqdefault.jpg)
4:17
[cvpr 2024] superprimitive: scene reconstruction at a primitive level
-
![[cvpr24 vision foundation model tutorial] large multimodal models by chunyuan li](https://i.ytimg.com/vi/S0CpenMvG48/mqdefault.jpg)
50:19
[cvpr24 vision foundation model tutorial] large multimodal models by chunyuan li
-
![[cvpr 2024 highlight] feature 3dgs (5 min talk)](https://i.ytimg.com/vi/DIjUVttqOfQ/mqdefault.jpg)
5:01
[cvpr 2024 highlight] feature 3dgs (5 min talk)
-
![[cvpr 2024] rt-detr, detrs beat yolos on real-time object detection.](https://i.ytimg.com/vi/UOc0qMSX4Ac/mqdefault.jpg)
12:55
[cvpr 2024] rt-detr, detrs beat yolos on real-time object detection.
-
6:51
cvpr 2024: humannorm, high-quality and realistic 3d human generation
-
5:00
cvpr 2024 paper: small steps and level sets: fitting neural surface models with point guidance
-
![[cvpr 2024 highlight] efficient loftr: semi-dense local feature matching with sparse-like speed](https://i.ytimg.com/vi/mdKcD7Dr9UM/mqdefault.jpg)
0:16
[cvpr 2024 highlight] efficient loftr: semi-dense local feature matching with sparse-like speed
-
![[cvpr 2024] extranerf](https://i.ytimg.com/vi/xe3SM-8FdHo/mqdefault.jpg)
8:27
[cvpr 2024] extranerf
-
![[cvpr 2024] rohm: robust human motion reconstruction via diffusion](https://i.ytimg.com/vi/hX7yO2c1hEE/mqdefault.jpg)
5:01
[cvpr 2024] rohm: robust human motion reconstruction via diffusion
-
![[cvpr 2024] on the robustness of language guidance for low-level vision tasks](https://i.ytimg.com/vi/gmmODGh1ulk/mqdefault.jpg)
5:08
[cvpr 2024] on the robustness of language guidance for low-level vision tasks
-
0:21
imageomics bioclip research wins best student paper at cvpr 2024
-
![[cvpr 2024] scaling laws of synthetic images for model training ... for now](https://i.ytimg.com/vi/iiXQTR8dXcc/mqdefault.jpg)
4:54
[cvpr 2024] scaling laws of synthetic images for model training ... for now
-
3:52
cvpr 2024 drivinggaussian