Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks
1:03:33
Oscar: Object-Semantics Aligned Pre-training for Vision-Language T…
May 4, 2020
Microsoft
Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation
1:20
Reinforced Cross-Modal Matching and Self-Supervised Imitation Lear…
Nov 27, 2018
Microsoft
Vison-language pretraining is pushing AI forward in novel object captioning and image caption generation. Learn about powerful new VLP methods in this webinar and how advances permit captioning without image-text pairs on February 11 at 10 AM PT. Register now: https://aka.ms/AAaz6bh | Microsoft Research
0:50
Vison-language pretraining is pushing AI forward in novel objec…
169K viewsJan 30, 2021
FacebookMicrosoft Research
In vision-and-language pretraining (VLP), objects can be used as anchor points to make aligning semantics between image-text pairs easier. Learn how Oscar, a novel VLP framework utilizing objects, sets new state of the art on six vision-and-language tasks: https://aka.ms/AA8flix | Microsoft Research
0:12
In vision-and-language pretraining (VLP), objects can be used as anc…
22.5K viewsMay 15, 2020
FacebookMicrosoft Research
Research talk: Large-scale, self-supervised pretraining: From language to vision
24:50
Research talk: Large-scale, self-supervised pretraining: From lang…
Nov 16, 2021
Microsoft
2601.21420 - ConceptMoE: Adaptive Token-to-Concept Compression for Implicit Compute Allocation
13:41
2601.21420 - ConceptMoE: Adaptive Token-to-Concept Compression fo…
2 weeks ago
YouTubeAI Paper Cast
NICE Session 80: ICCV 2025 Paper Sharing Session 2
1:27:56
NICE Session 80: ICCV 2025 Paper Sharing Session 2
50 views5 months ago
YouTubeNLP Academic Exchange Platform
4:39
VLAs: Resilience to Catastrophic Forgetting
24 views2 weeks ago
YouTubeAI Research Roundup
4:43
RoBERTa: Pretraining BERT Better - Liu, Yinhan, et al
3 views3 weeks ago
YouTubeAI explains Science
0:37
Vision Language Models #GlobalSensorAwards#sensorawa…
2 months ago
YouTubeGlobal Sensor
5:06
EgoScale: Scaling Robot Dexterity with Human Data
93 views3 weeks ago
YouTubeAI Research Roundup
4:54
V-Pretraining: Targeted Model Training Method
12 views1 month ago
YouTubeAI Research Roundup
21:11
Beyond Language Modeling: An Exploration of Multimodal Pretrain…
1 views2 weeks ago
YouTubeXiaol.x
0:45
ICL CHARACTERIZATION OF MULTI-MODAL GEO-FOUNDATIO…
1 week ago
YouTubeDr. Mosab Hawarey
6:54
Beyond Language Modeling: Multimodal Pretraining & Transfus…
42 views1 week ago
YouTubeSciPulse
0:41
VaulTech | End of LLMs? VL-JEPA stands for Vision-Language Joint …
386 views2 months ago
Instagramvaultechi
48:07
OpenAI CLIP: ConnectingText and Images (Paper Explained)
171.6K viewsJan 12, 2021
YouTubeYannic Kilcher
15:08
Contrastive Language-Image Pretraining (CLIP)
753 views11 months ago
YouTubeAntonio Rueda-Toicen
13:44
Vision Transformers explained
69.5K viewsJul 1, 2023
YouTubeCode With Aarohi
1:13:22
Contrastive Language-Image Pre-training (CLIP)
12.5K viewsApr 27, 2022
YouTubeSamuel Albanie
6:05
What is LLM Distillation ?
32K viewsFeb 2, 2025
YouTubeNew Machina
11:41
Pay Attention to MLPs | NLP Journal Club
1.9K viewsMay 24, 2021
YouTubeThe NLP Lab
2:03
Qwen3-VL is here!
781.3K views6 months ago
YouTubeQwen
1:02:41
Python + AI: Vision models
3.2K views5 months ago
YouTubeMicrosoft Reactor
5:18
Perception Encoder - Paper Walkthrough
1.8K views9 months ago
YouTubeDataMListic
31:47
Image GPT: Generative Pretraining from Pixels (Paper Explained)
30.6K viewsJun 18, 2020
YouTubeYannic Kilcher
10:10
Transformer training shootout, part 2: AWS Trainium vs. NVIDIA V100
3.6K viewsMay 17, 2023
YouTubeJulien Simon
39:51
Multimodal Machine Learning | Introduction | Part 1 | CVPR 2022 T…
40.6K viewsAug 9, 2022
YouTubeArtificial Intelligence
37:00
Introduction to Vision Language Models (VLM)
12.2K views4 months ago
YouTubeVizuara
8:46
SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
171 views5 months ago
YouTubeXiaol.x
See more videos
Static thumbnail place holder