Emerging Properties in Unified Multimodal Pretraining
Paper
•
2505.14683
•
Published
•
130
AI & ML interests
Computer vision, Reinforcement learning
Recent Activity
View all activity
Andy1621
authored
17
papers
about 1 month ago
Unmasked Teacher: Towards Training-Efficient Video Foundation Models
Paper
•
2303.16058
•
Published
Harvest Video Foundation Models via Efficient Post-Pretraining
Paper
•
2310.19554
•
Published
MVBench: A Comprehensive Multi-modal Video Understanding Benchmark
Paper
•
2311.17005
•
Published
•
2
Vlogger: Make Your Dream A Vlog
Paper
•
2401.09414
•
Published
Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks
Paper
•
2401.14159
•
Published
•
3
Self-slimmed Vision Transformer
Paper
•
2111.12624
•
Published
•
1
UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning
Paper
•
2201.04676
•
Published
UniFormer: Unifying Convolution and Self-attention for Visual Recognition
Paper
•
2201.09450
•
Published
You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction
Paper
•
2205.14871
•
Published
UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer
Paper
•
2211.09552
•
Published
InternVideo: General Video Foundation Models via Generative and Discriminative Learning
Paper
•
2212.03191
•
Published
MUSES: 3D-Controllable Image Generation via Multi-Modal Agent Collaboration
Paper
•
2408.10605
•
Published
•
1
TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning
Paper
•
2410.19702
•
Published
VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling
Paper
•
2501.00574
•
Published
•
6
Make Your Training Flexible: Towards Deployment-Efficient Video Models
Paper
•
2503.14237
•
Published
•
5
Seed1.5-VL Technical Report
Paper
•
2505.07062
•
Published
•
145
Andy1621
authored
a
paper
6 months ago
Post
21911
Google drops Gemini 2.0 Flash Thinking
a new experimental model that unlocks stronger reasoning capabilities and shows its thoughts. The model plans (with thoughts visible), can solve complex problems with Flash speeds, and more
now available in anychat, try it out: https://huggingface.co/spaces/akhaliq/anychat
a new experimental model that unlocks stronger reasoning capabilities and shows its thoughts. The model plans (with thoughts visible), can solve complex problems with Flash speeds, and more
now available in anychat, try it out: https://huggingface.co/spaces/akhaliq/anychat
- 4 replies
Andy1621
authored
a
paper
6 months ago