VDT: General-purpose Video Diffusion Transformers via Mask Modeling
Paper
•
2305.13311
•
Published
Haoyu Lu
Nealeon
AI & ML interests
Towards Real-World Vision-Language Understanding. Core contributor of DeepSeek-VL and Kimi-VL.
Recent Activity
liked
a model
8 days ago
moonshotai/Kimi-K2-Instruct
upvoted
a
collection
11 days ago
Kimi-K2
Organizations
authored
10
papers
about 1 month ago
WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training
Paper
•
2103.06561
•
Published
DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
Paper
•
2401.02954
•
Published
•
49
DeepSeek-VL: Towards Real-World Vision-Language Understanding
Paper
•
2403.05525
•
Published
•
47
UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling
Paper
•
2302.06605
•
Published
Needle In A Video Haystack: A Scalable Synthetic Framework for Benchmarking Video MLLMs
Paper
•
2406.09367
•
Published
Towards Event-oriented Long Video Understanding
Paper
•
2406.14129
•
Published
Beyond Filtering: Adaptive Image-Text Quality Enhancement for MLLM Pretraining
Paper
•
2410.16166
•
Published
Kimi k1.5: Scaling Reinforcement Learning with LLMs
Paper
•
2501.12599
•
Published
•
121
R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization
Paper
•
2503.10615
•
Published
•
17
authored
a
paper
3 months ago