VDT: General-purpose Video Diffusion Transformers via Mask Modeling
Paper
β’
2305.13311
β’
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
about 2 months ago
moonshotai/Kimi-K2-Thinking
liked
a model
5 months ago
moonshotai/Kimi-K2-Instruct
upvoted
a
collection
6 months ago
Kimi-K2
Organizations
authored
10
papers
7 months ago
WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training
Paper
β’
2103.06561
β’
Published
DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
Paper
β’
2401.02954
β’
Published
β’
50
DeepSeek-VL: Towards Real-World Vision-Language Understanding
Paper
β’
2403.05525
β’
Published
β’
48
UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling
Paper
β’
2302.06605
β’
Published
Needle In A Video Haystack: A Scalable Synthetic Framework for Benchmarking Video MLLMs
Paper
β’
2406.09367
β’
Published
Towards Event-oriented Long Video Understanding
Paper
β’
2406.14129
β’
Published
Beyond Filtering: Adaptive Image-Text Quality Enhancement for MLLM Pretraining
Paper
β’
2410.16166
β’
Published
Kimi k1.5: Scaling Reinforcement Learning with LLMs
Paper
β’
2501.12599
β’
Published
β’
126
R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization
Paper
β’
2503.10615
β’
Published
β’
17
authored
a
paper
9 months ago