MegaHan97K: A Large-Scale Dataset for Mega-Category Chinese Character Recognition with over 97K Categories Paper • 2506.04807 • Published 9 days ago • 2
CSVQA: A Chinese Multimodal Benchmark for Evaluating STEM Reasoning Capabilities of VLMs Paper • 2505.24120 • Published 15 days ago • 48
UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalization Paper • 2408.05939 • Published Aug 12, 2024 • 15
DeepSeek LLM: Scaling Open-Source Language Models with Longtermism Paper • 2401.02954 • Published Jan 5, 2024 • 49
Control-A-Video: Controllable Text-to-Video Generation with Diffusion Models Paper • 2305.13840 • Published May 23, 2023 • 4 • 1