jungseoik

backseollgi

AI engineer with experience in Vision-Language Models (VLMs) and generative video retrieval, focusing on multimodal learning and video understanding.

liked a Space 4 months ago

PIA-SPACE_LeaderBoard

liked a Space 11 months ago

Chatterbox TTS supporting 23 languages

liked a Space over 1 year ago

VLMEvalKit Evaluation Results Collection

liked a Space almost 2 years ago

VLMEvalKit Eval Results in video understanding benchmark

liked a model almost 2 years ago

backseollgi's activity