2 multiple-sequence-alignment Fellowship positions at Hong Kong Polytechnic University
-
the following competencies: • Hand-on PEFT for multimodal foundation models (LoRA/QLoRA/Adapters), with experience in video-language MLLMs (e.g., LLaVA-Video, VideoLLaMA3, Video-R1) and alignment; • Speech
-
framework; (b) undertake data collection, management, and analysis in alignment with project objectives; (c) coordinate and monitor project activities to ensure timely progress and adherence
Searches related to multiple sequence alignment
Enter an email to receive alerts for multiple-sequence-alignment positions