AI Research Intern, Vision-Language Model Direction

Job Detail

• Instruction Fine-Tuning: Assist in refining pre-trained vision-language models to better understand and follow complex instructions, enhancing their applicability across diverse tasks. • Deployment Acceleration: Collaborate with the team to optimize model inference performance, ensuring rapid deployment on various platforms. • Model Distillation: Engage in distilling knowledge from large-scale models into smaller, more efficient counterparts without significant loss of performance, facilitating easier deployment and scalability. • Quantization: Contribute to the quantization of vision-language models to reduce memory footprint and computational requirements, enabling deployment in resource-constrained environments. • Research and Development: Stay abreast of the latest advancements in vision-language modeling, propose innovative ideas, and apply cutting-edge technology to practical scenarios.