Multimodal Algo Researcher (AI Innovation Center) Intern - 2026 Soaring Star Talent Program

About The Team

The mission of the TikTok Eng-AI Innovation Center is to explore cutting-edge AGI technologies, including but not limited to LLM, multi-modal LLM (video/image/audio/text/code), etc., to let machine better understand user creations on Tiktok platform. Regarding to video/image/audio/text, enhanced content understanding can bring better user experience of searching, recommendation, and can more accurately identify and defend internet abuse and fraud on our platform. Regarding to code, our developed LLM aims to automatically re-organize/optimize Tiktok codebase, and make the code/coding become more accessible for Tiktok engineers.

Project Introduction: Multimodal foundation large models (VLM) represent a research hotspot in the industry and a critical technology for TikTok's business scenario applications. In 2024, TikTok's Innovation Center developed VFM V1, a multimodal large model tailored for TikTok's business scenarios. It matches the performance of the best open-source model Qwen VL on public test sets, while significantly outperforming all other foundation models on TikTok's business test sets. In the future, we aim to continuously develop foundation models with efficient perception and reasoning capabilities, capable of handling multilingual and massive video content understanding algorithms to deliver a better content consumption experience for users.

Project Challenges: Enhance the multimodal perception encoder: The current encoder uses a fixed frame rate. We need to explore more efficient adaptive frame rates while considering the integration of modalities such as audio and user behavior. How to fuse multimodal perception and thinking capabilities to promote stronger comprehensive perception and cognitive abilities of the model.