QTSplus
Query-Aware Tokenizer for Long-Video Multimodal Language Models.
Multimodal LLM
Alpachino
Hey there! Welcome to our team’s corner. We’re enthusiastic about Multimodal Large Language Models and explore ways to enhance interactions between language and image/video/audio.
Projects
Project pages hosted at /proj/*.
μ²Tokenizer
Differentiable Multi-Scale Multi-Modal Tokenizer for Radiology Report Generation.
About
Our research explores innovative ways to make AI systems better understand and generate multimodal content. We’re always on the lookout for practical techniques that improve capability and efficiency without sacrificing quality.