4 papers across 3 sessions
We present Omni-Mol, a multitask molecular model that can solve any-to-any modality tasks
a new learning scheme for multi-modal LLM, LLAVA
A fine-tuning method for Compositionally-aware Learning in CLIP
A novel multi-modal multi-agent framework that enables agents to collaborate and share multi-modal data during training while allowing inference with reduced modalities at test time.
