🏢 Harvard University

4D LangSplat learns 4D language fields for dynamic scenes using multimodal large language models, enabling time-sensitive open-vocabulary queries.

FLAG-TRADER fuses LLMs & RL for enhanced financial trading, achieving superior performance compared to traditional methods by efficiently integrating multimodal data and adapting to market dynamics.

Affordance-Aware Object Insertion uses a novel Mask-Aware Dual Diffusion model & SAM-FB dataset to realistically place objects in scenes, considering contextual relationships.

GazeGen uses real-time gaze tracking to enable intuitive hands-free visual content creation and editing, setting a new standard for accessible AR/VR interaction.