🏢 Singapore University of Technology and Design

MotionLab: One framework to rule them all! Unifying human motion generation & editing via a novel Motion-Condition-Motion paradigm, boosting efficiency and generalization.

GPT models’ multimodal reasoning abilities are tracked over time on challenging visual puzzles, revealing surprisingly steady improvement and cost trade-offs.

TANGOFLUX: Blazing-fast, high-fidelity text-to-audio generation using novel CLAP-Ranked Preference Optimization.

M-LongDoc: a new benchmark and retrieval-aware tuning framework revolutionizes multimodal long document understanding, improving model accuracy by 4.6%.