Multimodal Understanding

Seunghee Han, Jaewoong Lee, Jihan Kim

Multimodal Transformer models sample-level variability in MOFs, not just framework identity—enabling accurate property prediction for real experimental materials, transforming ML in materials science.

Habibeh Naderi, Behrouz Haji Soleimani, Stan Matwin

CALIBER introduces Bayesian low-rank adaptation for uncertainty-aware multimodal learning, enabling robust, efficient fine-tuning in low-resource settings—essential for builders deploying reliable multimodal systems under data scarcity.

Joongmin Shin, Chanjun Park, Jeongbae Park et al.

MultiDocFusion integrates vision and text to preserve structural context in long industrial documents, dramatically improving RAG accuracy—essential for enterprises relying on precise QA from complex PDFs, manuals, and reports.

Shilin Yan, Jintao Tong, Hongwei Xue et al.

Act Wisely separates task accuracy from tool-efficiency rewards so multimodal agents learn when not to call tools, cutting unnecessary invocations by orders of magnitude while improving accuracy, latency, and cost.