Yao Ma

Existing KB-VQA benchmarks mislead model evaluation, with flawed assumptions leading to overestimated reasoning capabilities in Visual Language Models.

MLLMs can significantly improve KB-VQA performance by first identifying entities from a limited candidate set before selecting evidence, leading to a more efficient and effective workflow.

Current red-teaming efforts miss the forest for the trees: ARES reveals that safety failures often stem from a systemic breakdown between the LLM *and* the reward model, not just the LLM itself.

A new lattice-based transaction scheme offers financial institutions a post-quantum secure and auditable distributed ledger solution that existing Ring-CT models can't provide.