See-Kiong Ng

The fragmented field of world modeling can now be unified under a "levels x laws" taxonomy, revealing critical gaps in autonomous model revision and decision-centric evaluation.

Customer service chatbots can be transformed from reactive support tools into proactive business intelligence engines by strategically probing users for information.

Forget hand-coded strategies: METRO uses LLMs to automatically learn dialogue strategies from expert transcripts, achieving state-of-the-art results in non-collaborative dialogue.

LLMs struggle to maintain context and avoid distraction when reasoning about causality, leading to a significant performance drop as tasks increase in complexity.

A cleverly shaped and rendered adversarial patch can reliably spoof palmprint recognition, even across different models and datasets.