Sanket Badhe

VLMs are prone to critical failures that vary significantly across cultures, exposing the inadequacy of Western-centric safety benchmarks.

Compact models can achieve frontier reasoning performance with minimal latency overhead, thanks to a novel method that distills explicit reasoning patterns into structured prompts.

LLMs still struggle with infrequently occurring knowledge, and this paper provides a structured framework to understand why, how we can fix it, and what the implications are for responsible AI.