Xiangyu Kong

Even state-of-the-art vision-language models frequently lie and hallucinate when playing social deduction games, raising serious questions about their reliability in real-world applications requiring grounded reasoning.

RAG systems can be significantly improved by reranking documents based on how much they increase the LLM's confidence, not just their relevance.

A unified benchmark reveals the trade-offs between pixel-wise accuracy and perceptual realism in state-of-the-art image super-resolution techniques.

Interactive avatars can now exhibit more emotionally appropriate and contextually aware facial behaviors thanks to a novel architecture that disentangles audio-driven lip movements from user-driven non-lip facial expressions.