🏢 Xi'an Jiaotong University

MARS: Optimizing prompts with multi-agent collaboration and Socratic learning for better LLM performance!

MAPS solves multimodal scientific problems better by combining multiple agents and Socratic learning.

GKG-LLM: Unifying Knowledge Graph Construction with a novel 3-stage framework, empowering domain adaptation & resource efficiency.

PhysReason benchmark evaluates physics-based reasoning in LLMs, revealing critical limitations and guiding future improvements.

LaDeCo: a layered approach to automatic graphic design composition, generating high-quality designs by sequentially composing elements into semantic layers.

ChatGen-Evo automates text-to-image generation from freestyle chatting, simplifying the process and significantly improving performance over existing methods.