Chi Zhang

DiagramRAG is a lightweight retrieval-augmented framework that uses reference diagrams to guide the completion of scientific diagrams from incomplete user sketches, achieving high performance on standard benchmarks.

The paper proposes ESC-Skills, a skill-centric framework that discovers and self-evolves executable emotional support skills to improve the interpretability and emotional quality of conversational AI.

The paper proposes TCP-MCP, a co-evolution framework that jointly optimizes agent prompts and communication topologies to design highly efficient and effective multi-agent systems.

Xetrieval introduces an embedding-level framework to mechanistically explain dense retrieval decisions by decomposing high-dimensional embeddings into sparse, human-interpretable features.

This paper introduces CFMME, a comprehensive Chinese financial multimodal benchmark, and evaluates current Large Vision-Language Models (LVLMs), finding that while state-of-the-art models perform moderately, there is significant room for improvement in handling complex financial multimodal tasks.

MindZero introduces a self-supervised reinforcement learning framework that trains multimodal large language models (MLLMs) for efficient and robust online mental reasoning without requiring explicit mental state annotations.

The paper introduces OpenSTBench, a unified, multidimensional evaluation framework designed to comprehensively compare heterogeneous speech translation systems by jointly assessing translation, speech, and temporal qualities.

MESA is a targeted alignment framework that decentralizes safety responsibilities across multiple experts in Mixture-of-Experts (MoE) LLMs using Optimal Transport theory, thereby improving safety robustness without sacrificing utility.