Zhiwei Zhang

State-of-the-art LLM agents face a staggering performance decline in multilingual workflows, revealing critical gaps in current evaluation methods.

Mid-tier LLMs outperform their stronger counterparts in harness self-evolution, challenging assumptions about model capability and adaptability.

Extracting agricultural parcels from satellite imagery gets a whole lot harder (and more realistic) with a new dataset focused on the complex, irregular, and heterogeneous terrain of terraced farms.

Coordinating multiple agents with a shared visual contract can dramatically improve the structural consistency and visual alignment of automatically generated scientific papers.