Search papers, labs, and topics across Lattice.
Beijing University of Posts and Telecommunications, Beijing, Beijing, China
5
0
8
3
Today's best vision-language models are surprisingly bad at reading scientific figures, failing to match expert-level reasoning on a new benchmark of experimental images.
LLMs can now generate research roadmaps that are 8% better and 84% faster than human experts, thanks to a novel multi-agent system.
Retrieval improvements don't always boost reasoning in RAG systems, but NeocorRAG's evidence chains can fix that, achieving SOTA with 20% fewer tokens.
Even GPT-5.1 struggles to distinguish AI-generated academic images from real ones, achieving only 48.8% accuracy, revealing a significant gap between generative and forensic AI capabilities.
LLM-powered recommendation agents, despite their reasoning prowess, are easily manipulated by contextual biases in high-stakes scenarios like paper review and job recruitment.
