Search papers, labs, and topics across Lattice.
Shenzhen University
2
0
5
LLMs can reason more effectively by directly tracking their own belief in the correct answer throughout the reasoning process, enabling more targeted policy updates.
Even the most advanced MLLMs like GPT-5 and Gemini struggle to spot the "odd one out" in simple visual grids, revealing a surprising weakness in fine-grained visual perception.
