Search papers, labs, and topics across Lattice.
Xi'an Jiaotong University
3
0
7
QUMem revolutionizes user-state inference by enabling LLMs to retrieve contextually relevant memories that evolve over time, outperforming existing methods on key benchmarks.
Visual-OPSD achieves a remarkable 14.3x speedup while boosting accuracy by over 3 percentage points, revealing the untapped potential of reasoning in visual thought generation.
LLMs struggle to explore multiple valid reasoning paths, often committing to a single route and missing alternative solutions, especially in complex, multi-step logical problems.
