Search papers, labs, and topics across Lattice.
The Chinese University of Hong Kong
3
0
4
LongSpace reveals that integrating explicit spatial memory into MLLMs can dramatically enhance their performance on long-horizon tasks, a critical advancement for applications in autonomous navigation.
Benchmark Agent reveals that current state-of-the-art models falter in domain-specific reasoning, underscoring the need for dynamic benchmarks in AI evaluation.
Current MLLMs falter in multi-stream contexts, achieving only 50% effectiveness, revealing a critical gap in their design for real-world applications.
