Search papers, labs, and topics across Lattice.
Chinese Academy of Sciences, Nanyang Technological University
4
0
6
TacReasoner outperforms larger models in tactile reasoning tasks, achieving competitive results with fewer parameters.
CoLT slashes inference time by over 10x while enabling multi-modal models to reason more efficiently with fewer steps.
Text-to-image models can be tricked into generating images containing malicious text with over 90% success, even when standard jailbreak methods fail.
Open-source VLN agents can nearly double their navigation success by remembering where they've been, thanks to a new hierarchical memory system.
