Search papers, labs, and topics across Lattice.
4
0
5
1
MemCatalyst reveals that targeted data poisoning can drastically boost membership inference accuracy in Vision-Language Models with minimal resource expenditure.
Tactile feedback can enhance VLA models without compromising their pretrained knowledge, leading to a 30.6 percentage-point improvement in manipulation tasks.
Privacy risks in retrieval-augmented generation are not static; they vary dynamically with user queries, and our new framework addresses this critical oversight.
GeoHAT achieves a remarkable 79.3% success rate in mobile manipulation, outperforming existing methods by a staggering 23.7% through innovative geometric token integration.
