Track manipulation, locomotion and embodied systems.
Search papers, labs, and topics across Lattice.
The University of Texas at Austin
4
0
9
14
A single auditor can generate its own hard training examples, turning a static dataset into a renewable source for improved failure prediction in multi-agent systems.
OPD may improve sampling efficiency, but it risks making previously solvable problems unsolvable, challenging the notion of true capability expansion in LLMs.
Existing Multi-modality Machine Unlearning methods are fundamentally flawed, allowing adversaries to recover nearly all supposedly erased sensitive information from MLLMs.