Search papers, labs, and topics across Lattice.
Affiliation:
5
0
8
3
SafeHarness is presented, which equips the model with two obstacle-aware harnesses that enable it to prioritize the safety constraint, and surpasses the previous SOTA by 6.5% and 27.0%, respectively.
BATON transforms long-horizon robot manipulation by making subtask exploration efficient and transition-aware, leading to significant performance gains.
Grounding preference learning in psychological and cultural constructs yields a significant boost in population alignment for LLMs, outperforming traditional demographic methods.
Quantization can increase bias in LLMs, with models generating stereotypes in one in four open-ended responses despite passing standard safety evaluations.
VLMs are prone to critical failures that vary significantly across cultures, exposing the inadequacy of Western-centric safety benchmarks.
