Search papers, labs, and topics across Lattice.
8
12
12
5
Collapsed generation reveals unique fingerprints in diffusion models, enabling reliable ownership verification without invasive watermarks.
Auditing Chinese web content reveals pervasive pollution that shifts over time, challenging the integrity of LLM training data.
Released tokenizer vocabularies can yield precise estimates of hidden corpus compositions, revealing insights that were previously obscured.
OEO shows that a capable optimizer can outperform traditional pipelines, achieving 12 wins in 14 comparisons while using significantly fewer resources.
AEGIS achieves near-zero attack success rates against visual synonym jailbreaks while preserving the fidelity of benign outputs, reshaping the defense landscape for text-to-image models.
LLM safety crumbles in low-resource languages because alignment is skin-deep; LASA fixes this by injecting safety at the semantic core, slashing attack success by 88%.
Multimodal models can "see" the image but still fail at reasoning because the visual input distracts the routing mechanism from activating the right experts.
LLMs can move beyond simple refusals to actively guide vulnerable users towards safe outcomes, achieving state-of-the-art safety and robustness against jailbreaks.
