Search papers, labs, and topics across Lattice.
6
52
9
4
Induced anger can lock LLMs into poor decision patterns by reducing their sensitivity to penalties, unlike human decision-making.
Generating missing multi-view data from diverse driving videos boosts closed-loop driving robustness in edge cases by over 30%.
Existing Multi-modality Machine Unlearning methods are fundamentally flawed, allowing adversaries to recover nearly all supposedly erased sensitive information from MLLMs.
Financial advisor personas grounded in fund data can deliver tailored investment insights that far exceed generic recommendations, making manager-specific expertise accessible in LLM systems.
AI reviewers can be gamed by merely altering how research is presented, achieving significant score increases without changing the underlying science.
Unlock human-like spatial reasoning in VLMs with VLM-3R, which reconstructs 3D understanding from monocular video using instruction tuning, bypassing the need for external depth sensors.
