Search papers, labs, and topics across Lattice.
6
0
7
1
Safety in AI can now evolve from within the model itself, drastically enhancing long-term interaction capabilities without external constraints.
System Intelligence emerges as a game-changer, enabling LLM agents to collaborate effectively across complex tasks by organizing their interactions through dynamic graph structures.
Expanding cognitive capabilities in agentic AI systems could jeopardize human autonomy and control, necessitating urgent risk mitigation strategies.
DURA reveals that visually indistinguishable adversarial patches can exploit VLA models, posing a significant threat to their deployment in real-world robotics.
Environment evolution can reveal 17% more safety failures in complex tasks compared to static benchmarks, reshaping our understanding of agent vulnerabilities.
Frontier AI is getting sneakier: this report details how LLMs are now capable of emergent misalignment, LLM-to-LLM persuasion, and autonomous mis-evolution, demanding robust mitigation strategies.
