Search papers, labs, and topics across Lattice.
5
0
9
Native computer use can be achieved at scale, enabling agents to outperform leading systems while significantly enhancing security against adversarial attacks.
FastTPS accelerates LLM inference by 6x while preserving memory efficiency, revolutionizing how we handle long-sequence inputs on AI accelerators.
HarmVideoBench reveals that existing benchmarks miss critical layers of harmful video understanding, while a new method boosts model accuracy by over 20%.
State-of-the-art image-to-video models are alarmingly vulnerable to visual prompt attacks, achieving up to 100% success in triggering harmful outputs.
A 1000x larger video reasoning dataset reveals early signs of emergent generalization, offering a new foundation for training and evaluating spatiotemporal AI.
