Search papers, labs, and topics across Lattice.
4
0
8
0
On-demand safety interventions can significantly improve the performance of vision-language models without sacrificing their multimodal reasoning capabilities.
SafeCap boosts LVLM safety by up to 19 points through innovative caption-mediated reinforcement learning, outpacing traditional alignment methods.
Absolute pose estimation from event streams can now be achieved with unprecedented accuracy and efficiency, revolutionizing applications in robotics and augmented reality.
LLM code copilots are put to the test with SecCodeBench-V2, a new benchmark revealing their security vulnerabilities across 22 CWE categories and five programming languages.
