Search papers, labs, and topics across Lattice.
5
2
12
12
Captions selected with VEGAS align significantly better with human attention, boosting retrieval performance and challenging the status quo of video captioning metrics.
PhysRAG not only elevates visual fidelity in video generation but also ensures compliance with physical laws, setting a new benchmark for realism in AI-generated content.
Achieve more precise and generalizable robot grasping by injecting grasp pose priors into latent diffusion policies, outperforming existing imitation learning methods.
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.
Forget closed-source: Instella's new family of fully open 3B parameter language models rivals leading open-weight models, proving transparency doesn't have to sacrifice performance.
