Search papers, labs, and topics across Lattice.
4
44
6
3
MMRAG gets a human-like reasoning upgrade: CogniVerse uses cognitive reflection and information geometry to filter noise, align modalities, and generate coherent responses, outperforming existing systems.
LLM defenses don't have to sacrifice performance: APD disentangles adversarial prompts to slash harmful outputs by 85% while maintaining model utility.
VLMs can be significantly improved by reasoning over diverse, generated text inputs, rather than relying on restrictive, predefined templates.
VLMs can now handle real-world sensor failures and data privacy constraints without catastrophic performance drops, thanks to a new plug-and-play module for incomplete multi-modal inputs.
