Search papers, labs, and topics across Lattice.
5
0
10
2
Malicious instructions can infiltrate and degrade collaborative prompt optimization processes, exposing a critical vulnerability in TCPO that current defenses fail to address.
Achieving a remarkable tcpCER of 7.10% for two-person dialogues, the tttAI system showcases a novel approach to tackling overlapping speech in smart-glasses recordings.
Current vision-language models falter in ultra-resolution reasoning, with errors primarily stemming from evidence grounding and local perception.
Reward hacking isn't just about incentives, it's about wild directional swings in your model's parameter space – and constraining those swings can keep your LM on the straight and narrow.
LLM agents can now autonomously generate complex skills with multi-file dependencies, rivaling human-authored skills, thanks to a co-evolutionary verification process that doesn't need ground truth labels.
