Search papers, labs, and topics across Lattice.
5
20
8
12
Seemingly innocuous prompts can covertly hijack robotic actions, steering them toward adversarial outcomes while maintaining the facade of intended commands.
LLMs can guide phoneme editing to create synthetic accented speech from just a handful of examples, substantially improving ASR accuracy where training data is scarce.
LLMs can spark scientific creativity by systematically bridging insights across disciplines, leading to more novel and insightful research directions.
Forget prompt engineering and fine-tuning: this "Reasoning Inception" method injects targeted reasoning into LLM agents at test time to fix conversational errors on the fly.
Forget specialized models: CoALM proves a single LLM can now master both multi-turn conversations *and* complex tool use, even outperforming GPT-4o.
