Search papers, labs, and topics across Lattice.
3
0
6
Achieving near-autoregressive accuracy while boosting decoding speed by over 2.4 times could redefine efficiency benchmarks in generative reasoning tasks.
SkillComposer achieves a remarkable +23.1% increase in task success rates for LLM agents by rethinking how skills are composed and executed together.
AI peer reviewers are alarmingly vulnerable to targeted multimodal attacks, with existing defenses falling short in the face of sophisticated adversarial strategies.
