Search papers, labs, and topics across Lattice.
6
0
9
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.
ITP-STDP slashes energy consumption and hardware footprint in spiking neural networks, achieving up to 219.8x efficiency gains.
Achieve SOTA zero-shot anomaly detection by dynamically routing image patches based on structural entropy, adapting to heterogeneous anomaly patterns without target-domain fine-tuning.
Stop MLLM hallucinations in VideoQA: ClueNet's two-stage training and adaptive clue filtering boosts accuracy by 1.1% while improving interpretability and efficiency.
AgentOS reimagines LLMs as reasoning kernels within a structured OS, offering a blueprint for more robust and scalable AI agents.