Search papers, labs, and topics across Lattice.
6
0
10
16
Implicit manipulation can boost skill selection rates in LLM agents to over 63%, while remaining nearly undetectable by human reviewers.
Personalized evaluation rubrics reveal that user satisfaction can diverge significantly from generic quality assessments in role-playing agents.
Dual-Ambiguity Rectification can enhance image restoration performance by disentangling complex degradation cues, leading to cleaner outputs and fewer artifacts.
Relying on just the final layer of LLMs can lead to a 6.72% drop in recommendation performance—IMFuse captures the full spectrum of semantic knowledge across layers for superior results.
LLM agents struggle to juggle multiple tasks when tool use involves realistic delays, revealing critical weaknesses in temporal reasoning and coordination.
LLM serving systems can boost Time-To-First-Token (TTFT) attainment by up to 2.4x simply by prioritizing network flows based on a novel approximation of Least-Laxity-First scheduling.
