Search papers, labs, and topics across Lattice.
8
0
7
6
SkillCAT boosts LLM agent performance by over 40% through a novel approach that intelligently evolves skills without retraining the model.
Echo-DM achieves superior ultrasound marker removal while maintaining anatomical integrity, challenging the effectiveness of existing marker removal techniques.
UniSHARP achieves unprecedented photorealistic view synthesis across a continuum of camera systems, outperforming traditional methods by a substantial margin.
Multi-hop question answering gets a serious boost: ConRAG's consensus-driven, multi-view retrieval approach leapfrogs existing RAG methods by a significant margin.
Unsupervised visual tracking gets a surprising boost from text-to-image diffusion models, which can be prompted to highlight the target object in each frame without any training data.
Video-LLMs are leaving performance on the table: explicitly anchoring to keyframes before answering questions unlocks significant gains in Video TextVQA.
LLMs struggle to retrieve the right tools when instructions are vague, but a simple "bridge model" that rephrases instructions can more than double retrieval accuracy.
LLMs can now navigate massive toolsets with a "Try-Check-Retry" loop, boosting tool-calling accuracy by up to 25% and letting smaller models punch above their weight.
