Search papers, labs, and topics across Lattice.
6
0
9
10
Video LLMs can significantly improve their QA performance by integrating spatio-temporal evidence, bridging the gap between accuracy and visual perception.
DACL achieves unprecedented accuracy in fetal ultrasound segmentation with minimal labeled data by leveraging dual-agreement consistency learning.
Achieve 50% parameter reduction in LLaMA-2-7B with minimal performance loss and no fine-tuning, thanks to a new global gating-based structured pruning method.
Doc-V* demonstrates that an agentic approach to multi-page document VQA, using active navigation and structured memory, can significantly outperform retrieval-augmented generation, especially in out-of-domain scenarios.
Get clinically-accurate 3D dental models from a single panoramic X-ray, slashing radiation exposure and cost.
Even state-of-the-art multimodal LLMs struggle to accurately cite their sources when reasoning across video, audio, and text, often hallucinating citations despite generating correct answers.
