Search papers, labs, and topics across Lattice.
8
0
12
0
Models fine-tuned with LongCrafter data achieve unprecedented performance on long-context tasks, particularly in high-difficulty scenarios.
Misclassifications in biomedical imaging can be drastically reduced with BioMedVR's confusion-aware approach, leading to superior model performance in critical healthcare applications.
Even state-of-the-art LLMs like GPT-5.2 falter in LakeQA, scoring just 18.37% on a benchmark that demands both searching and multi-hop reasoning.
AURA reveals that understanding implicit user intent can dramatically reduce the number of queries needed while enhancing the relevance of responses.
VLMs can achieve state-of-the-art adversarial robustness by iteratively refining visual and textual representations through a closed-loop prompting mechanism, even with frozen encoders.
Get clinically-accurate 3D dental models from a single panoramic X-ray, slashing radiation exposure and cost.
Forget hand-crafted KG traversal policies: GraphWalker uses automatically synthesized trajectories to train agents that achieve SOTA performance and generalize to unseen reasoning paths.
Even the best vision-language models struggle to diagnose brain tumors from MRI scans, but a new dataset and benchmark reveals a path to significant accuracy gains through instruction tuning.
