Search papers, labs, and topics across Lattice.
4
0
9
MT-EditFlow bridges the gap between local planning and global success in multi-turn image editing, achieving a significant performance boost over leading models.
LLM agents can remember more, and do it cheaper: MemMachine's ground-truth-preserving architecture and adaptive retrieval strategies boost accuracy while slashing input token usage by 80%.
SAM's impressive zero-shot segmentation abilities don't directly translate to medical imaging, but this new fine-tuning approach unlocks its potential for accurate nuclei instance segmentation with minimal added parameters.
VecFormer slashes the computational cost of graph transformers while boosting out-of-distribution generalization by operating attention on quantized "graph tokens" instead of individual nodes.
