Search papers, labs, and topics across Lattice.
6
0
7
Standard visual token pruning targets the wrong encoder depth: tapping into intermediate representations while asymmetrically skipping decoder sub-layers cuts MLLM inference FLOPs by 79% without requiring any retraining.
Agent memory can be compressed by 50% with virtually zero performance degradation (retaining up to 99.7% accuracy) and a 2x retrieval speedup by structuring historical context into event-centric maximum spanning trees.
Achieving 5-7x speedup in diffusion models without sacrificing quality, LinCa redefines the efficiency of feature caching through adaptive prediction strategies.
AViTS reduces redundant computation in dynamic-resolution generation by up to 14.76x while preserving fine-detail consistency in outputs.
Wuying-Browser-Agent achieves a groundbreaking 80.6% on WebVoyager, revealing that real-world browser agents can excel beyond short, clean demonstrations.
Output extrapolation in STEP-OPD enables a unified student model to surpass the performance of its specialized teachers across all evaluated tasks.
