Search papers, labs, and topics across Lattice.
5
2
8
8
A compact 4B model using DuoMem achieves a staggering 77.9% task success rate, rivaling a 72B teacher model while being over 3x faster in execution.
SpanDec achieves state-of-the-art NER accuracy with significantly improved throughput, proving that you don't need to exhaustively process every possible span to achieve top performance.
Differentially private federated learning gets a boost: PINA achieves 2.9% higher accuracy than state-of-the-art methods by using a novel two-stage approach with privacy-preserving initialization and normality-driven aggregation.
Minimizing variance of importance weights in diffusion models elegantly unifies existing alignment methods and opens doors to novel, non-KL optimization strategies.
On-device LLMs can now tackle complex tasks like generating translated summaries thanks to a new benchmark and calibration method tailored for compositional multi-tasking.
