Search papers, labs, and topics across Lattice.
5
0
7
2
ED-DiT achieves a remarkable reduction in prediction error, showcasing the power of physics-guided pretraining in molecular representation learning.
AcceptMoE slashes host-to-device traffic by over 73% while boosting throughput by more than double, all without a major accuracy trade-off.
LEEPS achieves a remarkable 3.7% performance boost in reasoning tasks by intelligently balancing prompt exploitation and exploration, redefining efficiency in RLVR for large language models.
Coset ensemble decoding achieves a breakthrough in quantum error correction by dramatically improving accuracy and reducing latency, all while slashing resource consumption on FPGA implementations.
Incomplete schedule search can lead to permanently suboptimal silicon, irrecoverable by software tuning, highlighting the critical need for co-design in 3D-stacked AI accelerators.
