Search papers, labs, and topics across Lattice.
Affiliation:
4
0
7
3
This work proposes a practical framework for verifiable DP training using CPU-side TEEs together with untrusted GPUs, and addresses a fundamental efficiency-security tension: training entirely inside a CPU TEE is too slow, while unrestricted GPU offloading can allow malicious deviations from DP.
EvoGS achieves superior dynamic view synthesis by modeling Gaussian deformations as a temporal evolution process, overcoming the limitations of traditional independent estimation methods.
Pointwise convolutions, which dominate parameter volume in large-kernel CNNs, can be drastically reduced through a novel group-sharing strategy, enabling efficient deployment on edge devices.
Humans are surprisingly vulnerable to deception by compromised LLM agents, with less than 10% detecting attacks even in high-stakes scenarios.
