Search papers, labs, and topics across Lattice.
Beijing Foreign Studies University, Academy of Artificial Intelligence
2
0
4
Identical ethical dilemmas trigger contradictory value judgments across languages in frontier LLMs, but inference-time steering vectors extracted from hidden-state discrepancies can reliably enforce culture-specific alignment without fine-tuning.
Dedicated memory architectures for VLAs are largely obsolete: feeding intact video history directly into modern backbones beats complex retrieval and compression mechanisms by a wide margin while prefix caching keeps latency at single-frame speeds.
