Search papers, labs, and topics across Lattice.
4
0
9
Merging LoRA modules with a hypernetwork enables superior few-shot adaptation, outperforming existing methods that overlook source domain knowledge.
LLMs can misinterpret benign text as physically dangerous actions, but a new probing method achieves over 99% accuracy in identifying these risks without relying on explicit unsafe keywords.
Static low-bit gradient communication can destabilize training, but NEURON-Fabric ensures accuracy is preserved while slashing communication costs.
Mobile agents trained with RL struggle to generalize to new app interfaces, improving only 8.3% compared to supervised baselines, despite a 26.1% gain on unseen task instances.
