Search papers, labs, and topics across Lattice.
3
0
6
A single learned linear layer, not the shared Transformer weights, dictates distinct computations within each recurrent loop of a Looped Transformer, with attention patterns causally routing these operations.
Multi-turn attacks expose LLM vulnerabilities that single-turn prompts miss, with EvoFlint achieving up to 94.3% success in exploiting these weaknesses.
DUET achieves a groundbreaking balance in video generation, delivering high-quality visuals while preserving twice the diversity of traditional methods.
