Search papers, labs, and topics across Lattice.
2
0
6
Stop reimplementing multimodal models: TorchUMM offers a unified codebase for evaluation, analysis, and post-training, streamlining research across diverse architectures and tasks.
Long-term memory doesn't just expand LLMs' knowledge, it also dramatically expands their attack surface: a new black-box attack, ER-MIA, achieves high success rates injecting adversarial memories into LLMs via similarity-based retrieval.
