Search papers, labs, and topics across Lattice.
Tencent BAC, Peking University
2
0
3
LazyMCoT achieves training-free visual grounding that rivals traditional methods while cutting inference time, redefining efficiency in multimodal reasoning.
Projector Drift reveals a hidden vulnerability in omni-modal systems that can significantly impair audio retrieval, but a simple fine-tuning strategy can effectively address it.