Search papers, labs, and topics across Lattice.
3
0
6
19
This work shows that Kimi Delta Attention (KDA) can realize 2D rotations by combining a single delta-rule transformation with a second reflection supplied by its channel-wise gate, and characterize the expressivity of CKDA and prove that every orthogonal diagonal-plus-rank-one matrix is exactly a CKDA transition matrix.
Models trained on LAION-BVD achieve state-of-the-art performance in multimodal tasks, showcasing the dataset's potential to redefine video understanding.
Data mixing, especially with instruction-heavy data, emerges as the crucial factor for optimizing VLM training, challenging traditional filtering approaches.
