Search

Few direct matches — filled in with the latest updates.

Tag: #3d-multimodal1 results

C^2ROPE Advances 3D Multimodal Reasoning

C^2ROPE Advances 3D Multimodal Reasoning

C^2ROPE enhances Rotary Position Embedding for 3D Large Multimodal Models by addressing spatial locality loss and long-term attention decay. It introduces spatio-temporal continuous positional embeddings using triplet hybrid indices and Chebyshev Causal Masking. Evaluations show superior performance on 3D scene reasoning and VQA benchmarks.

ArXiv AIResearchFeb 12#research#c2rope#v1