Search papers, labs, and topics across Lattice.
6
0
7
0
GraFT outperforms fine-tuned models by providing a training-free solution that boosts spatial reasoning in MLLMs by leveraging 3D scene graphs.
Achieving nearly 5x faster training for M-TGNNs without sacrificing accuracy could revolutionize how we handle temporal data in graph neural networks.
By framing camera trajectory generation as a language-grounded spatial reasoning problem, CinemaTraj achieves high-quality, collision-free cinematographic outputs that align closely with user prompts.
NeutronSparse reveals that with the right coordination strategies, NPUs can outperform leading GPU libraries in sparse matrix operations.
Achieving a 2.31x speedup in GNN training on heterogeneous CPU-NPU platforms could redefine efficiency benchmarks in graph learning.
Forget end-to-end video understanding: RieMind shows that explicitly grounding LLMs in 3D scene graphs unlocks a 16% jump in spatial reasoning, suggesting structured representations are the key.
