Search papers, labs, and topics across Lattice.
4
0
6
Adaptive modulation in RIS-assisted federated learning can drastically improve convergence speed and accuracy, even in challenging wireless environments.
Existing KB-VQA benchmarks mislead model evaluation, with flawed assumptions leading to overestimated reasoning capabilities in Visual Language Models.
CausalMem achieves over 20x visual token compression while maintaining high accuracy in streaming video understanding, redefining memory efficiency in MLLMs.
MLLMs can significantly improve KB-VQA performance by first identifying entities from a limited candidate set before selecting evidence, leading to a more efficient and effective workflow.
