Search papers, labs, and topics across Lattice.
North South University
4
0
6
Hallucinations in LVLMs can be effectively mitigated without training by leveraging per-instance subspaces that adaptively suppress specific hallucination modes.
A novel transformer framework achieves superior assessment of rehabilitation exercises by effectively extracting and utilizing joint position features from RGBD data.
Systematic biases in transformer-based time-series forecasting can be effectively mitigated by decoupling prediction and residual learning into a two-stage framework.
HyperVis reveals that leveraging hyperbolic geometry can significantly enhance compositional reasoning in VLMs, outperforming traditional discrete approaches.
