Search papers, labs, and topics across Lattice.
Technical University of Munich
2
0
4
Video LLMs can ace individual traffic video questions but still fail spectacularly at subtle counterfactual reasoning, revealing a critical blind spot for safety-critical applications.
A single model can now achieve state-of-the-art semantic segmentation across diverse sensor modalities like thermal, depth, and polarization, eliminating the need for modality-specific architectures.
