Search papers, labs, and topics across Lattice.
4
1
6
9
Over half of current video understanding benchmarks can be solved without any visual context, exposing a critical flaw in model evaluation.
Reconstructing humans and their environments from multi-view video can now be done in a single pass, and 8x faster, without needing extra modules or preprocessing.
Ditch noisy feature distances: SeaCache uses a spectral filter to cache and reuse intermediate diffusion model outputs, slashing latency while maintaining image quality.
Object-driven shortcuts can severely undermine action recognition, but RCORE effectively mitigates this issue, enhancing model generalization to unseen verb-object combinations.
