Track new results across pure and applied mathematics.
Search papers, labs, and topics across Lattice.
3
0
3
Diffusion model token merging can be optimized by analyzing denoising dynamics, not just prompt relevance, to preserve structural coherence and visual fidelity.
Visually grounded linguistic guidance transforms dense video captioning by dynamically adapting to semantic changes, leading to superior event localization.
LLM-augmented training with similarity-aware masking lets weakly-supervised video captioning models generate more accurate event descriptions and temporal boundaries, even with sparse training data.