Search papers, labs, and topics across Lattice.
6
0
8
0
The LPCVC 2025 winning solutions showcase surprisingly effective strategies for balancing accuracy and efficiency in edge-based computer vision, pushing the boundaries of what's possible on resource-constrained devices.
Unified benchmarks reveal the state-of-the-art in simultaneously addressing multiple real-world image degradations like blur, low-light, and rain.
By explicitly verifying the visual existence of spoken references before segmentation, APRVOS substantially improves robustness in noisy audio-conditioned Ref-VOS, outperforming standard pipelines.
Nemotron 3 Super proves you can achieve comparable accuracy to existing 120B models, but with significantly higher inference throughput, by combining Mamba, Attention, and Mixture-of-Experts.
VLMs can be easily fooled in the real world by strategically manipulating lighting, causing them to misinterpret scenes and hallucinate nonsensical captions.
A new dataset, SeIQA, offers a benchmark to evaluate how humans perceive semantic loss in degraded images, pushing beyond traditional quality metrics.
