Search papers, labs, and topics across Lattice.
3
0
5
A single visual tokenizer in UniAR bridges the gap between understanding and generation, achieving state-of-the-art performance in image generation and editing.
Stop passively waiting for retrieval cues – ProactAgent proactively asks for information from its memory and skills, leading to significant gains in lifelong learning performance.
DINO, not CLIP, might be the better foundation for open-set 3D object retrieval, especially when paired with dynamic view integration and virtual feature synthesis to avoid overfitting.
