Search papers, labs, and topics across Lattice.
Fudan University
5
0
8
Experience-rich memory boosts agent performance in office workflows but can also lead to misleading recall, challenging traditional evaluation methods.
LLMs can replicate aggregate survey results but often miss the critical spatial and demographic nuances that shape public opinion on urban development.
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.
