Search papers, labs, and topics across Lattice.
Tongji University
4
0
5
GARI enables a flexible, learnable interface that maintains transformation consistency across diverse data types, challenging the rigidity of traditional equivariant architectures.
ClawRec achieves a remarkable 11.3% increase in recommendation quality over traditional systems by leveraging cross-platform user behavior for more relevant suggestions.
MiniMax-M2 proves that massive parameter counts don't always translate to better agentic performance; strategic activation of a smaller subset can unlock frontier-level intelligence.
Recommender systems can move beyond passive item lists: RecPilot's multi-agent framework autonomously explores item spaces and generates user-centric reports, significantly reducing user effort in item evaluation.
