Search papers, labs, and topics across Lattice.
5
0
8
7
GALLM redefines sequential recommendation by seamlessly integrating collaborative signals into LLMs, achieving significant performance gains without extra complexity.
Unfaithful reasoning chains can significantly undermine the accuracy of MLLMs, but a training-free framework can effectively correct these errors and boost performance by over 8%.
SmartGR achieves an 8.6% boost in recommendation performance while slashing inference time by over 2.3 times, tackling unique challenges in generative recommendation systems.
Relying on just the final layer of LLMs can lead to a 6.72% drop in recommendation performance鈥擨MFuse captures the full spectrum of semantic knowledge across layers for superior results.
SpecFormer transforms recommendation systems by mitigating embedding and attention collapse, leading to superior performance and scalability.
