Search papers, labs, and topics across Lattice.
Group
2
0
3
LLM embedding models waste over 40% of their inference compute processing prefix tokens that become completely redundant at deeper layers, enabling aggressive, training-free token pruning with virtually zero retrieval degradation.
LLMs can be adapted for scenario-specific user representation by conditioning on queries, achieving state-of-the-art performance on Alipay benchmarks and demonstrating practical effectiveness in online A/B testing.
