Search papers, labs, and topics across Lattice.
3
0
5
Up to 47% of reported fine-tuning gains in tool retrieval are an evaluation illusion caused by benchmarks treating functionally equivalent tools as retrieval failures.
CoreMem achieves a remarkable +4.51 percentage point improvement in open-domain reasoning accuracy while operating within a strict 8 GB VRAM budget.
SemantiCache achieves up to 2.61x faster decoding and reduces memory footprint without sacrificing model performance by compressing KV caches along semantic boundaries.
