Search papers, labs, and topics across Lattice.
Renming University of China
5
0
11
A two-loop configuration in LoopCoder-v2 boosts code generation performance by over 50% compared to a non-looped baseline, while more loops actually hinder results.
FORT-Searcher achieves superior performance by synthesizing training tasks that actively resist shortcut exploitation, transforming how we train deep search agents.
Attention-guided denoising can dramatically enhance reasoning performance in diffusion language models, outperforming traditional post-training methods.
Fine-tuning on DeNovoSWE catapults LLM performance in generating entire software repositories, achieving nearly an 8x improvement on a challenging benchmark.
Building agents that can reliably automate complex, multi-step workflows over local files and tools just got a whole lot easier.
