Search papers, labs, and topics across Lattice.
Affiliation:
5
1
10
4
Aegis, trained with CyberFactory, outperforms existing models by 22.8 points in cybersecurity tasks, showcasing the power of agentic learning from real-world vulnerabilities.
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.
Code LLMs can achieve SOTA performance in agentic tasks by explicitly modeling the dynamic evolution of software logic across different training stages.
A new 32B code LLM trained specifically for industrial tasks crushes existing models on specialized domains like chip design and GPU kernel optimization, while remaining competitive on general coding benchmarks.
A 32B model trained entirely on synthetic data from InfTool outperforms models 10x larger on tool use, rivaling even Claude-Opus.
