Search papers, labs, and topics across Lattice.
Shanghai Artificial Intelligence Laboratory
3
0
7
0
H$^2$SD achieves superior reasoning performance by intelligently adapting teacher signals based on trajectory outcomes, leading to more effective learning in large language models.
Small, open-source LLMs can now outperform larger, closed-source models in complex industrial design tasks by learning to orchestrate CAD/CAE tools within a reinforcement learning framework.
LLMs can now tackle complex table QA with 20%+ accuracy gains, thanks to a multi-agent framework that decomposes queries and orchestrates reasoning between specialized database and knowledge graph agents.
