LLMs augmented hierarchical reinforcement learning with action primitives for long-horizon manipulation tasks
Yun, W. J., Mohaisen, D., Jung, S., Kim, J.-K. & Kim, J. Hierarchical reinforcement learning using gaussian random trajectory generation...
LLMs
DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning
GRPOGRPO9 is the RL algorithm that we use to train DeepSeek-R1-Zero and DeepSeek-R1. It was originally proposed to simplify the...
GEPA optimizes LLMs without costly reinforcement learning
Want smarter insights in your inbox? Sign up for our weekly newsletters to get only what matters to enterprise AI,...
CollabLLM: Teaching LLMs to collaborate with users
Large language models (LLMs) can solve complex puzzles in seconds, yet they sometimes struggle over simple conversations. When these AI...
Introducing KBLaM: Bringing plug-and-play external knowledge to LLMs
Large language models (LLMs) have demonstrated remarkable capabilities in reasoning, language understanding, and even creative tasks. Yet, a key challenge...
Specialized LLMs can outperform traditional methods in forecasting postoperative risks
Millions of Americans undergo surgery each year. After surgery, preventing complications like pneumonia, blood clots and infections can be the...
