Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training
Zhenyu Han, Ansheng You, Haibo Wang +16
Reinforcement learning (RL) has become a pivotal technology in the post-training phase of large language models (LLMs). Traditional task-colocated RL frameworks suffer from signifi…
cs.LG2025
Chip Placement with Diffusion Models
Vint Lee, Minh Nguyen, Leena Elzeiny +3
Macro placement is a vital step in digital circuit design that defines the physical location of large collections of components, known as macros, on a 2D chip. Because key performa…