4 papers · 1 filter
It Takes Two: Your GRPO Is Secretly DPO
Yihong Wu, Liheng Ma, Lei Ding +9
GRPO has emerged as a prominent reinforcement learning algorithm for post-training LLMs. Unlike critic-based methods, GRPO computes advantages by estimating the \emph{value baselin…
Omni-Thinker: Scaling Multi-Task RL in LLMs with Hybrid Reward and Task Scheduling
Derek Li, Jiaming Zhou, Leo Maxime Brunswic +8
The pursuit of general-purpose artificial intelligence depends on large language models (LLMs) that can handle both structured reasoning and open-ended generation. We present Omni-…
HardCore Generation: Generating Hard UNSAT Problems for Data Augmentation
Joseph Cotnareanu, Zhanguang Zhang, Hui-Ling Zhen +2
Efficiently determining the satisfiability of a boolean equation -- known as the SAT problem for brevity -- is crucial in various industrial problems. Recently, the advent of deep…
GraSS: Combining Graph Neural Networks with Expert Knowledge for SAT Solver Selection
Zhanguang Zhang, Didier Chetelat, Joseph Cotnareanu +7
Boolean satisfiability (SAT) problems are routinely solved by SAT solvers in real-life applications, yet solving time can vary drastically between solvers for the same instance. Th…