activity
20242026
collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

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…

cs.LG2026

Plain Transformers Can be Powerful Graph Learners

Liheng Ma, Soumyasundar Pal, Yingxue Zhang +2

Transformers have attained outstanding performance across various modalities, owing to their simple but powerful scaled-dot-product (SDP) attention mechanisms. Researchers have att…

cs.LG2025

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-…

cs.LG2024

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…

cs.LG2024

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…