4 papers
LC-GRPO: Bridging Train-Inference Gap for Flow-Based GRPO with Langevin Correction
Yingqing Guo, Hui Yuan, Zijian He +2
Flow-based generative models are typically sampled by solving a deterministic ordinary differential equation (ODE), whereas online reinforcement learning requires stochastic rollou…
A First-order Generative Bilevel Optimization Framework for Diffusion Models
Quan Xiao, Hui Yuan, A F M Saif +4
Diffusion models, which iteratively denoise data samples to synthesize high-quality outputs, have achieved empirical success across domains. However, optimizing these models for do…
Training-Free Guidance Beyond Differentiability: Scalable Path Steering with Tree Search in Diffusion and Flow Models
Yingqing Guo, Yukang Yang, Hui Yuan +1
Training-free guidance enables controlled generation in diffusion and flow models, but most methods rely on gradients and assume differentiable objectives. This work focuses on tra…
MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations
Kaixuan Huang, Jiacheng Guo, Zihao Li +15
Large language models have demonstrated impressive performance on challenging mathematical reasoning tasks, which has triggered the discussion of whether the performance is achieve…