6 citations · 6 across the 12 of their papers we have counts for
5 papers · 1 filter
Diffusion Transformers are Provably Optimal In-context Generators
Guoji Fu, Tomoya Wakayama, Ryotaro Kawata +3
Generative foundation models are attracting interest for their ability to produce desired outputs from demonstrations given at inference time, without updating parameters. However,…
Best Practice Critic Optimization
Penghui Qi, Xiangxin Zhou, Wee Sun Lee
Group-based reinforcement learning methods such as GRPO for large language models avoid training a critic by sampling multiple responses for each prompt. A reliable critic could in…
On the effectiveness of reward functions in reinforcement learning for confidence calibration of large language models
Chee Heng Tan, Zhuoyi Lin, Mehul Motani +1
In this paper, we consider the setting where large language models (LLMs) are trained using reinforcement learning (RL) to simultaneously improve reasoning accuracy and verbalize t…
Intrinsic Wasserstein Rates for Score-Based Generative Models on Smooth Manifolds
Guoji Fu, Taiji Suzuki, Wee Sun Lee +1
Score-based generative models are trained in high-dimensional ambient spaces, yet many data distributions are supported on low-dimensional nonlinear structures. We prove that, for…
Rethinking the Trust Region in LLM Reinforcement Learning
Penghui Qi, Xiangxin Zhou, Zichen Liu +4
Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) serving as the de facto standard algorith…