English
Related papers

Related papers: Boosting Maximum Entropy Reinforcement Learning vi…

200 papers

Continuous diffusion and flow matching models could represent a powerful alternative to autoregressive approaches for language modelling (LM), as they unlock a host of advantages currently reserved for continuous modalities, including…

Machine Learning · Computer Science 2026-05-12 Oscar Davis , Anastasiia Filippova , Pierre Ablin , Victor Turrisi , Amitis Shidani , Marco Cuturi , Louis Béthune

We propose \emph{Euler Mean Flows (EMF)}, a flow-based generative framework for one-step and few-step generation that enforces long-range trajectory consistency with minimal sampling cost. The key idea of EMF is to replace the trajectory…

Machine Learning · Computer Science 2026-02-04 Zhiqi Li , Yuchen Sun , Duowen Chen , Jinjin He , Bo Zhu

Recently, Flow Matching models have pushed the boundaries of high-fidelity data generation across a wide range of domains. It typically employs a single large network to learn the entire generative trajectory from noise to data. Despite…

Computer Vision and Pattern Recognition · Computer Science 2025-10-27 Dogyun Park , Taehoon Lee , Minseok Joo , Hyunwoo J. Kim

Few-step generation has been a long-standing goal, with recent one-step generation methods exemplified by MeanFlow achieving remarkable results. Existing research on MeanFlow primarily focuses on class-to-image generation. However, an…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Chenxi Zhao , Chen Zhu , Xiaokun Feng , Aiming Hao , Jiashu Zhu , Jiachen Lei , Jiahong Wu , Xiangxiang Chu , Jufeng Yang

Energy-based models (EBMs) are versatile density estimation models that directly parameterize an unnormalized log density. Although very flexible, EBMs lack a specified normalization constant of the model, making the likelihood of the model…

Machine Learning · Computer Science 2024-02-20 Louis Grenioux , Éric Moulines , Marylou Gabrié

Existing methods to enhance the reasoning capability of large language models predominantly rely on supervised fine-tuning (SFT) followed by reinforcement learning (RL) on reasoning-specific data. These approaches critically depend on…

Machine Learning · Computer Science 2025-05-20 Qingyang Zhang , Haitao Wu , Changqing Zhang , Peilin Zhao , Yatao Bian

Modern vision generators transport a base distribution to data through time-indexed measures, implemented as deterministic flows (ODEs) or stochastic diffusions (SDEs). Despite strong empirical performance, standard flow-matching objectives…

Machine Learning · Computer Science 2026-02-27 Chika Maduabuchi

Many potential applications of reinforcement learning (RL) require guarantees that the agent will perform well in the face of disturbances to the dynamics or reward function. In this paper, we prove theoretically that maximum entropy…

Machine Learning · Computer Science 2022-05-06 Benjamin Eysenbach , Sergey Levine

Entropy augmented to reward is known to soften the greedy argmax policy to softmax policy. Entropy augmentation is reformulated and leads to a motivation to introduce an additional entropy term to the objective function in the form of…

Machine Learning · Computer Science 2020-06-08 Donghoon Lee

Achieving both accuracy and diverse reasoning remains challenging for Large Language Models (LLMs) in complex domains like mathematics. A key bottleneck is evaluating intermediate reasoning steps to guide generation without costly human…

Machine Learning · Computer Science 2025-10-14 Adam Younsi , Ahmed Attia , Abdalgader Abubaker , Mohamed El Amine Seddik , Hakim Hacid , Salem Lahlou

Diffusion Large Language Models (dLLMs) are rapidly emerging alongside autoregressive models as a powerful paradigm for complex reasoning, with reinforcement learning increasingly used for downstream alignment. Existing trajectory-based RL…

Machine Learning · Computer Science 2025-11-20 Ranfei Chen , Ming Chen , Kaifei Wang

Language models based on discrete diffusion have attracted widespread interest for their potential to provide faster generation than autoregressive models. Despite their promise, these models typically produce samples whose quality sharply…

Computation and Language · Computer Science 2026-05-21 Chanhyuk Lee , Jaehoon Yoo , Manan Agarwal , Sheel Shah , Jerry Huang , Aditi Raghunathan , Seunghoon Hong , Nicholas M. Boffi , Jinwoo Kim

Generative models such as diffusion and flow matching have become dominant paradigms for visuomotor policy learning, yet their reliance on iterative denoising incurs high inference latency incompatible with real-time robotic control. We…

Robotics · Computer Science 2026-05-18 Jiaqi Bai , Jindou Jia , Yuxuan Hu , Gen Li , Xiangyu Chen , Tuo An , Kuangji Zuo , Jianfei Yang

Diffusion policies have achieved superior performance in imitation learning and offline reinforcement learning (RL) due to their rich expressiveness. However, the conventional diffusion training procedure requires samples from target…

Machine Learning · Computer Science 2025-07-01 Haitong Ma , Tianyi Chen , Kai Wang , Na Li , Bo Dai

Social goods, such as healthcare, smart city, and information networks, often produce ordered event data in continuous time. The generative processes of these event data can be very complex, requiring flexible models to capture their…

Machine Learning · Computer Science 2020-12-29 Shuang Li , Shuai Xiao , Shixiang Zhu , Nan Du , Yao Xie , Le Song

Allocating extra computation at inference time has recently improved sample quality in large language models and diffusion-based image generation. In parallel, Flow Matching (FM) has gained traction in language, vision, and scientific…

Machine Learning · Computer Science 2025-10-21 Adam Stecklov , Noah El Rimawi-Fine , Mathieu Blanchette

Reinforcement learning (RL) is a classical tool to solve network control or policy optimization problems in unknown environments. The original Q-learning suffers from performance and complexity challenges across very large networks. Herein,…

Machine Learning · Computer Science 2024-09-02 Talha Bozkus , Urbashi Mitra

Offline safe reinforcement learning (RL) seeks reward-maximizing policies from static datasets under strict safety constraints. Existing methods often rely on soft expected-cost objectives or iterative generative inference, which can be…

Machine Learning · Computer Science 2026-03-17 Mumuksh Tayal , Manan Tayal , Ravi Prakash

Stochastic Optimal Control provides a unified mathematical framework for solving complex decision-making problems, encompassing paradigms such as maximum entropy reinforcement learning(RL) and imitation learning(IL). However, conventional…

Machine Learning · Computer Science 2026-02-23 Hang Liu , Sangli Teng , Maani Ghaffari

Tilted (entropic) risk, obtained by applying a log-exponential transform to a base loss, is a well established tool in statistics and machine learning for emphasizing rare or high loss events while retaining a tractable optimization…

Machine Learning · Computer Science 2025-12-04 Vahid R. Ramezani , Benjamin Englard