English
Related papers

Related papers: Stabilizing MoE Reinforcement Learning by Aligning…

200 papers

Reinforcement learning (RL) has become a predominant technique to align language models (LMs) with human preferences or promote outputs which are deemed to be desirable by a given reward function. Standard RL approaches optimize average…

Machine Learning · Computer Science 2025-10-27 Stephen Zhao , Aidan Li , Rob Brekelmans , Roger Grosse

Mixture-of-Experts (MoE) models can scale parameter capacity by routing each token to a subset of experts through a learned gate function. While conditional routing reduces training costs, it shifts the burden on inference memory: expert…

Machine Learning · Computer Science 2025-10-07 Rana Shahout , Colin Cai , Yilun Du , Minlan Yu , Michael Mitzenmacher

We present Ring-lite, a Mixture-of-Experts (MoE)-based large language model optimized via reinforcement learning (RL) to achieve efficient and robust reasoning capabilities. Built upon the publicly available Ling-lite model, a 16.8 billion…

Scaling reinforcement learning (RL) has shown strong promise for enhancing the reasoning abilities of large language models (LLMs), particularly in tasks requiring long chain-of-thought generation. However, RL training efficiency is often…

Machine Learning · Computer Science 2026-03-25 Yiqi Zhang , Huiqiang Jiang , Xufang Luo , Zhihe Yang , Chengruidong Zhang , Yifei Shen , Dongsheng Li , Yuqing Yang , Lili Qiu , Yang You

Offline reinforcement learning (RL) is challenged by the distributional shift between learning policies and datasets. To address this problem, existing works mainly focus on designing sophisticated algorithms to explicitly or implicitly…

Machine Learning · Computer Science 2022-10-18 Yang Yue , Bingyi Kang , Xiao Ma , Zhongwen Xu , Gao Huang , Shuicheng Yan

This study presents a comparative analysis between single-objective and multi-objective reinforcement learning methods for training a robot to navigate effectively to an end goal while efficiently avoiding obstacles. Traditional…

Robotics · Computer Science 2023-12-15 Vicki Young , Jumman Hossain , Nirmalya Roy

Developing versatile quadruped robots that can smoothly perform various actions and tasks in real-world environments remains a significant challenge. This paper introduces a novel vision-language-action (VLA) model, mixture of robotic…

Robotics · Computer Science 2025-03-12 Han Zhao , Wenxuan Song , Donglin Wang , Xinyang Tong , Pengxiang Ding , Xuelian Cheng , Zongyuan Ge

Deep reinforcement learning (DRL) has been used to learn effective heuristics for solving complex combinatorial optimisation problem via policy networks and have demonstrated promising performance. Existing works have focused on solving…

Machine Learning · Computer Science 2020-12-25 Nasrin Sultana , Jeffrey Chan , A. K. Qin , Tabinda Sarwar

Ensuring reliability in modern software systems requires rigorous pre-production testing across highly heterogeneous and evolving environments. Because exhaustive evaluation is infeasible, practitioners must decide how to allocate limited…

Software Engineering · Computer Science 2025-10-08 Yu Zhu

In this paper, we study the outage minimization problem in a decode-and-forward cooperative network with relay uncertainty. To reduce the outage probability and improve the quality of service, existing researches usually rely on the…

Information Theory · Computer Science 2022-05-19 Yuanzhe Geng , Erwu Liu , Rui Wang , Pengcheng Sun , Binyu Lu

Reinforcement Learning (RL) is a method for learning decision-making tasks that could enable robots to learn and adapt to their situation on-line. For an RL algorithm to be practical for robotic control tasks, it must learn in very few…

Artificial Intelligence · Computer Science 2015-03-19 Todd Hester , Michael Quinlan , Peter Stone

Reinforcement learning with verifiable rewards (RLVR) has delivered impressive gains in mathematical and multimodal reasoning and has become a standard post-training paradigm for contemporary language and vision-language models. However,…

Machine Learning · Computer Science 2025-10-28 Hoang Phan , Xianjun Yang , Kevin Yao , Jingyu Zhang , Shengjie Bi , Xiaocheng Tang , Madian Khabsa , Lijuan Liu , Deren Lei

Mixture-of-Experts (MoE) architectures have emerged as a leading paradigm for scaling large language models through sparse, routing-based computation. However, this design introduces a new attack surface: the routing mechanism that…

Cryptography and Security · Computer Science 2026-05-07 Zekun Fei , Zihao Wang , Weijie Liu , Ruiqi He , Jianing Geng , Zheli Liu , XiaoFeng Wang

Sparsely gated Mixture of Experts (MoE) models have been shown to be a compute-efficient method to scale model capacity for multilingual machine translation. However, for low-resource tasks, MoE models severely over-fit. We show effective…

Computation and Language · Computer Science 2022-12-19 Maha Elbayad , Anna Sun , Shruti Bhosale

Reinforcement learning (RL) requires skillful definition and remarkable computational efforts to solve optimization and control problems, which could impair its prospect. Introducing human guidance into reinforcement learning is a promising…

Machine Learning · Computer Science 2022-11-30 Jingda Wu , Zhiyu Huang , Wenhui Huang , Chen Lv

Sparse Mixture-of-Experts (MoE) models scale Transformers efficiently but suffer from expert overlap -- redundant representations across experts and routing ambiguity, resulting in severely underutilized model capacity. While architectural…

Machine Learning · Computer Science 2026-02-17 Rizhen Hu , Yuan Cao , Boao Kong , Mou Sun , Kun Yuan

With the continuous growth in communication network complexity and traffic volume, communication load balancing solutions are receiving increasing attention. Specifically, reinforcement learning (RL)-based methods have shown impressive…

Networking and Internet Architecture · Computer Science 2023-03-30 Yi Tian Xu , Jimmy Li , Di Wu , Michael Jenkin , Seowoo Jang , Xue Liu , Gregory Dudek

Current Large Language Models (LLMs) face three major challenges: context length limitations, high inference costs, and catastrophic forgetting during continual learning. While Mixture-of-Experts (MoE) architectures mitigate some of these…

Machine Learning · Computer Science 2025-12-23 Zhongpan Tang

This tutorial provides a comprehensive survey of methods for fine-tuning diffusion models to optimize downstream reward functions. While diffusion models are widely known to provide excellent generative modeling capability, practical…

Machine Learning · Computer Science 2024-07-19 Masatoshi Uehara , Yulai Zhao , Tommaso Biancalani , Sergey Levine

Continual instruction tuning (CIT) requires multimodal large language models (MLLMs) to adapt to a stream of tasks without forgetting prior capabilities. A common strategy is to isolate updates by routing inputs to different LoRA experts.…

Machine Learning · Computer Science 2026-01-21 Zhiyan Hou , Haiyun Guo , Haokai Ma , Yandu Sun , Yonghui Yang , Jinqiao Wang