中文
相关论文

相关论文: Nemotron-Cascade: Scaling Cascaded Reinforcement L…

200 篇论文

In this paper, we investigate the problem of how to effectively master tool-use to solve complex visual reasoning tasks for Multimodal Large Language Models. To achieve that, we propose a novel Tool-supervised Reinforcement Learning…

计算机视觉与模式识别 · 计算机科学 2026-04-23 Qihua Dong , Gozde Sahin , Pei Wang , Zhaowei Cai , Robik Shrestha , Hao Yang , Davide Modolo

Reinforcement learning (RL) has demonstrated potential for enhancing reasoning in large language models (LLMs). However, effective RL training, which requires medium-difficulty training samples, faces two fundamental challenges: Effective…

机器学习 · 计算机科学 2026-05-19 Ru Zhang , Renda Li , Ziyu Ma , Weijie Qiu , Chongyang Tao , Yong Wang , Xiangxiang Chu

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…

软件工程 · 计算机科学 2025-10-08 Yu Zhu

Chaotic convective flows arise in many real-world systems, such as microfluidic devices and chemical reactors. Stabilizing these flows is highly desirable but remains challenging, particularly in chaotic regimes where conventional control…

机器学习 · 计算机科学 2025-11-04 Michiel Straat , Thorben Markmann , Sebastian Peitz , Barbara Hammer

Reinforcement learning (RL) offers a compelling data-driven paradigm for synthesizing controllers for complex systems when accurate physical models are unavailable; however, most existing control-oriented RL methods assume stationarity and,…

机器学习 · 计算机科学 2026-04-22 Austin Coursey , Abel Diaz-Gonzalez , Marcos Quinones-Grueiro , Gautam Biswas

Consistent image generation requires faithfully preserving identities, styles, and logical coherence across multiple images, which is essential for applications such as storytelling and character design. Supervised training approaches…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Bowen Ping , Chengyou Jia , Minnan Luo , Changliang Xia , Xin Shen , Zhuohang Dang , Hangwei Qian

Reinforcement learning (RL) commonly relies on scalar rewards with limited ability to express temporal, conditional, or safety-critical goals, and can lead to reward hacking. Temporal logic expressible via the more general class of…

人工智能 · 计算机科学 2025-11-26 Dominik Wagner , Leon Witzman , Luke Ong

Reinforcement learning (RL) has achieved notable performance in high-dimensional sequential decision-making tasks, yet remains limited by low sample efficiency, sensitivity to noise, and weak generalization under partial observability. Most…

机器学习 · 计算机科学 2026-02-18 Sibo Zhang , Rui Jing , Liangfu Lv , Jian Zhang , Yunliang Zang

Reinforcement learning (RL) research focuses on general solutions that can be applied across different domains. This results in methods that RL practitioners can use in almost any domain. However, recent studies often lack the engineering…

机器学习 · 计算机科学 2021-07-05 Anssi Kanervisto , Christian Scheller , Yanick Schraner , Ville Hautamäki

Large Language Models (LLMs) have made substantial strides in structured tasks through Reinforcement Learning (RL), demonstrating proficiency in mathematical reasoning and code generation. However, applying RL in broader domains like…

计算与语言 · 计算机科学 2025-02-10 Hao Sun , Yunyi Shen , Jean-Francois Ton , Mihaela van der Schaar

Reinforcement Learning from Human Feedback (RLHF) is widely used in Large Language Model (LLM) alignment. Traditional RL can be modeled as a dataflow, where each node represents computation of a neural network (NN) and each edge denotes…

机器学习 · 计算机科学 2024-10-03 Guangming Sheng , Chi Zhang , Zilingfeng Ye , Xibin Wu , Wang Zhang , Ru Zhang , Yanghua Peng , Haibin Lin , Chuan Wu

We introduce INTELLECT-2, the first globally distributed reinforcement learning (RL) training run of a 32 billion parameter language model. Unlike traditional centralized training efforts, INTELLECT-2 trains a reasoning model using fully…

Large language models (LLMs) have notably progressed in multi-step and long-chain reasoning. However, extending their reasoning capabilities to encompass deep interactions with search remains a non-trivial challenge, as models often fail to…

计算与语言 · 计算机科学 2025-06-05 Qingfei Zhao , Ruobing Wang , Dingling Xu , Daren Zha , Limin Liu

Reservoir computers (RCs) provide a computationally efficient alternative to deep learning while also offering a framework for incorporating brain-inspired computational principles. By using an internal neural network with random, fixed…

神经与进化计算 · 计算机科学 2025-04-18 Keshav Srinivasan , Dietmar Plenz , Michelle Girvan

Contemporary progress in large language models (LLMs) has revealed notable inferential capacities via reinforcement learning (RL) employing verifiable reward, facilitating the development of O1 and R1-like reasoning models. Directly…

机器学习 · 计算机科学 2025-10-21 Zexu Sun , Yongcheng Zeng , Erxue Min , Heyang Gao , Bokai Ji , Xu Chen

Reinforcement learning (RL) can elicit strong reasoning in large language models (LLMs), yet most open efforts focus on math and code. We propose Reasoning Curriculum, a simple two-stage curriculum that first elicits reasoning skills in…

人工智能 · 计算机科学 2025-10-31 Bo Pang , Deqian Kong , Silvio Savarese , Caiming Xiong , Yingbo Zhou

Machine learning applied to architecture design presents a promising opportunity with broad applications. Recent deep reinforcement learning (DRL) techniques, in particular, enable efficient exploration in vast design spaces where…

硬件体系结构 · 计算机科学 2019-05-14 Ting-Ru Lin , Drew Penney , Massoud Pedram , Lizhong Chen

Reinforcement Learning (RL) has achieved tremendous development in recent years, but still faces significant obstacles in addressing complex real-life problems due to the issues of poor system generalization, low sample efficiency as well…

人工智能 · 计算机科学 2025-02-25 Chao Yu , Shicheng Ye , Hankz Hankui Zhuo

In recent years, training methods centered on Reinforcement Learning (RL) have markedly enhanced the reasoning and alignment performance of Large Language Models (LLMs), particularly in understanding human intents, following user…

计算与语言 · 计算机科学 2025-09-23 Keliang Liu , Dingkang Yang , Ziyun Qian , Weijie Yin , Yuchi Wang , Hongsheng Li , Jun Liu , Peng Zhai , Yang Liu , Lihua Zhang

As a subfield of machine learning, reinforcement learning (RL) aims at empowering one's capabilities in behavioural decision making by using interaction experience with the world and an evaluative feedback. Unlike traditional supervised…

机器学习 · 计算机科学 2020-04-27 Chao Yu , Jiming Liu , Shamim Nemati