English
Related papers

Related papers: Not all tokens are needed(NAT): token efficient re…

200 papers

Offline Reinforcement Learning (Offline RL) presents challenges of learning effective decision-making policies from static datasets without any online interactions. Data augmentation techniques, such as noise injection and data…

Artificial Intelligence · Computer Science 2024-11-08 Jaewoo Lee , Sujin Yun , Taeyoung Yun , Jinkyoo Park

Controlled text generation tasks such as unsupervised text style transfer have increasingly adopted the use of Reinforcement Learning (RL). A major challenge in applying RL to such tasks is the sparse reward, which is available only after…

Computation and Language · Computer Science 2022-04-19 Bhargav Upadhyay , Akhilesh Sudhakar , Arjun Maheswaran

In this work, we address the problem of determining reliable policies in reinforcement learning (RL), with a focus on optimization under uncertainty and the need for performance guarantees. While classical RL algorithms aim at maximizing…

Machine Learning · Computer Science 2025-10-22 Nadir Farhi

Reinforcement learning (RL) has been proven to be an effective and robust method for training neural machine translation systems, especially when paired with powerful reward models that accurately assess translation quality. However, most…

Computation and Language · Computer Science 2025-11-24 Miguel Moura Ramos , Tomás Almeida , Daniel Vareta , Filipe Azevedo , Sweta Agrawal , Patrick Fernandes , André F. T. Martins

Non-autoregressive Transformer(NAT) significantly accelerates the inference of neural machine translation. However, conventional NAT models suffer from limited expression power and performance degradation compared to autoregressive (AT)…

Computation and Language · Computer Science 2023-11-15 Shangtong Gui , Chenze Shao , Zhengrui Ma , Xishan Zhang , Yunji Chen , Yang Feng

Large Language Models (LLMs) excel at multi-step reasoning, yet increasing the structural complexity of inference does not consistently improve system-level returns. Methods such as Tree of Thoughts (ToT), Graph of Thoughts (GoT), and…

Computation and Language · Computer Science 2026-03-09 Yuhang Liu , Ruijie Wang , Yunlong Chu , Bing Hao , Yumeng Lin , Shengzhong Liu , Minglai Shao

Large language models (LLMs) have shown impressive capabilities in handling complex tasks through long-chain reasoning. However, the extensive reasoning steps involved can significantly increase computational costs, posing challenges for…

Computation and Language · Computer Science 2025-05-28 Yunhao Wang , Yuhao Zhang , Tinghao Yu , Can Xu , Feng Zhang , Fengzong Lian

Large language models (LLMs) excel at complex tasks thanks to advances in their reasoning abilities. However, existing methods overlook the trade-off between reasoning effectiveness and efficiency, often encouraging unnecessarily long…

Machine Learning · Computer Science 2025-10-16 Jingyao Wang , Wenwen Qiang , Zeen Song , Changwen Zheng , Hui Xiong

Reinforcement learning (RL) has become a prevailing approach for fine-tuning large language models (LLMs) on complex reasoning tasks. Among recent methods, GRPO stands out for its empirical success in training models such as DeepSeek-R1,…

Machine Learning · Computer Science 2025-06-13 Wei Xiong , Jiarui Yao , Yuhui Xu , Bo Pang , Lei Wang , Doyen Sahoo , Junnan Li , Nan Jiang , Tong Zhang , Caiming Xiong , Hanze Dong

In practice, rigorous reasoning is often a key driver of correct code, while Reinforcement Learning (RL) for code generation often neglects optimizing reasoning quality. Bringing process-level supervision into RL is appealing, but it faces…

Software Engineering · Computer Science 2026-05-06 Lishui Fan , Yu Zhang , Mouxiang Chen , Zhongxin Liu

In the classical Reinforcement Learning from Human Feedback (RLHF) framework, Proximal Policy Optimization (PPO) is employed to learn from sparse, sentence-level rewards -- a challenging scenario in traditional deep reinforcement learning.…

Machine Learning · Computer Science 2025-05-22 Han Zhong , Zikang Shan , Guhao Feng , Wei Xiong , Xinle Cheng , Li Zhao , Di He , Jiang Bian , Liwei Wang

Latent reasoning represents a new development in Transformer language models that has shown potential in compressing reasoning lengths compared to chain-of-thought reasoning. By directly passing the information-rich previous final latent…

Machine Learning · Computer Science 2025-11-27 Alex Ning , Yen-Ling Kuo , Gabe Gomes

Reinforcement Learning with Verifiable Rewards (RLVR) trains reasoning models without labeled trajectories, relying on grouped rollouts to expose the policy to alternative reasoning paths and a verifier to score them. Rollout diversity has…

Artificial Intelligence · Computer Science 2026-05-28 Soeun Kim , Albert No

Large Reasoning Models (LRMs) demonstrate strong performance on complex tasks but often suffer from excessive verbosity, known as "overthinking." Existing solutions via reinforcement learning (RL) typically penalize generated tokens to…

Computation and Language · Computer Science 2025-12-02 Canhui Wu , Qiong Cao , Chang Li , Zhenfang Wang , Chao Xue , Yuwei Fan , Wei Xi , Xiaodong He

Training Large Language Models (LLMs) for chain-of-thought reasoning presents a significant challenge: supervised fine-tuning on a single "golden" rationale hurts generalization as it penalizes equally valid alternatives, whereas…

Computation and Language · Computer Science 2025-11-14 Mingye Zhu , Yi Liu , Zheren Fu , Quan Wang , Yongdong Zhang

To employ a Convolutional Neural Network (CNN) in an energy-constrained embedded system, it is critical for the CNN implementation to be highly energy efficient. Many recent studies propose CNN accelerator architectures with custom…

Hardware Architecture · Computer Science 2020-10-08 Syed M. A. H. Jafri , Hasan Hassan , Ahmed Hemani , Onur Mutlu

Multimodal Chain-of-Thought (CoT) reasoning requires large vision-language models to construct reasoning trajectories that interleave perceptual grounding with multi-step inference. However, existing Reinforcement Learning with Verifiable…

Computer Vision and Pattern Recognition · Computer Science 2026-03-25 Yunheng Li , Hangyi Kuang , Hengrui Zhang , Jiangxia Cao , Zhaojie Liu , Qibin Hou , Ming-Ming Cheng

Extending large language models (LLMs) to low-resource languages often incurs an "alignment tax": improvements in the target language come at the cost of catastrophic forgetting in general capabilities. We argue that this trade-off arises…

Computation and Language · Computer Science 2026-05-15 Zeli Su , Ziyin Zhang , Zhou Liu , Xuexian Song , Zhankai Xu , Longfei Zheng , Xiaolu Zhang , Rong Fu , Guixian Xu , Wentao Zhang

Non-autoregressive translation (NAT) models, which remove the dependence on previous target tokens from the inputs of the decoder, achieve significantly inference speedup but at the cost of inferior accuracy compared to autoregressive…

Computation and Language · Computer Science 2018-12-27 Junliang Guo , Xu Tan , Di He , Tao Qin , Linli Xu , Tie-Yan Liu

Large reasoning models (LRMs) substantially outperform their base LLM counterparts on challenging reasoning benchmarks, yet it remains poorly understood where base models go wrong during token-by-token generation and how to narrow this gap…

Artificial Intelligence · Computer Science 2026-05-19 Changshuo Shen , Leheng Sheng , Yuxin Chen , An Zhang , Xiang Wang