English
Related papers

Related papers: SofT-GRPO: Surpassing Discrete-Token LLM Reinforce…

200 papers

Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for enhancing Large Language Models (LLMs) on complex reasoning tasks. However, existing methods suffer from an exploration dilemma: the sharply peaked initial…

Artificial Intelligence · Computer Science 2025-09-30 Yuhua Jiang , Jiawei Huang , Yufeng Yuan , Xin Mao , Yu Yue , Qianchuan Zhao , Lin Yan

While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it requires models to verbalize every intermediate step in text tokens, constraining the model thoughts to the discrete vocabulary…

Computation and Language · Computer Science 2026-02-12 Weihao Liu , Dehai Min , Lu Cheng

Reinforcement Learning with Verifiable Rewards (RLVR) and Group Relative Policy Optimization (GRPO) have significantly advanced the reasoning capabilities of large language models. Extending these methods to multimodal settings, however,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Jinghan Li , Junfeng Fang , Jinda Lu , Yuan Wang , Xiaoyan Guo , Tianyu Zhang , Xiang Wang , Xiangnan He

Explicit chain-of-thought (CoT) reasoning substantially improves the reasoning ability of large language models (LLMs), but incurs high inference cost due to lengthy autoregressive traces. Existing latent reasoning methods offer a promising…

Computation and Language · Computer Science 2026-05-26 Hui Xie , Jie Liu , Ziyue Qiao , Joaquin Vanschore

Chain-of-thought (CoT) reasoning has enabled large language models (LLMs) to utilize additional computation through intermediate tokens to solve complex tasks. However, we posit that typical reasoning traces contain many redundant tokens,…

Computation and Language · Computer Science 2025-06-11 Tergel Munkhbat , Namgyu Ho , Seo Hyun Kim , Yongjin Yang , Yujin Kim , Se-Young Yun

Post-training methods, especially Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), play an important role in improving large language models' (LLMs) complex reasoning abilities. However, the dominant two-stage pipeline (SFT…

Machine Learning · Computer Science 2025-12-22 Mingyu Su , Jian Guan , Yuxian Gu , Minlie Huang , Hongning Wang

The advancement of Large Language Models (LLMs) has brought substantial attention to the Chain of Thought (CoT) approach, primarily due to its ability to enhance the capability of LLMs on complex reasoning tasks. Moreover, the significance…

Computation and Language · Computer Science 2024-03-05 Bingshuai Liu , Chenyang Lyu , Zijun Min , Zhanyu Wang , Jinsong Su , Longyue Wang

Recently, with the chain of thought (CoT) prompting, large language models (LLMs), e.g., GPT-3, have shown strong reasoning ability in several natural language processing tasks such as arithmetic, commonsense, and logical reasoning.…

Artificial Intelligence · Computer Science 2023-10-20 Yixuan Weng , Minjun Zhu , Fei Xia , Bin Li , Shizhu He , Shengping Liu , Bin Sun , Kang Liu , Jun Zhao

Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increased time-to-first-token (TTFT). We propose a training…

Computation and Language · Computer Science 2026-01-08 Roy Xie , David Qiu , Deepak Gopinath , Dong Lin , Yanchao Sun , Chong Wang , Saloni Potdar , Bhuwan Dhingra

Large language models (LLMs) have shown impressive capabilities, but still struggle with complex reasoning tasks requiring multiple steps. While prompt-based methods like Chain-of-Thought (CoT) can improve LLM reasoning at inference time,…

Artificial Intelligence · Computer Science 2024-11-25 Haolin Chen , Yihao Feng , Zuxin Liu , Weiran Yao , Akshara Prabhakar , Shelby Heinecke , Ricky Ho , Phil Mui , Silvio Savarese , Caiming Xiong , Huan Wang

Adapting large language models (LLMs) for specific tasks usually involves fine-tuning through reinforcement learning with human feedback (RLHF) on preference data. While these data often come from diverse labelers' groups (e.g., different…

Computation and Language · Computer Science 2024-05-31 Shyam Sundhar Ramesh , Yifan Hu , Iason Chaimalas , Viraj Mehta , Pier Giuseppe Sessa , Haitham Bou Ammar , Ilija Bogunovic

Large Language Models (LLMs) using Chain-of-Thought (CoT) prompting excel at complex reasoning but generate verbose thought processes with considerable redundancy, leading to increased inference costs and reduced efficiency. We introduce a…

Artificial Intelligence · Computer Science 2026-02-17 Zeju Li , Jianyuan Zhong , Ziyang Zheng , Xiangyu Wen , Zhijian Xu , Yingying Cheng , Fan Zhang , Qiang Xu

RTL design often relies heavily on ad-hoc testbench creation early in the design cycle. While large language models (LLMs) show promise for RTL code generation, their ability to reason about hardware specifications and generate targeted…

Hardware Architecture · Computer Science 2026-01-13 Dimple Vijay Kochar , Nathaniel Pinckney , Guan-Ting Liu , Chia-Tung Ho , Chenhui Deng , Haoxing Ren , Brucek Khailany

Supervised Fine-Tuning (SFT) has been a go-to and effective method for enhancing long chain-of-thought (CoT) reasoning in relatively small LLMs by fine-tuning them with long CoT responses from larger LLMs. To continually improve reasoning…

Machine Learning · Computer Science 2025-02-20 Wang Yang , Hongye Jin , Jingfeng Yang , Vipin Chaudhary , Xiaotian Han

This paper proposes a GRPO-based approach to enhance the performance of large language model (LLM)-based text-to-speech (TTS) models by deriving rewards from an off-the-shelf automatic speech recognition (ASR) model. Compared to previous…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-24 Chang Liu , Ya-Jun Hu , Ying-Ying Gao , Shi-Lei Zhang , Zhen-Hua Ling

With respect to improving the reasoning accuracy of LLMs, the representative reinforcement learning (RL) method GRPO faces failure due to insignificant reward variance, while verification methods based on process reward models (PRMs) suffer…

Artificial Intelligence · Computer Science 2025-09-09 Sining Zhoubian , Dan Zhang , Jie Tang

Large Language Models (LLMs) have demonstrated impressive capabilities in language processing, yet they often struggle with tasks requiring genuine visual spatial reasoning. In this paper, we introduce a novel two-stage training framework…

Computation and Language · Computer Science 2025-02-26 Alan Dao , Dinh Bach Vu

Existing 3D human motion generation and understanding methods often exhibit limited interpretability, restricting effective mutual enhancement between these inherently related tasks. While current unified frameworks based on large language…

Artificial Intelligence · Computer Science 2026-01-21 Guocun Wang , Kenkun Liu , Jing Lin , Guorui Song , Jian Li , Xiaoguang Han

Chain-of-Thought (CoT) prompting has recently shown significant promise across various NLP and computer vision tasks by explicitly generating intermediate reasoning steps. However, we find that reinforcement learning (RL)-based fine-tuned…

Computer Vision and Pattern Recognition · Computer Science 2025-11-19 Qingyang Yan , Guangyao Chen , Yixiong Zou

Medical Image Grounding (MIG), which involves localizing specific regions in medical images based on textual descriptions, requires models to not only perceive regions but also deduce spatial relationships of these regions. Existing…

Machine Learning · Computer Science 2025-07-08 Huihui Xu , Yuanpeng Nie , Hualiang Wang , Ying Chen , Wei Li , Junzhi Ning , Lihao Liu , Hongqiu Wang , Lei Zhu , Jiyao Liu , Xiaomeng Li , Junjun He