English
Related papers

Related papers: First SFT, Second RL, Third UPT: Continual Improvi…

200 papers

Value-based reinforcement learning (RL) can in principle learn effective policies for a wide range of multi-turn problems, from games to dialogue to robotic control, including via offline RL from static previously collected datasets.…

Machine Learning · Computer Science 2024-11-28 Joey Hong , Anca Dragan , Sergey Levine

Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities under the widely adopted SFT+RLVR paradigm, which first performs Supervised Fine-Tuning (SFT) on human-annotated reasoning trajectories (rationales) to…

Computation and Language · Computer Science 2025-10-15 Chaoxu Pang , Yixuan Cao , Ping Luo

Recent studies demonstrate that multimodal large language models (MLLMs) can proficiently evaluate visual quality through interpretable assessments. However, existing approaches typically treat quality scoring and reasoning descriptions as…

Computer Vision and Pattern Recognition · Computer Science 2025-06-13 Zhuoxuan Cai , Jian Zhang , Xinbin Yuan , Peng-Tao Jiang , Wenxiang Chen , Bowen Tang , Lujian Yao , Qiyuan Wang , Jinwen Chen , Bo Li

Recent state-of-the-art language models utilize a two-phase training procedure comprised of (i) unsupervised pre-training on unlabeled text, and (ii) fine-tuning for a specific supervised task. More recently, many studies have been focused…

Computation and Language · Computer Science 2019-11-15 Itzik Malkiel , Lior Wolf

Large language models (LLMs) have demonstrated remarkable performance across a wide range of tasks. Advances in prompt engineering and fine-tuning techniques have further enhanced their ability to address complex reasoning challenges.…

Computation and Language · Computer Science 2024-12-16 Jing Bi , Yuting Wu , Weiwei Xing , Zhenjie Wei

Post-training processes are essential phases in grounding pre-trained language models to real-world tasks, with learning from demonstrations or preference signals playing a crucial role in this adaptation. We present a unified theoretical…

Machine Learning · Computer Science 2025-07-08 Bo Wang , Qinyuan Cheng , Runyu Peng , Rong Bao , Peiji Li , Qipeng Guo , Linyang Li , Zhiyuan Zeng , Yunhua Zhou , Xipeng Qiu

Large Language Models (LLMs) display strikingly different generalization behaviors: supervised fine-tuning (SFT) often narrows capability, whereas reinforcement-learning (RL) tuning tends to preserve it. The reasons behind this divergence…

Machine Learning · Computer Science 2026-01-01 Haoyue Bai , Yiyou Sun , Wenjie Hu , Shi Qiu , Maggie Ziyu Huan , Peiyang Song , Robert Nowak , Dawn Song

Large Language Models (LLMs) are rapidly surpassing human knowledge in many domains. While improving these models traditionally relies on costly human data, recent self-rewarding mechanisms (Yuan et al., 2024) have shown that LLMs can…

Computation and Language · Computer Science 2024-07-31 Tianhao Wu , Weizhe Yuan , Olga Golovneva , Jing Xu , Yuandong Tian , Jiantao Jiao , Jason Weston , Sainbayar Sukhbaatar

Large language models (LLMs) face significant challenges in effectively leveraging sequential environmental feedback (EF) signals, such as natural language evaluations, for feedback-independent chain-of-thought (CoT) reasoning. Existing…

Computation and Language · Computer Science 2025-07-29 Kang Yang , Jingxue Chen , Qingkun Tang , Tianxiang Zhang , Qianchun Lu

We study self-rewarding reasoning large language models (LLMs), which can simultaneously generate step-by-step reasoning and evaluate the correctness of their outputs during the inference time-without external feedback. This integrated…

Artificial Intelligence · Computer Science 2025-02-28 Wei Xiong , Hanning Zhang , Chenlu Ye , Lichang Chen , Nan Jiang , Tong Zhang

Process Reward Models (PRMs) provide step-level supervision that improves the reliability of reasoning in large language models. While PRMs have been extensively studied in text-based domains, their extension to Vision Language Models…

Artificial Intelligence · Computer Science 2025-10-08 Brandon Ong , Tej Deep Pala , Vernon Toh , William Chandra Tjhi , Soujanya Poria

Reinforcement learning (RL) with verifiable rewards (RLVR) has demonstrated the great potential of enhancing the reasoning abilities in multimodal large language models (MLLMs). However, the reliance on language-centric priors and expensive…

Computer Vision and Pattern Recognition · Computer Science 2026-04-23 Jiahao Xie , Alessio Tonioni , Nathalie Rauschmayr , Federico Tombari , Bernt Schiele

As the widespread adoption of Large Language Models (LLMs) accelerates, token consumption from intermediate reasoning traces increasingly contributes to inference latency and operational cost. Recent studies suggest that many real-world…

Artificial Intelligence · Computer Science 2026-05-08 Richmond Sin Jing Xuan , Rishabh Bhardwaj , Soujanya Poria

Large Language Models (LLMs) have demonstrated remarkable capabilities in open-ended text generation tasks. However, the inherent open-ended nature of these tasks implies that there is always room for improvement in the quality of model…

Computation and Language · Computer Science 2024-09-16 Ziqi Wang , Le Hou , Tianjian Lu , Yuexin Wu , Yunxuan Li , Hongkun Yu , Heng Ji

Existing efforts to improve logical reasoning ability of language models have predominantly relied on supervised fine-tuning, hindering generalization to new domains and/or tasks. The development of Large Langauge Models (LLMs) has…

Computation and Language · Computer Science 2024-06-18 Fangkai Jiao , Zhiyang Teng , Bosheng Ding , Zhengyuan Liu , Nancy F. Chen , Shafiq Joty

To acquire instruction-following capabilities, large language models (LLMs) undergo instruction tuning, where they are trained on instruction-response pairs using next-token prediction (NTP). Efforts to improve instruction tuning often…

Computation and Language · Computer Science 2026-04-21 Yuxin Xiao , Shujian Zhang , Wenxuan Zhou , Marzyeh Ghassemi , Sanqiang Zhao

In the quest for super-human performance, Large Language Models (LLMs) have traditionally been tethered to human-annotated datasets and predefined training objectives-a process that is both labor-intensive and inherently limited. This paper…

Computation and Language · Computer Science 2024-06-10 Ke Ji , Junying Chen , Anningzhe Gao , Wenya Xie , Xiang Wan , Benyou Wang

Mathematical reasoning remains a challenging area for large language models (LLMs), prompting the development of math-specific LLMs such as LLEMMA, DeepSeekMath, and Qwen2-Math, among others. These models typically follow a two-stage…

Computation and Language · Computer Science 2025-03-25 Zui Chen , Tianqiao Liu , Mi Tian , Qing Tong , Weiqi Luo , Zitao Liu

Large language models (LLMs) solve problems more accurately and interpretably when instructed to work out the answer step by step using a ``chain-of-thought'' (CoT) prompt. One can also improve LLMs' performance on a specific task by…

This paper investigates the role of explicit thinking process in rule-based reinforcement fine-tuning (RFT) for MLLMs. We first propose CLS-RL for MLLM image classification, using verifiable rewards for fine-tuning. Experiments show CLS-RL…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Ming Li , Jike Zhong , Shitian Zhao , Yuxiang Lai , Haoquan Zhang , Wang Bill Zhu , Kaipeng Zhang
‹ Prev 1 4 5 6 7 8 10 Next ›