paper-with-me

홈 › Papers

SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning

2025-10-18 · Xiaojun Guo, Runyu Zhou, Yifei Wang, Qi Zhang, Chenheng Zhang, Stefanie Jegelka, Xiaohan Wang, Jiajun Chai, Guojun Yin, Wei Lin, Yisen Wang arxiv

Vision-language models (VLMs) have shown remarkable abilities by integrating large language models with visual inputs. However, they often fail to utilize visual evidence adequately, either depending on linguistic priors in vision-centric tasks or resorting to textual shortcuts during reasoning. Although reinforcement learning (RL) can align models with desired behaviors, its application to VLMs has been hindered by the lack of scalable and reliable reward mechanisms. To overcome this challenge, we propose SSL4RL, a novel framework that leverages self-supervised learning (SSL) tasks as a source of verifiable rewards for RL-based fine-tuning. Our approach reformulates SSL objectives-such as predicting image rotation or reconstructing masked patches-into dense, automatic reward signals, eliminating the need for human preference data or unreliable AI evaluators. Experiments show that SSL4RL substantially improves performance on both vision-centric and vision-language reasoning benchmarks. Furthermore, through systematic ablations, we identify key factors-such as task difficulty, model scale, and semantic alignment with the target domain-that influence the effectiveness of SSL4RL tasks, offering new design principles for future work. We also demonstrate the framework's generality by applying it to graph learning, where it yields significant gains. SSL4RL establishes a versatile and effective paradigm for aligning multimodal models using verifiable, self-supervised objectives.

📄 PDF Abstract BibTeX arXiv:2510.16416

Code (0)

등록된 구현이 없습니다.

Tasks

Self-Supervised LearningReinforcement LearningGraph Learning

Similar Papers 제목 키워드 기반

Image Augmentation Based Momentum Memory Intrinsic Reward for Sparse Reward Visual Scenes

2022-05-19 · Zheng Fang, Biao Zhao, Guizhong Liu

Many scenes in real life can be abstracted to the sparse reward visual scenes, where it is difficult for an agent to tackle the task under the condition of only accepting images and sparse rewards. We propose to decompos…

Image AugmentationRepresentation LearningVisual Navigation

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models

2026-04-22 · Jiahao Xie, Alessio Tonioni, Nathalie Rauschmayr, Federico Tombari 외 arxiv

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 …

Self-Supervised LearningReinforcement Learning

iReasoner: Trajectory-Aware Intrinsic Reasoning Supervision for Self-Evolving Large Multimodal Models

2026-01-09 · Meghana Sunil, Manikandarajan Venmathimaran, Muthu Subash Kavitha arxiv

Recent work shows that large multimodal models (LMMs) can self-improve from unlabeled data via self-play and intrinsic feedback. Yet existing self-evolving frameworks mainly reward final outcomes, leaving intermediate re…

Multimodal ReasoningDecision Making

SEMI: Self-supervised Exploration via Multisensory Incongruity

2020-09-26 · Jianren Wang, Ziwen Zhuang, Hang Zhao

Efficient exploration is a long-standing problem in reinforcement learning since extrinsic rewards are usually sparse or missing. A popular solution to this issue is to feed an agent with novelty signals as intrinsic rew…

Efficient Exploration

Noisy Agents: Self-supervised Exploration by Predicting Auditory Events

2020-07-27 · Chuang Gan, Xiaoyu Chen, Phillip Isola, Antonio Torralba 외

Humans integrate multiple sensory modalities (e.g. visual and audio) to build a causal understanding of the physical world. In this work, we propose a novel type of intrinsic motivation for Reinforcement Learning (RL) th…

Atari GamesReinforcement Learning (RL)