English
Related papers

Related papers: RL makes MLLMs see better than SFT

200 papers

Multimodal Large Language Models (MLLMs) perform well in single-image visual grounding but struggle with real-world tasks that demand cross-image reasoning and multi-modal instructions. To address this, we adopt a reinforcement learning…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Bob Zhang , Haoran Li , Tao Zhang , Jianan Li , Cilin Yan , Xikai Liu , Jiayin Cai , Yanbin Hao

Achieving deep alignment between vision and language remains a central challenge for Multimodal Large Language Models (MLLMs). These models often fail to fully leverage visual input, defaulting to strong language priors. Our approach first…

Computer Vision and Pattern Recognition · Computer Science 2025-07-03 Aarti Ghatkesar , Ganesh Venkatesh

Multimodal Large Language Models (MLLMs) have recently achieved remarkable success in visual-language understanding, demonstrating superior high-level semantic alignment within their vision encoders. An important question thus arises: Can…

Computer Vision and Pattern Recognition · Computer Science 2026-02-11 Yikun Liu , Yuan Liu , Shangzhe Di , Haicheng Wang , Zhongyin Zhao , Le Tian , Xiao Zhou , Jie Zhou , Jiangchao Yao , Yanfeng Wang , Weidi Xie

In recent times, the standard practice for developing MLLMs is to feed features from vision encoder(s) into the LLM and train with natural language supervision. This approach often causes models to lean towards language comprehension and…

Computer Vision and Pattern Recognition · Computer Science 2025-10-20 Jitesh Jain , Zhengyuan Yang , Humphrey Shi , Jianfeng Gao , Jianwei Yang

Reinforcement learning (RL) has emerged as a promising approach for eliciting reasoning chains before generating final answers. However, multimodal large language models (MLLMs) generate reasoning that lacks integration of visual…

Computer Vision and Pattern Recognition · Computer Science 2026-01-05 Omar Sharif , Eftekhar Hossain , Patrick Ng

Despite the remarkable success of the LLaVA architecture for vision-language tasks, its design inherently struggles to effectively integrate visual features due to the inherent mismatch between text and vision modalities. We tackle this…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Dongwan Kim , Viresh Ranjan , Takashi Nagata , Arnab Dhua , Amit Kumar K C

In recent years, multimodal large language models (MLLMs) have shown strong potential in real-world applications. They are developing rapidly due to their remarkable ability to comprehend multimodal information and their inherent powerful…

Computer Vision and Pattern Recognition · Computer Science 2024-08-02 Bozhou Li , Hao Liang , Zimo Meng , Wentao Zhang

Multimodal Large Language Models (MLLMs) have achieved notable gains in various tasks by incorporating Chain-of-Thought (CoT) reasoning in language spaces. Recent work extends this direction by leveraging external tools for visual editing,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Bangzheng Li , Ximeng Sun , Jiang Liu , Ze Wang , Jialian Wu , Xiaodong Yu , Hao Chen , Emad Barsoum , Muhao Chen , Zicheng Liu

Multimodal large language models (MLLMs) trained with visual instruction tuning have achieved strong performance across diverse tasks, yet they remain limited in vision-centric tasks such as object counting or spatial reasoning. We…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Heeji Yoon , Jaewoo Jung , Junwan Kim , Hyungyu Choi , Heeseong Shin , Sangbeom Lim , Honggyu An , Chaehyun Kim , Jisang Han , Donghyun Kim , Chanho Eom , Sunghwan Hong , Seungryong Kim

Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a powerful paradigm for post-training large language models (LLMs), achieving state-of-the-art performance on tasks with structured, verifiable answers. Applying…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Yiqing Liang , Jielin Qiu , Wenhao Ding , Zuxin Liu , James Tompkin , Mengdi Xu , Mengzhou Xia , Zhengzhong Tu , Laixi Shi , Jiacheng Zhu

This work revisits the dominant supervised fine-tuning (SFT) then reinforcement learning (RL) paradigm for training Large Vision-Language Models (LVLMs), and reveals a key finding: SFT can significantly undermine subsequent RL by inducing…

Computation and Language · Computer Science 2025-04-17 Hardy Chen , Haoqin Tu , Fali Wang , Hui Liu , Xianfeng Tang , Xinya Du , Yuyin Zhou , Cihang Xie

While large language models (LLMs) demonstrate strong reasoning capabilities utilizing reinforcement learning (RL) with verifiable reward, whether large vision-language models (VLMs) can directly inherit such capabilities through similar…

Artificial Intelligence · Computer Science 2025-05-27 Tianle Li , Jihai Zhang , Yongming Rao , Yu Cheng

Recent advances in vision-language models (VLMs) reasoning have been largely attributed to the rise of reinforcement Learning (RL), which has shifted the community's focus away from the supervised fine-tuning (SFT) paradigm. Many studies…

Multimodal large language models (MLLMs) typically extract visual features from the final layers of a pretrained Vision Transformer (ViT). This widespread deep-layer bias, however, is largely driven by empirical convention rather than…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Haoran Chen , Junyan Lin , Xinghao Chen , Yue Fan , Jianfeng Dong , Xin Jin , Hui Su , Jinlan Fu , Xiaoyu Shen

Reinforcement learning (RL) is increasingly used to post-train medical Vision-Language Models (VLMs), yet it remains unclear whether RL improves medical visual reasoning or mainly sharpens behaviors already induced by supervised fine-tuning…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Ahmadreza Jeddi , Kimia Shaban , Negin Baghbanzadeh , Natasha Sharan , Abhishek Moturu , Elham Dolatabadi , Babak Taati

Pre-trained Large Language Model (LLM) exhibits broad capabilities, yet, for specific tasks or domains their attainment of higher accuracy and more reliable reasoning generally depends on post-training through Supervised Fine-Tuning (SFT)…

Artificial Intelligence · Computer Science 2026-03-17 Haitao Jiang , Wenbo Zhang , Jiarui Yao , Hengrui Cai , Sheng Wang , Rui Song

We initiate the first empirical study on the use of MLP architectures for vision-and-language (VL) fusion. Through extensive experiments on 5 VL tasks and 5 robust VQA benchmarks, we find that: (i) Without pre-training, using MLPs for…

Computer Vision and Pattern Recognition · Computer Science 2021-12-09 Yixin Nie , Linjie Li , Zhe Gan , Shuohang Wang , Chenguang Zhu , Michael Zeng , Zicheng Liu , Mohit Bansal , Lijuan Wang

Recently, there has been a surge in the popularity of pre trained large language models (LLMs) (such as GPT-4), sweeping across the entire Natural Language Processing (NLP) and Computer Vision (CV) communities. These LLMs have demonstrated…

Computer Vision and Pattern Recognition · Computer Science 2024-01-09 Shuxiao Ma , Linyuan Wang , Senbao Hou , Bin Yan

Many vision-language models (VLMs) that prove very effective at a range of multimodal task, build on CLIP-based vision encoders, which are known to have various limitations. We investigate the hypothesis that the strong language backbone in…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Sho Takishita , Jay Gala , Abdelrahman Mohamed , Kentaro Inui , Yova Kementchedjhieva

As the performance of Large-scale Vision Language Models (LVLMs) improves, they are increasingly capable of responding in multiple languages, and there is an expectation that the demand for explanations generated by LVLMs will grow.…

Computation and Language · Computer Science 2025-02-17 Shintaro Ozaki , Kazuki Hayashi , Yusuke Sakai , Hidetaka Kamigaito , Katsuhiko Hayashi , Taro Watanabe
‹ Prev 1 2 3 10 Next ›