# VLRM: Vision-Language Models act as Reward Models for Image Captioning

arXiv: https://arxiv.org/abs/2404.01911 · HTML: https://mlsanity.com/paper/2404.01911/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 21 of its 26 references that are in the map.
- First posted on arXiv 2 Apr 2024.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)
- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language](https://mlsanity.com/paper/2204.00598/) (2022)
- [Image Captioners Are Scalable Vision Learners Too](https://mlsanity.com/paper/2306.07915/) (2023)
- [ChatGPT Asks, BLIP-2 Answers: Automatic Questioning Towards Enriched Visual Descriptions](https://mlsanity.com/paper/2303.06594/) (2023)
- [IC3: Image Captioning by Committee Consensus](https://mlsanity.com/paper/2302.01328/) (2023)

## Built on by (most cited first, 18 of 18)

- [EmoLLM: Multimodal Emotional Understanding Meets Large Language Models](https://mlsanity.com/paper/2406.16442/) (2024)
- [Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)](https://mlsanity.com/paper/2504.03151/) (2025)
- [QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models](https://mlsanity.com/paper/2510.16292/) (2025)
- [Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models](https://mlsanity.com/paper/2510.18053/) (2025)
- [WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models](https://mlsanity.com/paper/2604.02570/) (2026)
- [ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models](https://mlsanity.com/paper/2507.21985/) (2025)
- [Clarification as Supervision: Reinforcement Learning for Vision-Language Interfaces](https://mlsanity.com/paper/2509.26594/) (2025)
- [What Makes a Good Generated Image? Investigating Human and Multimodal LLM Image Preference Alignment](https://mlsanity.com/paper/2509.12750/) (2025)
- [Reasoning Like Experts: Leveraging Multimodal Large Language Models for Drawing-based Psychoanalysis](https://mlsanity.com/paper/2510.19451/) (2025)
- [Multimodal Backdoor Attack on VLMs for Autonomous Driving via Graffiti and Cross-Lingual Triggers](https://mlsanity.com/paper/2604.04630/) (2026)
- [DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation](https://mlsanity.com/paper/2606.00535/) (2026)
- [FigEx2: Visual-Conditioned Panel Detection and Captioning for Scientific Compound Figures](https://mlsanity.com/paper/2601.08026/) (2026)
- [Grandes Modelos de Linguagem Multimodais (MLLMs): Da Teoria `a Pr'atica](https://mlsanity.com/paper/2602.12302/) (2026)
- [Cross-modal Identity Mapping: Minimizing Information Loss in Modality Conversion via Reinforcement Learning](https://mlsanity.com/paper/2603.01696/) (2026)
- [Geometry-Aware Semantic Reasoning for Training Free Video Anomaly Detection](https://mlsanity.com/paper/2603.13374/) (2026)
- [LASER: Loss-Aware Singular-value Decomposition and Rank Allocation for Efficient Low-Precision Vision-Language Models](https://mlsanity.com/paper/2606.00573/) (2026)
- [Re3Cap: Retrieval-Guided Refinement for Image Captioning Enhancement via Reinforcement Learning](https://mlsanity.com/paper/2608.21305/) (2026)
- [LineupRL: Verifiable Reinforcement Learning for Time Series Captioning via Caption-to-Series Identification](https://mlsanity.com/paper/2610.01800/) (2026)

## Abstract (arXiv)

In this work, we present an unsupervised method for enhancing an image captioning model (in our case, BLIP2) using reinforcement learning and vision-language models like CLIP and BLIP2-ITM as reward models. The RL-tuned model is able to generate longer and more comprehensive descriptions. Our model reaches impressive 0.90 R@1 CLIP Recall score on MS-COCO Carpathy Test Split. Weights are available at https://huggingface.co/sashakunitsyn/vlrm-blip2-opt-2.7b.