# Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment

arXiv: https://arxiv.org/abs/2405.17871 · HTML: https://mlsanity.com/paper/2405.17871/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 66 of its 77 references that are in the map.
- First posted on arXiv 28 May 2024.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Builds on (most cited first, 30 of 66)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)
- [SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension](https://mlsanity.com/paper/2307.16125/) (2023)
- [Are We on the Right Way for Evaluating Large Vision-Language Models?](https://mlsanity.com/paper/2403.20330/) (2024)

## Built on by (most cited first, 20 of 20)

- [MLLM Is a Strong Reranker: Advancing Multimodal Retrieval-augmented Generation via Knowledge-enhanced Reranking and Noise-injected Training](https://mlsanity.com/paper/2407.21439/) (2024)
- [ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2411.15268/) (2024)
- [Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation](https://mlsanity.com/paper/2503.19622/) (2025)
- [LanP: Rethinking the Impact of Language Priors in Large Vision-Language Models](https://mlsanity.com/paper/2502.12359/) (2025)
- [LLM-RG4: Flexible and Factual Radiology Report Generation across Diverse Input Contexts](https://mlsanity.com/paper/2412.12001/) (2024)
- [OmChat: A Recipe to Train Multimodal Language Models with Strong Long Context and Video Understanding](https://mlsanity.com/paper/2407.04923/) (2024)
- [OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucination](https://mlsanity.com/paper/2509.00723/) (2025)
- [TG-LLaVA: Text Guided LLaVA via Learnable Latent Embeddings](https://mlsanity.com/paper/2409.09564/) (2024)
- [ProxyThinker: Test-Time Guidance through Small Visual Reasoners](https://mlsanity.com/paper/2505.24872/) (2025)
- [TARAC: Mitigating Hallucination in LVLMs via Temporal Attention Real-time Accumulative Connection](https://mlsanity.com/paper/2504.04099/) (2025)
- [SAILViT: Towards Robust and Generalizable Visual Backbones for MLLMs via Gradual Feature Refinement](https://mlsanity.com/paper/2507.01643/) (2025)
- [MoIIE: Mixture of Intra- and Inter-Modality Experts for Large Vision Language Models](https://mlsanity.com/paper/2508.09779/) (2025)
- [AsyMoE: Leveraging Modal Asymmetry for Enhanced Expert Specialization in Large Vision-Language Models](https://mlsanity.com/paper/2509.12715/) (2025)
- [Knowledge Transfer from Interaction Learning](https://mlsanity.com/paper/2509.18733/) (2025)
- [SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification](https://mlsanity.com/paper/2602.13600/) (2026)
- [Decoupled Proxy Alignment: Mitigating Language Prior Conflict for Multimodal Alignment in MLLM](https://mlsanity.com/paper/2509.14735/) (2025)
- [SVAC: Scaling Is All You Need For Referring Video Object Segmentation](https://mlsanity.com/paper/2509.24109/) (2025)
- [Towards Accurate UAV Image Perception: Guiding Vision-Language Models with Stronger Task Prompts](https://mlsanity.com/paper/2512.07302/) (2025)
- [Seeing Right but Saying Wrong: Inter- and Intra-Layer Refinement in MLLMs without Training](https://mlsanity.com/paper/2601.07359/) (2026)
- [CUSE: Fine-Grained Multimodal Unlearning with Counterfactual Guidance and On-Policy Self-Distillation](https://mlsanity.com/paper/2610.14763/) (2026)

## Abstract (arXiv)

Existing image-text modality alignment in Vision Language Models (VLMs) treats each text token equally in an autoregressive manner. Despite being simple and effective, this method results in sub-optimal cross-modal alignment by over-emphasizing the text tokens that are less correlated with or even contradictory with the input images. In this paper, we advocate for assigning distinct contributions for each text token based on its visual correlation. Specifically, we present by contrasting image inputs, the difference in prediction logits on each text token provides strong guidance of visual correlation. We therefore introduce Contrastive ALignment (CAL), a simple yet effective re-weighting strategy that prioritizes training visually correlated tokens. Our experimental results demonstrate that CAL consistently improves different types of VLMs across different resolutions and model sizes on various benchmark datasets. Importantly, our method incurs minimal additional computational overhead, rendering it highly efficient compared to alternative data scaling strategies. Codes are available at https://github.com/foundation-multimodal-models/CAL.