# GoldiCLIP: The Goldilocks Approach for Balancing Explicit Supervision for Language-Image Pretraining

arXiv: https://arxiv.org/abs/2603.24804 · HTML: https://mlsanity.com/paper/2603.24804/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 39 of its 41 references that are in the map.
- First posted on arXiv 25 Mar 2026.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 30 of 39)

- [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)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [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)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [Phi-4 Technical Report](https://mlsanity.com/paper/2412.08905/) (2024)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [GIT: A Generative Image-to-text Transformer for Vision and Language](https://mlsanity.com/paper/2205.14100/) (2022)
- [SLIP: Self-supervision meets Language-Image Pre-training](https://mlsanity.com/paper/2112.12750/) (2021)
- [Scaling Open-Vocabulary Object Detection](https://mlsanity.com/paper/2306.09683/) (2023)
- [Perception Encoder: The best visual embeddings are not at the output of the network](https://mlsanity.com/paper/2504.13181/) (2025)
- [Long-CLIP: Unlocking the Long-Text Capability of CLIP](https://mlsanity.com/paper/2403.15378/) (2024)
- [Demystifying CLIP Data](https://mlsanity.com/paper/2309.16671/) (2023)
- [Improving CLIP Training with Language Rewrites](https://mlsanity.com/paper/2305.20088/) (2023)
- [Scaling Up Vision-Language Pre-training for Image Captioning](https://mlsanity.com/paper/2111.12233/) (2021)
- [DOCCI: Descriptions of Connected and Contrasting Images](https://mlsanity.com/paper/2404.19753/) (2024)
- [A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions](https://mlsanity.com/paper/2312.08578/) (2023)
- [EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters](https://mlsanity.com/paper/2402.04252/) (2024)
- [FG-CLIP: Fine-Grained Visual and Textual Alignment](https://mlsanity.com/paper/2505.05071/) (2025)
- [DreamLIP: Language-Image Pre-training with Long Captions](https://mlsanity.com/paper/2403.17007/) (2024)
- [SILC: Improving Vision Language Pretraining with Self-Distillation](https://mlsanity.com/paper/2310.13355/) (2023)
- [TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives](https://mlsanity.com/paper/2411.02545/) (2024)

## Abstract (arXiv)

Until recently, the success of large-scale vision-language models (VLMs) has primarily relied on billion-sample datasets, posing a significant barrier to progress. Latest works have begun to close this gap by improving supervision quality, but each addresses only a subset of the weaknesses in contrastive pretraining. We present GoldiCLIP, a framework built on a Goldilocks principle of finding the right balance of supervision signals. Our multifaceted training framework synergistically combines three key innovations: (1) a text-conditioned self-distillation method to align both text-agnostic and text-conditioned features; (2) an encoder integrated decoder with Visual Question Answering (VQA) objective that enables the encoder to generalize beyond the caption-like queries; and (3) an uncertainty-based weighting mechanism that automatically balances all heterogeneous losses. Trained on just 30 million images, 300x less data than leading methods, GoldiCLIP achieves state-of-the-art among data-efficient approaches, improving over the best comparable baseline by 2.2 points on MSCOCO retrieval, 2.0 on fine-grained retrieval, and 5.9 on question-based retrieval, while remaining competitive with billion-scale models. Project page: https://petsi.uk/goldiclip.