# Fewer Tokens, Greater Scaling: Self-Adaptive Visual Bases for Efficient and Expansive Representation Learning

arXiv: https://arxiv.org/abs/2511.19515 · HTML: https://mlsanity.com/paper/2511.19515/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 56 references that are in the map.
- First posted on arXiv 24 Nov 2025.

## Builds on (most cited first, 30 of 43)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [Dense Contrastive Learning for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2011.09157/) (2020)
- [Masked Siamese Networks for Label-Efficient Learning](https://mlsanity.com/paper/2204.07141/) (2022)
- [SSD: A Unified Framework for Self-Supervised Outlier Detection](https://mlsanity.com/paper/2103.12051/) (2021)
- [Large Language Models as Commonsense Knowledge for Large-Scale Task Planning](https://mlsanity.com/paper/2305.14078/) (2023)
- [Proxy Anchor Loss for Deep Metric Learning](https://mlsanity.com/paper/2003.13911/) (2020)
- [Contrastive Training for Improved Out-of-Distribution Detection](https://mlsanity.com/paper/2007.05566/) (2020)
- [Adaptive Token Sampling For Efficient Vision Transformers](https://mlsanity.com/paper/2111.15667/) (2021)
- [Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer](https://mlsanity.com/paper/2108.01390/) (2021)
- [How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?](https://mlsanity.com/paper/2203.04450/) (2022)
- [Token Fusion: Bridging the Gap between Token Pruning and Token Merging](https://mlsanity.com/paper/2312.01026/) (2023)
- [Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design](https://mlsanity.com/paper/2305.13035/) (2023)
- [Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers](https://mlsanity.com/paper/2304.10716/) (2023)
- [Siamese Image Modeling for Self-Supervised Vision Representation Learning](https://mlsanity.com/paper/2206.01204/) (2022)
- [Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic](https://mlsanity.com/paper/2404.07177/) (2024)
- [When Do We Not Need Larger Vision Models?](https://mlsanity.com/paper/2403.13043/) (2024)
- [Which Tokens to Use? Investigating Token Reduction in Vision Transformers](https://mlsanity.com/paper/2308.04657/) (2023)
- [MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers](https://mlsanity.com/paper/2205.13137/) (2022)
- [Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers](https://mlsanity.com/paper/2211.11315/) (2022)

## Built on by (most cited first, 16 of 16)

- [TC-SSA: Token Compression via Semantic Slot Aggregation for Gigapixel Pathology Reasoning](https://mlsanity.com/paper/2603.01143/) (2026)
- [The Model Knows Which Tokens Matter: Automatic Token Selection via Noise Gating](https://mlsanity.com/paper/2603.07135/) (2026)
- [Efficient Chest X-ray Representation Learning via Semantic-Partitioned Contrastive Learning](https://mlsanity.com/paper/2603.07113/) (2026)
- [Beyond Surrogate Gradients: Fully Differentiable Token Pruning for Vision-Language Models](https://mlsanity.com/paper/2605.28051/) (2026)
- [Multimodal Model for Computational Pathology:Representation Learning and Image Compression](https://mlsanity.com/paper/2603.18660/) (2026)
- [A unified multi-task framework enables interpretable chest radiograph analysis](https://mlsanity.com/paper/2606.03417/) (2026)
- [XrayClaw: Cooperative-Competitive Multi-Agent Alignment for Trustworthy Chest X-ray Diagnosis](https://mlsanity.com/paper/2604.02695/) (2026)
- [Stepwise Token Selection for Efficient Multimodal Large Language Models](https://mlsanity.com/paper/2606.16067/) (2026)
- [Learnable Token Sparsification for Efficient Gigapixel Whole Slide Image Reasoning](https://mlsanity.com/paper/2606.08641/) (2026)
- [Towards Robust Endogenous Reasoning: Unifying Drift Adaptation in Non-Stationary Tuning](https://mlsanity.com/paper/2604.15705/) (2026)
- [PathSelect: Sequential Token Selection for Whole Slide Pathology](https://mlsanity.com/paper/2607.23631/) (2026)
- [Decoupling semantics from vision: A framework for faithful visual-text compression evaluation](https://mlsanity.com/paper/2608.01848/) (2026)
- [DiffPrune: differentiable information throttling for token pruning in vision-language models](https://mlsanity.com/paper/2608.01985/) (2026)
- [From Snapshots to Symphonies: The Evolution of Protein Prediction from Static Structures to Generative Dynamics and Multimodal Interactions](https://mlsanity.com/paper/2603.18505/) (2026)
- [Autonomous Drift Learning in Data Streams: A Unified Perspective](https://mlsanity.com/paper/2605.01295/) (2026)
- [StepPrune: Adaptive Sequential Visual Token Selection across Multimodal Large Language Models](https://mlsanity.com/paper/2609.13804/) (2026)

## Abstract (arXiv)

This paper investigates the fundamental relationship between model capacity and the minimal number of visual tokens required to preserve image semantics. Inspired by the Minimum Description Length principle, we reinterpret image tokens as vectors in a visual semantic space and define the intrinsic semantic complexity of an image as the smallest set of basis vectors needed to span this space. Building on this perspective, we propose Orthogonal Filtering, a lightweight module that adaptively clusters redundant tokens into a compact set of orthogonal bases. Through extensive experiments across a range of ViT models, we reveal a consistent token, model scaling law: larger models require significantly fewer tokens to span visual semantic space. Besides, we also contribute a visual long-context dataset.