# LAS-CLIP: A Lightweight Adapter Steering Approach for CLIP's Visual Encoder

arXiv: https://arxiv.org/abs/2610.03370 · HTML: https://mlsanity.com/paper/2610.03370/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 34 references that are in the map.
- First posted on arXiv 2 Oct 2026.

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [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)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [RegionCLIP: Region-based Language-Image Pretraining](https://mlsanity.com/paper/2112.09106/) (2021)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing](https://mlsanity.com/paper/2305.14720/) (2023)
- [MAttNet: Modular Attention Network for Referring Expression Comprehension](https://mlsanity.com/paper/1801.08186/) (2018)
- [Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification](https://mlsanity.com/paper/2207.09519/) (2022)
- [What does CLIP know about a red circle? Visual prompt engineering for VLMs](https://mlsanity.com/paper/2304.06712/) (2023)
- [Interpreting CLIP's Image Representation via Text-Based Decomposition](https://mlsanity.com/paper/2310.05916/) (2023)
- [CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models](https://mlsanity.com/paper/2109.11797/) (2021)
- [Alpha-CLIP: A CLIP Model Focusing on Wherever You Want](https://mlsanity.com/paper/2312.03818/) (2023)
- [ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension](https://mlsanity.com/paper/2204.05991/) (2022)
- [Large-scale Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2106.03149/) (2021)
- [FALIP: Visual Prompt as Foveal Attention Boosts CLIP Zero-Shot Performance](https://mlsanity.com/paper/2407.05578/) (2024)

## Abstract (arXiv)

CLIP's visual encoder produces only global image representations, limiting its use in region-level tasks. Existing adaptations rely on visual prompting, input masking, or encoder fine-tuning, each compromising pre-trained representations. We propose LAS-CLIP, a Lightweight Adapter Steering approach that keeps every CLIP parameter frozen. A compact MaskAdapter generates per-head, per-layer attention biases from an input mask and injects them into the frozen self-attention layers, steering attention toward the target region. Crucially, because the backbone remains strictly untouched, LAS-CLIP seamlessly reverts to vanilla CLIP when no mask is provided, preserving its foundational zero-shot capabilities. With approximately 116K to 145K trainable parameters and 100K training samples on two T4 GPUs, LAS-CLIP achieves competitive or superior results compared to Alpha-CLIP on ImageNet-S zero-shot classification and RefCOCO referring expression comprehension, despite the latter fine-tuning its entire encoder on millions of samples. Qualitative analysis further confirms stronger representational fidelity under incorrect masks and in downstream generation.