# AttAnchor: Guiding Cross-Modal Token Alignment in VLMs with Attention Anchors

arXiv: https://arxiv.org/abs/2509.23109 · HTML: https://mlsanity.com/paper/2509.23109/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 46 references that are in the map.
- First posted on arXiv 27 Sep 2025.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [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)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation](https://mlsanity.com/paper/2108.12409/) (2021)
- [VizWiz Grand Challenge: Answering Visual Questions from Blind People](https://mlsanity.com/paper/1802.08218/) (2018)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [NExT-GPT: Any-to-Any Multimodal LLM](https://mlsanity.com/paper/2309.05519/) (2023)
- [HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models](https://mlsanity.com/paper/2310.14566/) (2023)
- [AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation](https://mlsanity.com/paper/2311.07397/) (2023)
- [Think before you speak: Training Language Models With Pause Tokens](https://mlsanity.com/paper/2310.02226/) (2023)
- [OneLLM: One Framework to Align All Modalities with Language](https://mlsanity.com/paper/2312.03700/) (2023)
- [Learning Latent Permutations with Gumbel-Sinkhorn Networks](https://mlsanity.com/paper/1802.08665/) (2018)
- [X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages](https://mlsanity.com/paper/2305.04160/) (2023)
- [A Length-Extrapolatable Transformer](https://mlsanity.com/paper/2212.10554/) (2022)
- [Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning](https://mlsanity.com/paper/2212.04994/) (2022)
- [PuMer: Pruning and Merging Tokens for Efficient Vision Language Models](https://mlsanity.com/paper/2305.17530/) (2023)

## Built on by (most cited first, 1 of 1)

- [ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation](https://mlsanity.com/paper/2607.06565/) (2026)

## Abstract (arXiv)

A fundamental reason for the dominance of attention over RNNs and LSTMs in LLMs is its ability to capture long-range dependencies by modeling direct interactions between all tokens, overcoming the sequential limitations of recurrent architectures. Similarly, a key reason why today's vision language models (VLMs) hallucinate and underperform pure language models is that they rely on direct concatenation of image and text tokens with a modality-blinded positional encoding, which conveniently adopts the pretrained LLM backbone but forces unnecessary long-distance attention between semantically related tokens across modalities. This underscores the urgent need for mechanisms that efficiently enhance token locality and cross-modal alignment. In response, we propose Attention Anchor, a parameter-free framework that efficiently groups semantically similar tokens across modalities, improving cross-modal locality. By inserting text tokens near relevant visual patches, we create semantic signposts that reveal true content-based cross-modal attention scores, guiding the model to focus on the correct image regions for tasks such as VQA, MMBench and POPE. This improves answer accuracy and reduces hallucinations without disrupting the prompt's semantic flow. AttAnchor achieves improvements across 13 out of 15 different metrics and benchmarks, including up to 32% gains on reasoning tasks and up to 15% improvements on hallucination benchmarks. AttAnchor enables TinyLLaVA 1B to outperform much larger models like LLaVA 7B and QwenVL 3B on POPE with only 0.1% inference time overhead. To the best of our knowledge, this work is among the first to investigate mixed-modal token grouping, where text and image tokens are clustered jointly into shared groups rather than being grouped within a single modality or merely aligned post-hoc with additional alignment losses.