# TDDN: Text-aligned Diffused DINO Network for Puzzle Understanding

arXiv: https://arxiv.org/abs/2609.07937 · HTML: https://mlsanity.com/paper/2609.07937/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 25 of its 49 references that are in the map.
- First posted on arXiv 7 Sep 2026.

## Placed in

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

## Builds on (most cited first, 25 of 25)

- [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)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2401.06209/) (2024)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence](https://mlsanity.com/paper/2305.15347/) (2023)
- [RAVEN: A Dataset for Relational and Analogical Visual rEasoNing](https://mlsanity.com/paper/1903.02741/) (2019)
- [LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models](https://mlsanity.com/paper/2306.09265/) (2023)
- [SPair-71k: A Large-scale Benchmark for Semantic Correspondence](https://mlsanity.com/paper/1908.10543/) (2019)
- [Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs](https://mlsanity.com/paper/2212.00785/) (2022)
- [LaViDa: A Large Diffusion Language Model for Multimodal Understanding](https://mlsanity.com/paper/2505.16839/) (2025)
- [DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment](https://mlsanity.com/paper/2412.16334/) (2024)
- [Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Training](https://mlsanity.com/paper/2403.02325/) (2024)
- [TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives](https://mlsanity.com/paper/2411.02545/) (2024)
- [DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception](https://mlsanity.com/paper/2405.15232/) (2024)
- [Revisiting a kNN-based Image Classification System with High-capacity Storage](https://mlsanity.com/paper/2204.01186/) (2022)
- [FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model](https://mlsanity.com/paper/2510.10921/) (2025)

## Abstract (arXiv)

Structured visual reasoning, such as image puzzles, demands fine-grained visual perception, which current Vision Language Models (VLMs) often lack. VLMs built on CLIP-based ViT backbones tend to trade fine-grained visual details for high-level semantics. We show that this deficit propagates downstream, affecting various vision and language tasks. To address this, we fuse DINOv3 and CleanDIFT representations into a perception encoder (DiffusedDINO), and align it with RoBERTa-L, yielding a text-aligned model (TDDN) that preserves this perceptual advantage: with frozen backbones and only ~590K alignment pairs, TDDN surpasses CLIP ViT-L/14 in image-text retrieval tasks: text-to-image on Flickr30K and both directions on MS-COCO-2014. TDDN more than triples CLIP's dense-prediction accuracy (ADE20K 5.20 -> 18.11 mIoU, COCO-Stuff 7.35 -> 24.44), despite CLIP's massive training corpus. TDDN leads on segmentation benchmarks among general-purpose contrastive encoders, including SigLIP 2. We further introduce PuzzlePerception, a segmentation and visual question answering dataset that probes fine-grained spatial understanding, on which TDDN doubles CLIP's segmentation accuracy (11.04 -> 22.51 mIoU). Our code and data are available at https://github.com/adityaSomak/TDDN.