arXiv Computer Vision October 12, 2026 By Nadav Alali, Ohad Ben-Shahar

Fix the Match, Not the Solver: STITCH -- a Self-Supervised Compatibility Measure for Eroded Visual Puzzles

Read the original on arXiv Computer Vision →

The paper introduces STITCH, a self‑supervised compatibility measure that replaces traditional boundary‑dependent metrics for solving visual puzzles with eroded fragments. By comparing frozen ViT patch tokens from piece interiors using a lightweight cross‑attention head, STITCH can be plugged into existing solvers and achieves near‑perfect reconstruction on the JPwLEG‑5 benchmark, outperforms prior methods on a new ImageNet 7×7 benchmark, and remains robust across varying erosion levels and high missing‑piece scenarios. The authors demonstrate that improving the matching metric, rather than the solver itself, yields significant performance gains across multiple datasets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

benchmarks

arXiv AI

Aug 5

JigShape: Evaluating Visual-Geometric Reasoning in VLMs through Jigsaw Puzzles

arXiv:2607. 27670v2 Announce Type: replace-cross Abstract: Jigsaw puzzle solving requires jointly reasoning about visual content and geometric constraints, yet existing benchmarks use rectangular cuts that create ambiguous ground truth in texture-repeated regions.

By Shawn Li, Wei Yang, Jike Zhong, Jiate Li, Jiawei Yang, You Qin, Ryan Rossi, Franck Dernoncourt, Roger Zimmermann, Yue Wang, Zhengzhong Tu, Vicente Ordonez, Mohit Bansal, Yue Zhao

llms fine-tuning multimodal benchmarks

arXiv AI

Sep 10

TDDN: Text-aligned Diffused DINO Network for Puzzle Understanding

arXiv:2609.07937v1 Announce Type: cross Abstract: Structured visual reasoning, such as image puzzles, demands fine-grained visual perception, an ability current Vision Language Models (VLMs) lack. VL...

By Harsha Patnala, Debopriyo Banerjee, Ayush Sunil Munot, Somak Aditya

llms computer-vision nlp multimodal benchmarks safety

arXiv Computer Vision

Sep 15

PuzzleMate: Benchmarking MLLMs for Egocentric Puzzle Assistance

arXiv:2609.14473v1 Announce Type: new Abstract: Personal AI assistants hold the potential to evolve from digital interfaces into embodied companions capable of guiding users through complex physical...

By Avijit Dasgupta, Shayon Dasgupta, Zakaria Laskar, C. V. Jawahar, Karteek Alahari

llms robotics multimodal benchmarks

arXiv AI

Jun 4

Revisiting Model Stitching In the Foundation Model Era

arXiv:2603. 12433v3 Announce Type: replace-cross Abstract: Model stitching, connecting early layers of one model (source) to later layers of another (target) via a light stitch layer, has served as a probe of representational compatibility.

By Zheda Mai, Ke Zhang, Fu-En Wang, Zixiao Ken Wang, Albert Y. C. Chen, Lu Xia, Min Sun, Wei-Lun Chao, Cheng-Hao Kuo

llms multimodal

arXiv Computer Vision

Sep 14

Retrieved Images as Visual Thought: Training-Free Multimodal In-Context Learning for the Open-vs-Closed Gap

ReVisIT is a train‑free framework that turns retrieved image‑label pairs into units of visual thought, combining structured class definitions, multimodal retrieval, and alternating user/assistant injection before joint decoding. On several benchmarks—including Fast Open MiniImageNet, Bongard‑OpenWorld, and the newly released MAAC‑Bench—ReVisIT achieves performance comparable to or surpassing large, trained models while using far fewer parameters. The approach demonstrates that high‑quality retrieval and a simple turns layer can provide a universal performance boost across diverse multimodal tasks.

By Bingchen Huang, Zhiling Wang, Yifu Chen, Yuanchao Du

llms multimodal benchmarks

arXiv AI

Jun 16

Tool-IQA: Augmenting Image Quality Assessment with Simple Tools

arXiv:2606. 16082v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have been increasingly adopted for Image Quality Assessment (IQA).

By Guanyi Qin, Junjie Zhang, Chunming He, Yibing Fu, Jie Liang, Tianhe Wu, Lei Zhang

llms agents multimodal benchmarks

One email a morning, machine-written

Related stories

JigShape: Evaluating Visual-Geometric Reasoning in VLMs through Jigsaw Puzzles

TDDN: Text-aligned Diffused DINO Network for Puzzle Understanding

PuzzleMate: Benchmarking MLLMs for Egocentric Puzzle Assistance

Revisiting Model Stitching In the Foundation Model Era

Retrieved Images as Visual Thought: Training-Free Multimodal In-Context Learning for the Open-vs-Closed Gap

Tool-IQA: Augmenting Image Quality Assessment with Simple Tools