← Back to all news
arXiv Computer Vision By Bingchen Huang, Zhiling Wang, Yifu Chen, Yuanchao Du

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

Read the original on arXiv Computer Vision →

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.

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.

Related stories

arXiv AI
6d ago

ClueTracer: Question-to-Vision Clue Tracing for Training-Free Hallucination Suppression in Multimodal Reasoning

ClueTracer is a training‑free, parameter‑free plugin that suppresses hallucinations in multimodal reasoning models by tracing how visual clues propagate from the question through the model’s reasoning pathway. It localizes task‑relevant image patches while ignoring irrelevant regions, thereby addressing the problem of reasoning drift where models over‑focus on question‑irrelevant entities. The method improves performance across various reasoning architectures by an average of 1.21× on reasoning benchmarks.

By Gongli Xi, Kun Wang, Zeming Gao, Huahui Yi, Haolang Lu, Qianshan Wei, Ye Tian, Wendong Wang
multimodalbenchmarkssafety
More like this →
arXiv AI
Jun 16

Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings

arXiv:2606. 15134v1 Announce Type: cross Abstract: Vision encoders for retrieval are typically trained with class-label supervision: each training pair reduces to a scalar that uniformly pushes the embedding apart or pulls it together, as if every visual attribute either differed or matched.

By Shubhang Bhatnagar, Dheeraj Baiju, Narendra Ahuja
llmsragefficiencymultimodalbenchmarks
More like this →
arXiv Machine Learning
Oct 9

WOVEN: Weaving Visual World Modeling into Multimodal LLMs

WOVEN is a new training source and benchmark for visual transition reasoning, comprising 36,076 examples across 20 scenes, 5 actions, and 8 reasoning types. The study shows that current multimodal large language models (MLLMs) have a systematic deficit in spatial, embodied, physical, and temporal reasoning, and that training on WOVEN improves performance on 22 of 26 external benchmarks by up to 27.3 percentage points. The authors also provide a training recipe that prioritizes reasoning operations and larger visual changes for robust visual world modeling.

By Zheyu Fan, Yue Zhang, Mingkai Deng, Kangrui Wang, Qineng Wang, Canyu Chen, Jie Hao, Xing Fan, Chenlei Guo, Eric P. Xing, Mohit Bansal, Manling Li
llmsroboticsmultimodalbenchmarks
More like this →