The paper introduces the Detection Surface, a geometric framework that maps the decision boundaries of heterogeneous safety filters in text‑to‑image models. Using this insight, the authors propose CRACK, a multi‑agent debate system that iteratively mutates prompts, diagnoses layer‑specific constraints, and refines attacks to bypass composite defenses. Experiments demonstrate that CRACK can achieve attack success rates up to 99.63% while using fewer queries and preserving semantic fidelity.
By Kaiyan Wen, Shijie Zhang, Lu Yu, Guangdong Bai
The paper introduces a cross‑modal pseudo‑labeling pipeline for unsupervised domain adaptation in semantic segmentation, particularly for waste sorting. It combines SAM for class‑agnostic region proposals with EVA‑CLIP to assign semantic labels via region‑text similarity, applying confidence filtering to ensure reliable pseudo‑labels for self‑training. An optional BLIP‑based language‑grounded verification further refines ambiguous regions, and the method shows consistent improvements over source‑only baselines on synthetic‑to‑real driving and lab‑to‑factory waste sorting shifts.
By Udo Schlegel, Shubhangi, Gabriel Dax, Sai Rahul Kaminwar, Florian Karl, Thomas Seidl
arXiv:2510.23508v4 Announce Type: replace
Abstract: Existing real-world datasets for multimodal fact-checking have multiple limitations: they contain few instances, cover only one or two languages, f...
By Jiahui Geng, Jonathan Tonglet, Iryna Gurevych
arXiv:2609.00746v1 Announce Type: new
Abstract: Fine-tuning a pretrained LLM into a vision-language model (VLM) can erode the backbone's text capability, with the damage concentrated on tasks that re...
By Minsik Choi, Geewook Kim, Young Geun Kim
The paper proposes a method called Restrict, Don't Retrain that enhances zero-shot aerial segmentation by using inference-time guidance from a vision‑language model (VLM). It combines a frozen foundation model that labels every pixel with two VLM queries: one to select relevant classes and another to locate small objects missed by the base model. Experiments on four aerial datasets show consistent performance gains at each stage where the base model is competent.
By Teresa DiMeola, Charles Walter, Hong Xiao
arXiv:2609.01409v1 Announce Type: new
Abstract: Vision-language models (VLMs) have shown strong performance in generating scientific figures from text or images. However, producing publication-ready...
By Christian Greisinger, Zhixue Zhao, Steffen Eger
The paper introduces WM‑RMoE, a World Model‑based Risk‑aware Mixture‑of‑Experts framework for autonomous overtaking. It uses a learned latent dynamics model to perform multi‑step rollouts, evaluating cumulative risk at the trajectory level, and employs a hierarchical gating mechanism to coordinate long‑, short‑horizon, and rule‑based safety experts. A Gaussian Mixture Model preserves multimodal maneuver branches, improving robustness and preventing behavioral averaging, leading to better safety compliance, decision stability, and generalization in experiments.
By Yongzhi Liu, Sunan Zhang, Jinchang Xu, Jiawei Wang, Yushu Qiu, Chen Lv, Weichao Zhuang
arXiv:2609.00377v1 Announce Type: cross
Abstract: We present FoldingAgent, an agentic framework for inferring explicit parametric folding programs directly from origami demonstration videos. Our fram...
By Maya Moriya, Sigal Raab, Yael Vinker, Tali Dekel
arXiv:2609.00443v1 Announce Type: cross
Abstract: Language models learn about grammatical number primarily from co-occurrence, and show frequency effects as a result---sometimes taken to indicate tha...
By Zach Studdiford, Kanishka Misra
arXiv:2609.00866v1 Announce Type: cross
Abstract: The rapid advancement of vision-language models (VLMs) has accelerated progress in computational pathology; however, whole-slide image (WSI)-based pa...
By Yumi Lee, Harim Oh, Hyoryung Kim, Minji Kim, Eunsu Kim, Hyeseong Lee, Junya Fukuoka, Andrey Bychkov, Jijgee Munkhdelger, Rajiv Kumar Kaushal, Ayushi Sahay, Rajni Yadav, Bharathi Prabakaran, Sulen Sarioglu, Serdar Balc{\i}, Ilknur Turkmen, Yuri Tolkach, Christian Harder, Julian Westerdorf, Reinhard Buettner, Audun Ljone Henriksen, Sepp De Raedt, Byung Hyun Lee, Sungjin Lim, Joohoon Lee, Gwanghyun Kim, Se Young Chun, Suryakant Singh, Saarthak Kapse, Prateek Prasanna, Kyung A Kim, Yousun Kang, Sehwan Yoo, Sungman Hong, Shubham Innani, Michael Feldman, Spyridon Bakas, Ujjwal Baid, Prasad Dutande, Suhas Gajare, Bhakti Baheti, Serkan S\"okmen, Ece Tu\u{g}ba Cebeci, Ahmet Hal{\i}c{\i}, Musa Balc{\i}, Kardelen Pe\c{c}enek, Srividhya Sainath, Kyongseok Jang, Messi H. J. Lee, Noorul Wahab, Bodong Du, Jiaming Zhang, Qixiang Zhang, Jang-Hwan Choi, Sangjeong Ahn
arXiv:2505.13180v3 Announce Type: replace
Abstract: Integrating Large Language Models with symbolic planners is a promising direction for obtaining verifiable and grounded plans, with recent works ex...
By Matteo Merler, Nicola Dainese, Minttu Alakuijala, Giovanni Bonetta, Pietro Ferrazzi, Yu Tian, Bernardo Magnini, Pekka Marttinen
arXiv:2609.01147v1 Announce Type: cross
Abstract: Text-rich visual inputs require models that can read, retrieve, and compress language directly in pixel space, yet existing pixel-text encoders strug...
By Chaohao Yuan, Ruifeng Yuan, Zhuoxu Huang, Yu Rong, Hong Cheng, Hou Pong Chan, Chenghao Xiao
arXiv:2609.01059v1 Announce Type: new
Abstract: As Vision-Language Models (VLMs) tackle dynamic 3D spatial reasoning, ego-motion perception becomes essential to resolve monocular scale ambiguity. How...
By Jiayu Ding, Zhuodong Liu, Lei Zhang, Manyu Xiong, Hongbo Jin, Haoran Tang, Hongbo Zhang, Changen Zhu, Wenbo Xing
arXiv:2609.01200v1 Announce Type: new
Abstract: When the visual encoder and the language decoder of a vision-language model (VLM) run on different compute nodes, the intermediate visual-token embeddi...
By Reza Heidari, Hamed R. Tavakoli, Juho Kannala
The paper introduces a top‑down approach for multi‑person 3D reconstruction from multiple views, using a unified, instance‑centric human‑aware 3D space. Observations from different cameras are lifted into this shared space where geometry, appearance, and semantic cues are jointly encoded, and a spatial contrastive learning strategy aligns features of the same person across views while separating different individuals. The method then regresses SMPL parameters from 3D tokens in a feed‑forward manner, achieving robust, accurate, and efficient reconstruction even under severe occlusions.
By Yuanwang Yang, Buzhen Huang, Zongxuan Ren, Jing Huang, Kun Li
arXiv:2605.12413v4 Announce Type: replace
Abstract: Multimodal Large Language Models (MLLMs) show strong visual perception, yet remain limited in reasoning about space under changing viewpoints. We s...
By Yuangong Chen, Wai Keung Wong, Jiaxing Li, Ioannis Patras, Xu Zheng
The paper introduces Pref‑MH, an exact Metropolis‑Hastings sampler that uses only stochastic binary pairwise comparisons from judges to sample from distributions conditioned on desired semantic properties. By linking the MH density ratio to the preference odds of the Bradley‑Terry model, the authors devise an accept/reject rule that guarantees convergence to the target distribution. Experiments on text, molecular, and image generation with large‑language‑model and vision‑language‑model judges show Pref‑MH as a practical, flexible method for conditional sampling when comparative feedback is readily available.
By Ariel Smogorghevski, Nir Rosenfeld, Yaniv Romano
arXiv:2609.00712v1 Announce Type: new
Abstract: Landslides are widespread geological hazards, yet their automated detection and mapping in remote sensing imagery remain challenging because of their i...
By Yuanchao Su, Lianru Gao, Mengying Jiang, Jiangyi Chen, Jiaxin Cheng, Yicong Zhou
arXiv:2609.00663v1 Announce Type: new
Abstract: Multimodal evaluations cannot say whether a vision-language model misread an image or misreasoned about it, because every existing method for separatin...
By Can Polat, Mustafa Kurban, Erchin Serpedin, Hasan Kurban
SCAFFOLD is a large-scale structured dataset of computer science research figures, each paired with captions, context, questions, answers, and chain-of-thought reasoning traces. It contains 157,387 figure–question pairs from 3,058 arXiv papers, with subsets of 36,797 and 12,000 pairs for medium and small-scale use. The dataset was created using layout detection, PDF parsing, and AI-assisted question generation, and was used to benchmark a vision‑language model (Qwen2.5‑VL‑3B‑Instruct).
By Ranjit Raut, Aarav Subedi, Sagun Rai, Sudan Jha