arXiv:2602. 07025v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) exhibit puzzling failures in multi-object visual tasks, such as hallucinating non-existent elements or failing to identify the most similar objects among distractions.
By Daniele Savietto, Declan Campbell, Andr\'e Panisson, Marco Nurisso, Giovanni Petri, Jonathan D. Cohen, Alan Perotti
arXiv:2609.18345v1 Announce Type: new
Abstract: Large vision-language models (LVLMs) are commonly used with only a single text prompt as the input, or plus an image. In this paper, we demonstrate tha...
By Xiaomeng Wang, Martha Larson, Zhengyu Zhao
The paper investigates how vision‑language models resolve conflicts between visual evidence and memorized knowledge. Using activation patching and ablation across residual streams, attention heads, and MLP sublayers, the authors find that visual grounding is the default behavior, while prior knowledge relies on a small, causally essential set of attention heads concentrated in the network’s second half. Ablating these heads flips knowledge‑grounded predictions to visually grounded ones in most cases, revealing an asymmetric causal structure and a sparse circuit of routing and writing heads that underlies perception‑knowledge conflict.
By Niclas Lietzow, Danielle Bitterman, Carsten Eickhoff, William Rudman, Michal Golovanevsky
The paper investigates how vision‑language models (VLMs) resolve conflicts between image features using a Stroop‑style benchmark. By prompting contrastive and generative VLMs on images where text and color disagree, the authors find a consistent bias toward textual cues, with models preferring to respond based on text rather than color. Analysis of the embedding space reveals that textual signals are represented more strongly and separably than color signals, explaining why steering models toward text is easier than toward color.
By Nurb\"uke Teker, Rui Xiao, Zeynep Akata, Shuchen Wu
arXiv:2608. 14286v1 Announce Type: cross Abstract: Vision language models (VLMs) are increasingly used in industrial decision-making systems, such as recruitment support and recommendation.
By Kohsuke Ide, Ryousuke Yamada, Yoshihiro Fukuhara, Hirokatsu Kataoka, Yutaka Satoh
arXiv:2602. 02465v2 Announce Type: replace Abstract: Frontier models are transitioning from multimodal large language models (MLLMs) that merely ingest visual information to unified multimodal models (UMMs) capable of native interleaved generation.
By Jana Zeller, Thadd\"aus Wiedemer, Fanfei Li, Thomas Klein, Prasanna Mayilvahanan, Matthias Bethge, Felix Wichmann, Ryan Cotterell, Wieland Brendel