arXiv:2607. 27069v2 Announce Type: cross Abstract: Closed yes/no spatial benchmarks can reward a correct answer even when the image adds little support beyond no-image contexts.
arXiv:2605.31192v2 Announce Type: replace Abstract: Generalizable deepfake detection requires complementary forensic and semantic visual evidence. Specialist encoders capture subtle manipulation trac...
Reinforcement learning with verifiable rewards (RLVR) drives multimodal reasoning, but answer-level correctness does not guarantee that a vision-language model grounds its predictions in visual evidence. Existing visual-intervention methods contrast policy behavior on original and modified images, yet assign supervision by the type of intervention rather than its observed effect.
The paper argues that cross‑view correspondence, commonly used in agent evaluation and trace‑based learning, functions as a measurement intervention. Removing or altering this correspondence can create artificial sensitivity or invariance, and multiple optimal correspondences can obscure mechanism labels and learning credit. The authors propose a validity theory with two‑sided validation, all‑optima identification, and uncertainty propagation, and demonstrate through experiments that unvalidated correspondences can misattribute credit and erase harmful responses.
arXiv:2607. 00491v1 Announce Type: cross Abstract: Benchmarks for vision-language models (VLMs) mostly test observational spatial reasoning: models describe relations already visible in the input.
MR‑IQA‑2 introduces an actor‑editor‑judge framework that separates reasoning from rating in image quality assessment. The actor generates quality reasoning, the editor modifies the image based on identified factors, and a frozen judge compares the original and edited images to provide reflective supervision. Fine‑grained credit assignment allows distinct supervision signals for reasoning and rating, achieving competitive human‑aligned ratings while offering richer, faithful visual understanding.
arXiv:2606. 17710v1 Announce Type: cross Abstract: Medical vision-language models report strong chest radiograph accuracy, and this is increasingly read as evidence that they use the image.
arXiv:2608. 09101v1 Announce Type: cross Abstract: Semantic segmentation models are trained and evaluated against human-drawn masks, yet remote-sensing annotations are often coarse, incomplete, or misaligned; high overlap scores may then reflect agreement with imperfect labels rather than faithfulness to the image, creating an evaluation paradox.
arXiv:2608. 04509v1 Announce Type: new Abstract: Vision-language systems combine images with retrieved text, but these sources can disagree or jointly fail to support an answer.
Large vision-language models can recognize the objects and attributes in a crowded scene yet assign an attribute to the wrong same-class instance. Generic visual-question-answering accuracy marks the...
arXiv:2607. 29240v1 Announce Type: cross Abstract: In vision--language models, commonsense-driven hallucination (CDH) occurs when a model's commonsense prior overrides clear visual evidence of an atypical state.
arXiv:2606. 10066v1 Announce Type: cross Abstract: Medical vision-language models (VLMs) are evaluated on public benchmarks whose images and question-answer pairs have been freely downloadable for years, yet reported accuracy assumes these examples were absent from pretraining.
arXiv:2608. 16805v1 Announce Type: cross Abstract: Large vision-language models can recognize the objects and attributes in a crowded scene yet assign an attribute to the wrong same-class instance.