The paper investigates how vision‑language models acquire and specialize semantic capabilities during fine‑tuning, proposing a trajectory‑based framework that separates acquisition, optima, and specialization phases. It introduces Structured Semantic Routing (SSR) to analyze how supervision representation affects what is learned, showing that SSR improves name‑free attribute‑profile retrieval and that different capabilities peak at different training stages. The study reveals that continued optimization can preserve target‑class retrieval while diminishing transferable semantic knowledge, highlighting a trade‑off between specialization and generalization.
By Suguru Onda, Matthew Bailey, Ryan Farrell
arXiv:2607. 18695v1 Announce Type: cross Abstract: A popular route to interpretable zero-shot classification asks a large language model (LLM) to describe each class name and prompts CLIP with the resulting descriptors.
By Gautam Rajendrakumar Gare, Jia Shi, Zhiqiu Lin, Deepak Pathak, John Galeotti, Deva Ramanan
arXiv:2608.20886v1 Announce Type: cross
Abstract: Real-world image search queries are multimodal and compositional: ``find this shirt in pink'' specifies an entity to retain, an attribute to modify,...
By Enjun Du, Siyi Liu, Zirong Chen, Xinyu Zuo, Jinwen Luo, Ruiwen Tao, Lisheng Duan, Haijin Liang, Jin Ma, Junfu Pu, Yongqi Zhang
VisionQ is a new benchmark for qualitative analysis in computer vision that evaluates vision‑language models (VLMs) on criterion‑conditioned visual discrimination. It is built from over 1,800 peer‑reviewed comparison figures in CVPR and ICCV papers, linking each image crop to author‑stated visual claims through 3,911 hand‑annotated data points. The benchmark includes a 51‑leaf taxonomy of visual criteria, a protocol that hides method identities and reports accuracy per criterion, and a DPO‑tuned Gemma‑4‑E4B judge that improves accuracy on a held‑out test set.
By Vu Dinh Xuan, Duc-Hai Nguyen, Minh-Dung Dao, Vu Quynh Giao, Quang Hong Nguyen, Binh-Son Hua, Barry O'Sullivan, David Murphy, Hoang D. Nguyen
Knowledge-Intensive Visual Question Answering (KI-VQA) benchmarks evaluate Vision-Language Models (VLMs) as multimodal knowledge assistants by requiring external information beyond a provided image to answer questions. KI-VQA involves multiple sub-problems -referring expression understanding, visual grounding, object recognition, knowledge retrieval, and reasoning-yet existing benchmarks typically report only end-task accuracy, obscuring where failures arise.
arXiv:2609.13228v1 Announce Type: new
Abstract: Vision Language Models (VLMs) should rely on visual evidence that directly determines the correct answer, but supervision for grounding visual reasonin...
By Marko Jojic, Zhaonan Li, Ben Zhou
arXiv:2609. 31450v1 Announce Type: cross Abstract: Medical vision-language model (VLM) post-training is commonly evaluated through answer accuracy.
By Wang Jingxin
arXiv:2610.16441v1 Announce Type: cross
Abstract: Current image-text evaluation often relies on a global score, which gives limited insight into which semantic details are supported by the image. Exp...
By Subhadeep Roy, Christoph Leiter, Steffen Eger
arXiv:2608.28316v1 Announce Type: new
Abstract: Static importance scores compress visual evidence into a single ranking, but the value of remaining evidence can change after one cue has been observed...
By Yunxuan Fang, Xinhe Wang
arXiv:2607. 21155v1 Announce Type: cross Abstract: Knowledge-Intensive Visual Question Answering (KI-VQA) benchmarks evaluate Vision-Language Models (VLMs) as multimodal knowledge assistants by requiring external information beyond a provided image to answer questions.
By Hanseok Oh, Parishad BehnamGhader, Benno Krojer, Hyunji Lee, Paul Liang, Siva Reddy, Verna Dankers
The paper demonstrates that vision‑language models (VLMs) possess a small set of attention heads, called Visual Retrieval Heads (VRHs), that are causally responsible for linking text prompts to specific image regions. By adapting head‑scoring techniques from language models, the authors identify VRHs as the heads whose attention from output prediction tokens, summed over the ground‑truth referent region, most reliably indicates causal grounding. Experiments across eleven VLMs and five referring‑expression benchmarks show that masking the top 20 VRHs can drop grounding accuracy by up to 80 percentage points, while random masking has little effect, and that VRHs generalize across diverse visual tasks and transfer across models sharing an LLM backbone.
The paper introduces Visual Retrieval Heads (VRHs), a small fraction of attention heads in vision‑language models that are causally responsible for grounding text descriptions to image regions. By recasting head‑scoring methods and evaluating across eleven VLMs and five benchmarks, the authors show that masking the top 20 VRHs can drop grounding accuracy by up to 80 percentage points, while random masking has little effect. VRHs generalize across various visual reference tasks, preserve output format while corrupting localization, and transfer causally across models sharing an LLM backbone.
By Chanho Park, Daehyeon Choi, Jihyun Lee, Minhyuk Sung