{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:05:50Z","timestamp":1777889150279,"version":"3.51.4"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-2212182"],"award-info":[{"award-number":["IIS-2212182"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00407","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"4275-4284","source":"Crossref","is-referenced-by-count":0,"title":["Zero-Shot Vision Encoder Grafting via LLM Surrogates"],"prefix":"10.1109","author":[{"given":"Kaiyu","family":"Yue","sequence":"first","affiliation":[{"name":"University of Maryland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vasu","family":"Singla","sequence":"additional","affiliation":[{"name":"University of Maryland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Menglin","family":"Jia","sequence":"additional","affiliation":[{"name":"Meta"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John","family":"Kirchenbauer","sequence":"additional","affiliation":[{"name":"University of Maryland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rifaa","family":"Qadri","sequence":"additional","affiliation":[{"name":"University of Maryland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zikui","family":"Cai","sequence":"additional","affiliation":[{"name":"University of Maryland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhinav","family":"Bhatele","sequence":"additional","affiliation":[{"name":"University of Maryland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Furong","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Maryland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tom","family":"Goldstein","sequence":"additional","affiliation":[{"name":"University of Maryland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Understanding Intermediate Layers Using Linear Classifier Probes","volume-title":"ICLR","author":"Alain","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","article-title":"Eliciting Latent Predictions From Transformers With the Tuned Lens","author":"Belrose","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"ref5","article-title":"GenQA: Generating Millions of Instructions from a Handful of Prompts","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","volume-title":"CVPR","author":"Chen","year":"2024"},{"key":"ref7","article-title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes\/No Questions","volume-title":"ACL Anthology","author":"Clark","year":"2019"},{"key":"ref8","article-title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","author":"Clark","year":"2018","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"The Llama 3 Herd of Models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","author":"Fu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","volume-title":"A Framework for Few-Shot Language Model Evaluation","author":"Gao","year":"2024"},{"key":"ref12","article-title":"The Unreasonable Ineffectiveness of the Deeper Layers","volume-title":"ICLR","author":"Gromov","year":"2025"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.864"},{"key":"ref15","article-title":"Measuring Massive Multitask Language Understanding","author":"Hendrycks","year":"2021","journal-title":"ICLR"},{"key":"ref16","article-title":"LoRA: Low-Rank Adaptation of Large Language Models","volume-title":"ICLR","author":"Hu","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref18","volume-title":"InternVL2: Better than the Best-Expanding Performance Boundaries of Open-Source Multimodal Models with the Progressive Scaling Strategy","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"ref20","article-title":"Propulsion: Steering LLM with Tiny Fine-Tuning","volume-title":"ACL Anthology","author":"Kowsher","year":"2024"},{"key":"ref21","article-title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","volume-title":"CVPR","author":"Li","year":"2024"},{"key":"ref22","volume-title":"LLaVA-Next: Stronger Llms Supercharge Multimodal Capabilities in the Wild","author":"Li","year":"2024"},{"key":"ref23","volume-title":"LMMs-Eval: Accelerating the Development of Large Multimodal Models","author":"Li","year":"2024"},{"key":"ref24","article-title":"LlaVA-OneVision: Easy Visual Task Transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","volume-title":"ICML","author":"Li","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref28","volume-title":"LlaVA-Next: Improved Reasoning, Ocr, and World Knowledge","author":"Liu","year":"2024"},{"key":"ref29","article-title":"Visual Instruction Tuning","volume-title":"NeurIPS","author":"Liu","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"ref34","article-title":"ShortGPT: Layers in Large Language Models are More Redundant Than You Expect","author":"Men","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1260"},{"key":"ref36","volume-title":"interpreting GPT: the logit lens","year":"2020"},{"key":"ref37","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3474381"},{"key":"ref39","article-title":"Open Problems in Mechanistic Interpretability","author":"Sharkey","year":"2025","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Models That Can Read","volume-title":"CVPR","author":"Singh","year":"2019"},{"key":"ref41","article-title":"Transformer Layers as Painters","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","volume-title":"Gemma-2. Kaggle","year":"2024"},{"key":"ref43","volume-title":"Gemma-3. Kaggle","year":"2025"},{"key":"ref44","article-title":"Qwen2.5 Technical Report","year":"2025","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Qwen3 Technical Report","year":"2025","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Cambrian1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","volume-title":"NeurIPS","author":"Tong","year":"2025"},{"key":"ref47","article-title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","author":"Tschannen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Qwen2-VL: Enhancing Vision-Language Model\u2019s Perception of the World at Any Resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"CogVLM: Visual Expert for Pretrained Language Models","volume-title":"NeurIPS","author":"Wang","year":"2024"},{"key":"ref50","article-title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","volume-title":"ICML","author":"Yu","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1472"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.14778\/3611540.3611569"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446144.pdf?arnumber=11446144","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:08:54Z","timestamp":1777612134000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446144\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00407","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}