@article{bb236700,
AUTHOR = "Yao, H.T. and Zhang, R. and Lyu, H.H. and Zhang, Y.D. and Xu, C.S.",
TITLE = "Bi-Modality Individual-Aware Prompt Tuning for Visual-Language Model",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "8",
MONTH = "August",
PAGES = "6352-6368",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231666"}
@inproceedings{bb236701,
AUTHOR = "Yao, H.T. and Zhang, R. and Xu, C.S.",
TITLE = "TCP: Textual-Based Class-Aware Prompt Tuning for Visual-Language
Model",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "23438-23448",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231667"}
@article{bb236702,
AUTHOR = "Hao, Z.W. and Guo, J.Y. and Shen, L. and Luo, Y. and Hu, H. and Wen, Y.G.",
TITLE = "ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language
Tuning",
JOURNAL = IJCV,
VOLUME = "133",
YEAR = "2025",
NUMBER = "8",
MONTH = "August",
PAGES = "5527-5543",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231668"}
@article{bb236703,
AUTHOR = "Zeng, R.F. and Yang, Z.P. and Yu, R.Y. and Zhang, Y.G.",
TITLE = "Supplementary Prompt Learning for Vision-Language Models",
JOURNAL = IJCV,
VOLUME = "133",
YEAR = "2025",
NUMBER = "8",
MONTH = "August",
PAGES = "5822-5839",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231669"}
@article{bb236704,
AUTHOR = "Liu, K.C. and Liu, Y.J. and Chen, B.Q.",
TITLE = "General 3D Vision-Language Model With Fast Rendering and Pre-Training
Vision-Language Alignment",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "9",
MONTH = "September",
PAGES = "7352-7368",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231670"}
@article{bb236705,
AUTHOR = "Gao, Y.S. and Zhu, Z.X. and Wang, S.S.",
TITLE = "Mixture of coarse and fine-grained prompt tuning for vision-language
model",
JOURNAL = PR,
VOLUME = "170",
YEAR = "2026",
PAGES = "112074",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231671"}
@article{bb236706,
AUTHOR = "Hao, F.S. and Liu, L. and Wu, F.X. and Zhang, Q.S. and Cheng, J.",
TITLE = "Textual Embeddings are Good Class-Aware Visual Prompts for Adapting
Vision-Language Models",
JOURNAL = SPLetters,
VOLUME = "32",
YEAR = "2025",
PAGES = "2992-2996",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231672"}
@article{bb236707,
AUTHOR = "Liu, J. and Lu, Z.Q. and Luo, H. and Lu, Z.M. and Zheng, Y.M.",
TITLE = "Progressive Multi-Prompt Learning for Vision-Language Models",
JOURNAL = CirSysVideo,
VOLUME = "35",
YEAR = "2025",
NUMBER = "10",
MONTH = "October",
PAGES = "9562-9574",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231673"}
@article{bb236708,
AUTHOR = "Zhang, E. and Zhu, B. and Chen, Y.Y. and Miao, Q.H. and Tang, M. and Wang, J.Q.",
TITLE = "Optimization of Prompt Learning via Multi-Knowledge Representation
for Vision-Language Models",
JOURNAL = MultMed,
VOLUME = "27",
YEAR = "2025",
PAGES = "7557-7569",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231674"}
@article{bb236709,
AUTHOR = "Park, K.Y. and An, S. and Lee, Y.J. and Kim, D.H.",
TITLE = "Learning Compositionality from Multifaceted Synthetic Data for
Language-based Object Detection",
JOURNAL = IJCV,
VOLUME = "133",
YEAR = "2025",
NUMBER = "1",
MONTH = "January",
PAGES = "7873-7896",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231675"}
@inproceedings{bb236710,
AUTHOR = "Park, K.Y. and Saito, K. and Kim, D.H.",
TITLE = "Weak-to-strong Compositional Learning from Generative Models for
Language-based Object Detection",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXIII: 1-19",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231676"}
@article{bb236711,
AUTHOR = "Sarto, S. and Moratelli, N. and Cornia, M. and Baraldi, L. and Cucchiara, R.",
TITLE = "Positive-Augmented Contrastive Learning for Vision-and-Language
Evaluation and Training",
JOURNAL = IJCV,
VOLUME = "133",
YEAR = "2025",
NUMBER = "1",
MONTH = "January",
PAGES = "7647-7671",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231677"}
@inproceedings{bb236712,
AUTHOR = "Stefanini, M. and Cornia, M. and Baraldi, L. and Cucchiara, R.",
TITLE = "A Novel Attention-based Aggregation Function to Combine Vision and
Language",
BOOKTITLE = ICPR21,
YEAR = "2021",
PAGES = "1212-1219",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231678"}
@article{bb236713,
AUTHOR = "Liu, L.C. and Wang, N.N. and Chen, C. and Liu, D. and Yang, X. and Gao, X.B. and Liu, T.L.",
TITLE = "Frequency-Based Comprehensive Prompt Learning for Vision-Language
Models",
JOURNAL = PAMI,
VOLUME = "47",
YEAR = "2025",
NUMBER = "12",
MONTH = "December",
PAGES = "11974-11989",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231679"}
@inproceedings{bb236714,
AUTHOR = "Ma, Z.Y. and Gou, C. and Shi, H. and Sun, B. and Li, S.T. and Rezatofighi, H. and Cai, J.F.",
TITLE = "DrVideo: Document Retrieval Based Long Video Understanding",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "18936-18946",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231680"}
@inproceedings{bb236715,
AUTHOR = "Dhouib, M. and Buscaldi, D. and Vanier, S. and Shabou, A.",
TITLE = "PACT: Pruning and Clustering-Based Token Reduction for Faster Visual
Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "14582-14592",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231681"}
@inproceedings{bb236716,
AUTHOR = "Xie, P. and Bie, Y. and Mao, J. and Song, Y.Q. and Wang, Y. and Chen, H. and Chen, K.",
TITLE = "Chain of Attack: On the Robustness of Vision-Language Models Against
Transfer-Based Adversarial Attacks",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "14679-14689",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231682"}
@inproceedings{bb236717,
AUTHOR = "Yu, C. and Chen, T. and Gan, Z.X.",
TITLE = "Once-Tuning-Multiple-Variants: Tuning Once and Expanded as Multiple
Vision-Language Model Variants",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "14712-14722",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231683"}
@inproceedings{bb236718,
AUTHOR = "Hao, F.S. and He, F.X. and Wu, F. and Wang, T. and Song, C.Q. and Cheng, J.",
TITLE = "Task-Aware Clustering for Prompting Vision-Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "14745-14755",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231684"}
@inproceedings{bb236719,
AUTHOR = "Koleilat, T. and Asgariandehkordi, H. and Rivaz, H. and Xiao, Y.M.",
TITLE = "BiomedCoOp: Learning to Prompt for Biomedical Vision-Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "14766-14776",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231685"}
@inproceedings{bb236720,
AUTHOR = "Nath, V. and Li, W.Q. and Yang, D. and Myronenko, A. and Zheng, M.X. and Lu, Y. and Liu, Z.J. and Yin, H.X. and Law, Y.M. and Tang, Y.C. and Guo, P.F. and Zhao, C. and Xu, Z.Y. and He, Y.F. and Harmon, S. and Simon, B. and Heinrich, G. and Aylward, S. and Edgar, M. and Zephyr, M. and Molchanov, P. and Turkbey, B. and Roth, H. and Xu, D.",
TITLE = "VILA-M3: Enhancing Vision-Language Models with Medical Expert
Knowledge",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "14788-14798",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231686"}
@inproceedings{bb236721,
AUTHOR = "Du, H. and Wu, B. and Lu, Y. and Mao, Z.D.",
TITLE = "SVLTA: Benchmarking Vision-Language Temporal Alignment via Synthetic
Video Situation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "13798-13809",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231687"}
@inproceedings{bb236722,
AUTHOR = "Kaduri, O. and Bagon, S. and Dekel, T.",
TITLE = "What's in the Image? A Deep-Dive into the Vision of Vision Language
Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "14549-14558",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231688"}
@inproceedings{bb236723,
AUTHOR = "Xing, L. and Huang, Q.D. and Dong, X.Y. and Lu, J.J. and Zhang, P. and Zang, Y.H. and Cao, Y.H. and He, C.H. and Wang, J.Q. and Wu, F. and Lin, D.",
TITLE = "Conical Visual Concentration for Efficient Large Vision-Language
Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "14593-14603",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231689"}
@inproceedings{bb236724,
AUTHOR = "Zhang, L. and Yang, Q. and Agrawal, A.",
TITLE = "Assessing and Learning Alignment of Unimodal Vision and Language
Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "14604-14614",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231690"}
@inproceedings{bb236725,
AUTHOR = "Sehgal, A. and Yuan, P. and Hu, Z. and Yue, Y.S. and Sun, J.J. and Chaudhuri, S.",
TITLE = "Self-Evolving Visual Concept Library using Vision-Language Critics",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "13124-13134",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231691"}
@inproceedings{bb236726,
AUTHOR = "Wang, W.H. and Wang, L. and Gu, X.T. and Huang, S.Y. and Dong, Y.X. and Tang, J.",
TITLE = "MotionBench: Benchmarking and Improving Fine-Grained Video Motion
Understanding for Vision Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "8450-8460",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231692"}
@inproceedings{bb236727,
AUTHOR = "Nacson, M.S. and Aberdam, A. and Ganz, R. and Avraham, E.B. and Golts, A. and Kittenplon, Y. and Mazor, S. and Litman, R.",
TITLE = "DocVLM: Make Your VLM an Efficient Reader",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29005-29015",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231693"}
@inproceedings{bb236728,
AUTHOR = "Alhamoud, K. and Alshammari, S. and Tian, Y.L. and Li, G.H. and Torr, P.H.S. and Kim, Y. and Ghassemi, M.",
TITLE = "Vision-Language Models Do Not Understand Negation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29612-29622",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231694"}
@inproceedings{bb236729,
AUTHOR = "Schmalfuss, J. and Chang, N. and VS, V. and Shen, M. and Bruhn, A. and Alvarez, J.M.",
TITLE = "PARC: A Quantitative Framework Uncovering the Symmetries within
Vision Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "25081-25091",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231695"}
@inproceedings{bb236730,
AUTHOR = "Xiao, J.Q. and Sang, S. and Zhi, T.C. and Liu, J. and Yan, Q. and Luo, L.J. and Yuan, B.",
TITLE = "COAP: Memory-Efficient Training with Correlation-Aware Gradient
Projection",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "30116-30126",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231696"}
@inproceedings{bb236731,
AUTHOR = "Zhu, Y.Q. and Wang, Z.Y. and Zhang, C. and Li, P. and Liu, Y.",
TITLE = "CoSpace: Benchmarking Continuous Space Perception Ability for
Vision-Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29569-29579",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231697"}
@inproceedings{bb236732,
AUTHOR = "Kang, H.Q. and Sachdeva, E. and Gupta, P. and Bae, S.J. and Lee, K.",
TITLE = "GFlowVLM: Enhancing Multi-step Reasoning in Vision-Language Models
with Generative Flow Networks",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "3815-3825",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231698"}
@inproceedings{bb236733,
AUTHOR = "Chen, J.H. and Yang, J.W. and Wu, H.P. and Li, D. and Gao, J.F. and Zhou, T.Y. and Xiao, B.",
TITLE = "Florence-VL: Enhancing Vision-Language Models with Generative Vision
Encoder and Depth-Breadth Fusion",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "24928-24938",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231699"}
@inproceedings{bb236734,
AUTHOR = "Yang, C.Y. and Dong, X. and Zhu, X.Z. and Su, W.J. and Wang, J.H. and Tian, H. and Chen, Z. and Wang, W.H. and Lu, L.W. and Dai, J.F.",
TITLE = "PVC: Progressive Visual Token Compression for Unified Image and Video
Processing in Large Vision-Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "24939-24949",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231700"}
@inproceedings{bb236735,
AUTHOR = "Zhang, K. and Li, J.Y. and Li, Z. and Zhou, S.K.",
TITLE = "DH-Set: Improving Vision-Language Alignment with Diverse and Hybrid
Set-Embeddings Learning",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "24993-25003",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231701"}
@inproceedings{bb236736,
AUTHOR = "Guo, Y.C. and Gu, X.D.",
TITLE = "MMRL: Multi-Modal Representation Learning for Vision-Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "25015-25025",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231702"}
@inproceedings{bb236737,
AUTHOR = "Zhu, B. and Cui, J. and Zhang, H.W. and Zhang, C.",
TITLE = "Project-Probe-Aggregate: Efficient Fine-Tuning for Group Robustness",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "25487-25496",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231703"}
@inproceedings{bb236738,
AUTHOR = "Li, H.Y. and Wang, L. and Wang, C. and Jiang, J. and Peng, Y. and Long, G.D.",
TITLE = "DPC: Dual-Prompt Collaboration for Tuning Vision-Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "25623-25632",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231704"}
@inproceedings{bb236739,
AUTHOR = "Saravanan, D. and Gupta, V. and Singh, D. and Khan, Z. and Gandhi, V. and Tapaswi, M.",
TITLE = "VELOCITI: Benchmarking Video-Language Compositional Reasoning with
Strict Entailment",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "18914-18924",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231705"}
@inproceedings{bb236740,
AUTHOR = "Pan, B. and Li, Q. and Tang, X.Y. and Huang, W. and Fang, Z. and Liu, F. and Wang, J.Y. and Yu, J.Y. and Shi, Y.",
TITLE = "NLPrompt: Noise-Label Prompt Learning for Vision-Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "19963-19973",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231706"}
@inproceedings{bb236741,
AUTHOR = "Zhang, Y.T. and Chen, L. and Zheng, G.D. and Gao, Y.F. and Zheng, R. and Fu, J. and Yin, Z.F. and Jin, S. and Qiao, Y. and Huang, X.J. and Zhao, F. and Gui, T. and Shao, J.",
TITLE = "SPA-VL: A Comprehensive Safety Preference Alignment Dataset for
Vision Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "19867-19878",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231707"}
@inproceedings{bb236742,
AUTHOR = "Bhattacharjee, S.S. and Campbell, D. and Shome, R.",
TITLE = "Believing is Seeing: Unobserved Object Detection using Generative
Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "19366-19377",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231708"}
@inproceedings{bb236743,
AUTHOR = "Zhou, E. and Su, Q. and Chi, C. and Zhang, Z.Z. and Wang, Z.Y. and Huang, T.J. and Sheng, L. and Wang, H.",
TITLE = "Code-as-Monitor: Constraint-aware Visual Programming for Reactive and
Proactive Robotic Failure Detection",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "6919-6929",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231709"}
@inproceedings{bb236744,
AUTHOR = "Zhou, W.J. and Tao, M. and Zhao, C.Y. and Guo, H.Y. and Dong, H.H. and Tang, M. and Wang, J.Q.",
TITLE = "PhysVLM: Enabling Visual Language Models to Understand Robotic
Physical Reachability",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "6940-6949",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231710"}
@inproceedings{bb236745,
AUTHOR = "Song, C.H. and Blukis, V. and Tremblay, J. and Tyree, S. and Su, Y. and Birchfield, S.",
TITLE = "RoboSpatial: Teaching Spatial Understanding to 2D and 3D
Vision-Language Models for Robotics",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "15768-15780",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231711"}
@inproceedings{bb236746,
AUTHOR = "Lozano, A. and Sun, M.W. and Burgess, J. and Chen, L. and Nirschl, J.J. and Gu, J. and Lopez, I. and Aklilu, J. and Rau, A. and Katzer, A.W. and Zhang, Y.H. and Chiu, C. and Wang, X.H. and Song, A.S. and Tibshirani, R. and Yeung Levy, S.",
TITLE = "BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and
Vision-Language Models Derived from Scientific Literature",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "19724-19735",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231712"}
@inproceedings{bb236747,
AUTHOR = "Xiao, R. and Kim, S. and Georgescu, M.I. and Akata, Z. and Alaniz, S.",
TITLE = "FLAIR: VLM with Fine-grained Language-informed Image Representations",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "24884-24894",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231713"}
@inproceedings{bb236748,
AUTHOR = "Zhang, J.M. and Ye, J. and Ma, X. and Li, Y. and Yang, Y.F. and Chen, Y.H. and Sang, J. and Yeung, D.Y.",
TITLE = "Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on
Vision-language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "19900-19909",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231714"}
@inproceedings{bb236749,
AUTHOR = "Wang, X. and Chen, K. and Zhang, J.M. and Chen, J.J. and Ma, X.",
TITLE = "TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in
Vision-Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "19910-19920",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231715"}
@inproceedings{bb236750,
AUTHOR = "Vasu, P.K.A. and Faghri, F. and Li, C.L. and Koc, C. and True, N. and Antony, A. and Santhanam, G. and Gabriel, J. and Grasch, P. and Tuzel, O. and Pouransari, H.",
TITLE = "FastVLM: Efficient Vision Encoding for Vision Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "19769-19780",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231716"}
@inproceedings{bb236751,
AUTHOR = "Chen, Q.Z. and Wang, C. and Wang, D. and Zhang, T. and Li, W. and He, X.F.",
TITLE = "Lifelong Knowledge Editing for Vision Language Models with Low-Rank
Mixture-of-Experts",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "9455-9466",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231717"}
@inproceedings{bb236752,
AUTHOR = "Chen, T.Y. and Fu, X.C. and Gao, Y. and Qian, H.D. and Wei, Y. and Yan, K. and Zhou, H.Y. and Li, J.X.",
TITLE = "Galaxy Walker: Geometry-aware VLMs For Galaxy-scale Understanding",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "4112-4121",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231718"}
@inproceedings{bb236753,
AUTHOR = "Liu, Z.J. and Zhu, L. and Shi, B. and Zhang, Z.Y. and Lou, Y.M. and Yang, S. and Xi, H.C. and Cao, S.Y. and Gu, Y.X. and Li, D.C. and Li, X. and Tang, H.T. and Fang, Y.H. and Chen, Y. and Hsieh, C.Y. and Huang, D.A. and Cheng, A.C. and Hu, J.Y. and Liu, S. and Krishna, R. and Molchanov, P. and Kautz, J. and Yin, H.X. and Han, S. and Lu, Y.",
TITLE = "NVILA: Efficient Frontier Visual Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "4122-4134",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231719"}
@inproceedings{bb236754,
AUTHOR = "Poppi, T. and Kasarla, T. and Mettes, P. and Baraldi, L. and Cucchiara, R.",
TITLE = "Hyperbolic Safety-Aware Vision-Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "4222-4232",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231720"}
@inproceedings{bb236755,
AUTHOR = "Zhang, H.Y. and Guo, Y.Y. and Kankanhalli, M.",
TITLE = "Joint Vision-Language Social Bias Removal for CLIP",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "4246-4255",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231721"}
@inproceedings{bb236756,
AUTHOR = "Zhang, Y. and Deng, Y.X. and Guo, M.H. and Hu, S.M.",
TITLE = "Adaptive Parameter Selection for Tuning Vision-Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "4280-4290",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231722"}
@inproceedings{bb236757,
AUTHOR = "Deng, A. and Cao, T. and Chen, Z. and Hooi, B.",
TITLE = "Words or Vision: Do Vision-Language Models Have Blind Faith in Text?",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "3867-3876",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231723"}
@inproceedings{bb236758,
AUTHOR = "Huang, R. and Ding, X.P. and Wang, C.W. and Han, J.H. and Liu, Y.L. and Zhao, H.S. and Xu, H. and Hou, L. and Zhang, W. and Liang, X.D.",
TITLE = "HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large
Vision-Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29814-29824",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231724"}
@inproceedings{bb236759,
AUTHOR = "Wang, S. and Zhang, Y.J. and Zhu, Y. and Li, J.N. and Wang, Z.Z. and Liu, Y.W. and Ji, X.Y.",
TITLE = "Towards Understanding How Knowledge Evolves in Large Vision-Language
Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29858-29868",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231725"}
@inproceedings{bb236760,
AUTHOR = "Deitke, M. and Clark, C. and Lee, S.H. and Tripathi, R. and Yang, Y. and Park, J.S. and Salehi, M. and Muennighoff, N. and Lo, K. and Soldaini, L. and Lu, J. and Anderson, T. and Bransom, E. and Ehsani, K. and Ngo, H. and Chen, Y. and Patel, A. and Yatskar, M. and Callison Burch, C. and Head, A. and Hendrix, R. and Bastani, F. and VanderBilt, E. and Lambert, N. and Chou, Y. and Chheda, A. and Sparks, J. and Skjonsberg, S. and Schmitz, M. and Sarnat, A. and Bischoff, B. and Walsh, P. and Newell, C. and Wolters, P. and Gupta, T. and Zeng, K.H. and Borchardt, J. and Groeneveld, D. and Nam, C. and Lebrecht, S. and Wittlif, C. and Schoenick, C. and Michel, O. and Krishna, R. and Weihs, L. and Smith, N.A. and Hajishirzi, H. and Girshick, R. and Farhadi, A. and Kembhavi, A.",
TITLE = "Molmo and PixMo: Open Weights and Open Data for State-of-the-Art
Vision-Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "91-104",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231726"}
@inproceedings{bb236761,
AUTHOR = "Zhao, W. and Han, Y.Z. and Tang, J.S. and Li, Z. and Song, Y.B. and Wang, K. and Wang, Z.Y. and You, Y.",
TITLE = "A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for
Accelerating Large VLMs",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "19814-19824",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231727"}
@inproceedings{bb236762,
AUTHOR = "Lee, B.K. and Hachiuma, R. and Wang, Y.C.A.F. and Ro, Y.M. and Wu, Y.H.",
TITLE = "VLsI: Verbalized Layers-to-Interactions from Large to Small Vision
Language Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "29545-29557",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231728"}
@inproceedings{bb236763,
AUTHOR = "Sun, J.C. and Sharma, R. and Lokhande, V.S. and Chen, C.Y.",
TITLE = "Cross-Modal Feature Alignment and MMD Improve Robustness of Prompt
Tuning",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "4714-4724",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231729"}
@inproceedings{bb236764,
AUTHOR = "Safaei, B. and Patel, V.M.",
TITLE = "Active Learning for Vision-Language Models",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "4902-4912",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231730"}
@inproceedings{bb236765,
AUTHOR = "Wang, Y.C. and Zhang, Z.K. and Wang, J. and Fan, D. and Xu, Z.L. and Liu, L. and Hao, X. and Bhat, V. and Li, X.Y.",
TITLE = "GEXIA: Granularity Expansion and Iterative Approximation for Scalable
Multi-Grained Video-Language Learning",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "4725-4735",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231731"}
@inproceedings{bb236766,
AUTHOR = "Colman, R. and Vu, M. and Bhattarai, M. and Ma, M. and Viswanathan, H. and O'Malley, D. and Santos, J.E.",
TITLE = "PatchFinder: Leveraging Visual Language Models for Accurate
Information Retrieval Using Model Uncertainty",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "9146-9155",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231732"}
@inproceedings{bb236767,
AUTHOR = "Jawade, B. and Soares, J.V.B. and Thadani, K. and Mohan, D.D. and Eshratifar, A.E. and Culpepper, B. and de Juan, P. and Setlur, S. and Govindaraju, V.",
TITLE = "SCOT: Self-Supervised Contrastive Pretraining for Zero-Shot
Compositional Retrieval",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "5509-5519",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231733"}
@inproceedings{bb236768,
AUTHOR = "Talemi, N.A. and Kashiani, H. and Afghah, F.",
TITLE = "Style-Pro: Style-Guided Prompt Learning for Generalizable
Vision-Language Models",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "6207-6216",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231734"}
@inproceedings{bb236769,
AUTHOR = "Chang, H.S. and Wang, C.Y. and Wang, R.R. and Chou, G. and Liao, H.Y.M.",
TITLE = "Generalist YOLO: Towards Real-Time End-to-End Multi-Task Visual
Language Models",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "6217-6227",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231735"}
@inproceedings{bb236770,
AUTHOR = "Westfechtel, T. and Zhang, D. and Harada, T.",
TITLE = "Combining Inherent Knowledge of Vision-Language Models with
Unsupervised Domain Adaptation Through Strong-Weak Guidance",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "6528-6537",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231736"}
@inproceedings{bb236771,
AUTHOR = "Chen, H.N. and Ni, Y. and Huang, W.J. and Liu, Y. and Jeong, S. and Wen, F. and Bastian, N.D. and Latapie, H. and Imani, M.",
TITLE = "VLTP: Vision-Language Guided Token Pruning for Task-Oriented
Segmentation",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "9353-9363",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231737"}
@inproceedings{bb236772,
AUTHOR = "Ali, E. and Silva, S. and Khan, M.H.",
TITLE = "DPA: Dual Prototypes Alignment for Unsupervised Adaptation of
Vision-Language Models",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "6083-6093",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231738"}
@inproceedings{bb236773,
AUTHOR = "Zhang, C. and Stepputtis, S. and Sycara, K. and Xie, Y.Q.",
TITLE = "Enhancing Vision-Language Few-Shot Adaptation with Negative Learning",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "5905-5915",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231739"}
@inproceedings{bb236774,
AUTHOR = "Yamada, M. and Dharamshi, N. and Kohli, A. and Kasu, P. and Khan, A. and Ghulyani, M.",
TITLE = "Unleashing Potentials of Vision-Language Models for Zero-Shot HOI
Detection",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "5751-5760",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231740"}
@inproceedings{bb236775,
AUTHOR = "Imam, R. and Gani, H. and Huzaifa, M. and Nandakumar, K.",
TITLE = "Test-Time Low Rank Adaptation via Confidence Maximization for
Zero-Shot Generalization of Vision-Language Models",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "5449-5459",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231741"}
@inproceedings{bb236776,
AUTHOR = "Ghoddoosian, R. and Agarwal, N. and Dwivedi, I. and Darisuh, B.",
TITLE = "ACE: Action Concept Enhancement of Video-Language Models in
Procedural Videos",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "9521-9531",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231742"}
@inproceedings{bb236777,
AUTHOR = "Onoe, Y. and Rane, S. and Berger, Z. and Bitton, Y. and Cho, J. and Garg, R. and Ku, A. and Parekh, Z. and Pont Tuset, J. and Tanzer, G. and Wang, S. and Baldridge, J.",
TITLE = "DOCCI: Descriptions of Connected and Contrasting Images",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LX: 291-309",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231743"}
@inproceedings{bb236778,
AUTHOR = "Li, T. and Ma, M.M. and Peng, X.",
TITLE = "DEAL: Disentangle and Localize Concept-level Explanations for VLMs",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXXIX: 383-401",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231744"}
@inproceedings{bb236779,
AUTHOR = "Li, S.C. and Li, L. and Liu, Y. and Ren, S.H. and Liu, Y.X. and Gao, R.D. and Sun, X. and Hou, L.",
TITLE = "Vitatecs: A Diagnostic Dataset for Temporal Concept Understanding of
Video-language Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXX: 331-348",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231745"}
@inproceedings{bb236780,
AUTHOR = "Yang, Y.T. and Chen, M.H. and Qiu, Q. and Wu, J.H. and Wang, W.X. and Lin, B.B. and Guan, Z.Y. and He, X.F.",
TITLE = "Adapt2reward: Adapting Video-language Models to Generalizable Robotic
Rewards via Failure Prompts",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LVII: 163-180",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231746"}
@inproceedings{bb236781,
AUTHOR = "Rahmanzadehgervi, P. and Bolton, L. and Taesiri, M.R. and Nguyen, A.T.",
TITLE = "Vision Language Models are blind",
BOOKTITLE = ACCV24,
YEAR = "2024",
PAGES = "V: 293-309",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231747"}
@inproceedings{bb236782,
AUTHOR = "Chytas, S.P. and Kim, H.W.J. and Singh, V.",
TITLE = "Understanding Multi-compositional Learning in Vision and Language
Models via Category Theory",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLVIII: 324-341",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231748"}
@inproceedings{bb236783,
AUTHOR = "Song, Y.Z. and Chen, Y.S. and Lin, T.L. and Liu, B. and Fu, J.L. and Shuai, H.H.",
TITLE = "Capture Concept Through Comparison: Vision-and-language Representation
Learning with Intrinsic Information Mining",
BOOKTITLE = ACCV24,
YEAR = "2024",
PAGES = "III: 220-238",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231749"}
@inproceedings{bb236784,
AUTHOR = "Adhikari, R. and Thapaliya, S. and Dhakal, M. and Khanal, B.",
TITLE = "Tunevlseg: Prompt Tuning Benchmark for Vision-language Segmentation
Models",
BOOKTITLE = ACCV24,
YEAR = "2024",
PAGES = "III: 44-62",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231750"}
@inproceedings{bb236785,
AUTHOR = "He, H.C. and Liu, W.B. and Xing, W.W.",
TITLE = "Biefficient: Bidirectionally Prompting Vision-language Models for
Parameter-efficient Video Recognition",
BOOKTITLE = ACCV24,
YEAR = "2024",
PAGES = "III: 257-274",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231751"}
@inproceedings{bb236786,
AUTHOR = "Yang, J.K. and Dong, Y.H. and Liu, S. and Li, B. and Wang, Z.Y. and Tan, H.R. and Jiang, C.C. and Kang, J. and Zhang, Y.H. and Zhou, K.Y. and Liu, Z.W.",
TITLE = "Octopus: Embodied Vision-language Programmer from Environmental
Feedback",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "I: 20-38",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231752"}
@inproceedings{bb236787,
AUTHOR = "Kar, O.F. and Tonioni, A. and Poklukar, P. and Kulshrestha, A. and Zamir, A. and Tombari, F.",
TITLE = "Brave: Broadening the Visual Encoding of Vision-language Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XVI: 113-132",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231753"}
@inproceedings{bb236788,
AUTHOR = "Kamath, A. and Hsieh, C.Y. and Chang, K.W. and Krishna, R.",
TITLE = "The Hard Positive Truth About Vision-language Compositionality",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XIV: 37-54",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231754"}
@inproceedings{bb236789,
AUTHOR = "Jia, B.X. and Chen, Y.X. and Yu, H.Y. and Wang, Y. and Niu, X.S. and Liu, T.Y. and Li, Q. and Huang, S.Y.",
TITLE = "Sceneverse: Scaling 3d Vision-language Learning for Grounded Scene
Understanding",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "IX: 289-310",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231755"}
@inproceedings{bb236790,
AUTHOR = "Zhang, Y.F. and Jiang, M. and Zhao, Q.",
TITLE = "Learning Chain of Counterfactual Thought for Bias-robust
Vision-language Reasoning",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "VIII: 334-351",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231756"}
@inproceedings{bb236791,
AUTHOR = "Li, J. and Chen, D. and Cai, T. and Chen, P.H. and Hong, Y. and Chen, Z.F. and Shen, Y.K. and Gan, C.",
TITLE = "Flexattention for Efficient High-resolution Vision-language Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXV: 286-302",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231757"}
@inproceedings{bb236792,
AUTHOR = "Li, X. and Ding, J. and Chen, Z.Y. and Elhoseiny, M.",
TITLE = "UNI3DL: A Unified Model for 3d Vision-language Understanding",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXIII: 74-92",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231758"}
@inproceedings{bb236793,
AUTHOR = "Hao, T.X. and Ding, X.H. and Feng, J.X. and Yang, Y.H. and Chen, H. and Ding, G.",
TITLE = "Quantized Prompt for Efficient Generalization of Vision-language Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XIX: 54-73",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231759"}
@inproceedings{bb236794,
AUTHOR = "Xu, H.B. and Ke, X. and Li, Y.Z. and Xu, R. and Wu, H.Q. and Lin, X.F. and Guo, W.Z.",
TITLE = "Vision-language Action Knowledge Learning for Semantic-aware Action
Quality Assessment",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLII: 423-440",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231760"}
@inproceedings{bb236795,
AUTHOR = "Zhu, Z.Y. and Zhang, Z. and Ma, X.J. and Niu, X.S. and Chen, Y.X. and Jia, B.X. and Deng, Z.D. and Huang, S.Y. and Li, Q.",
TITLE = "Unifying 3d Vision-language Understanding via Promptable Queries",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLIV: 188-206",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231761"}
@inproceedings{bb236796,
AUTHOR = "Zhang, J.M. and Ma, X.J. and Wang, X. and Qiu, L.Y. and Wang, J.Q. and Jiang, Y.G. and Sang, J.",
TITLE = "Adversarial Prompt Tuning for Vision-language Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLV: 56-72",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231762"}
@inproceedings{bb236797,
AUTHOR = "Wu, G. and Zhang, X. and Li, Z. and Chen, Z.W. and Liang, J.J. and Yang, J. and Li, X.",
TITLE = "Cascade Prompt Learning for Vision-language Model Adaptation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "L: 304-321",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231763"}
@inproceedings{bb236798,
AUTHOR = "Gao, S. and Jia, X.J. and Ren, X.H. and Tsang, I. and Guo, Q.",
TITLE = "Boosting Transferability in Vision-language Attacks via Diversification
Along the Intersection Region of Adversarial Trajectory",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LVII: 442-460",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231764"}
@inproceedings{bb236799,
AUTHOR = "Jiang, H.B. and Yue, J.P. and Luo, H. and Ding, Z. and Lu, Z.Q.",
TITLE = "Reinforcement Learning Friendly Vision-language Model for Minecraft",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXVIII: 1-17",
BIBSOURCE = "http://www.visionbib.com/bibliography/applicat803vlm3.html#TT231765"}
Last update:Nov 26, 2025 at 20:24:09