Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-10T15:29:49.681399Z
Paper Citation Record · LEDGER
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding
As of 13 August 2026, this Paper Citation Record lists 62 of 62 outbound references and 1 inbound Pith citation observation for arXiv:2604.11122.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-06-29T08:13:42.526597Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-06-29T08:23:15.836108Z
Reference resolution
62 of 62 outbound references displayed
- verified exact10
- verified fuzzy22
- unresolved4
- parse uncertain0
- malformed identifier0
- metadata mismatch26
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 682a15fa-604c-4f73-81ec-3fdb3bcff763 · outbound
This paper cites GPT-4 Technical Report.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding GPT-4 Technical Report
Reference 1
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T10:26:01.553947Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation f7d337c7-beb3-4197-a843-161e1d963f59 · outbound
This paper cites NeurIPS35, 23716–23736 (2022) 2, 4.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding NeurIPS35, 23716–23736 (2022) 2, 4
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:15:27.587168Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 2350c999-240f-47d3-9385-4b99d93acced · outbound
This paper cites an unresolved cited work.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding Unresolved cited work
Reference 3
- Resolution
- unresolved
- raw_fallback, observed 2026-05-17T23:15:27.580918Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 0b0505fb-8b2a-4e20-860a-9cc8a0cbf832 · outbound
This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
Reference 4
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T10:26:01.525600Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 2e2b0023-fce9-44c7-b175-b10b29e2d4d0 · outbound
This paper cites Intern-s1: A scientific multimodal foundation model.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding Intern-s1: A scientific multimodal foundation model
Reference 5
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T10:26:01.509011Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 5dbace75-1ed2-49d0-8386-c426739b2c14 · outbound
This paper cites Qwen3-VL Technical Report.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding Qwen3-VL Technical Report
Reference 6
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T10:26:01.534709Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 9220fe71-9dc3-4d70-9a8c-da3b089bf531 · outbound
This paper cites Qwen2.5-VL Technical Report.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding Qwen2.5-VL Technical Report
Reference 7
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T10:26:01.490076Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 5758ac7b-d82d-4573-9bba-614583f0ee6d · outbound
This paper cites Token Merging: Your ViT But Faster.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding Token Merging: Your ViT But Faster
Reference 8
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T20:52:10.541797Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation d0d01b0f-1c0e-4967-9196-aed86201c6cc · outbound
This paper cites Machine Learning111(9), 3125–3160 (2022) 2.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding Machine Learning111(9), 3125–3160 (2022) 2
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:15:27.594129Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 093c6ddb-a74d-4e0d-9d22-10f0a07d8477 · outbound
This paper cites In: ECCV.
Reference 10
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:15:27.597603Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 52324a58-4b0d-4655-a4eb-eb21986d803d · outbound
This paper cites Science China Information Sciences67(12), 220101 (2024) 2.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding Science China Information Sciences67(12), 220101 (2024) 2
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:15:27.590739Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation f8958755-30d4-4583-9daa-e8827f78b2bc · outbound
This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Reference 12
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T10:26:01.494111Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 7a04eef4-778b-4349-9638-da94cd060bd2 · outbound
This paper cites NeurIPS36, 49250–49267 (2023) 2, 4.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding NeurIPS36, 49250–49267 (2023) 2, 4
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:15:27.570587Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation c5326a5f-2dd8-4602-80aa-e2cda368c97e · outbound
This paper cites AdaFV: Rethinking of Visual-Language alignment for VLM acceleration.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding AdaFV: Rethinking of Visual-Language alignment for VLM acceleration
Reference 14
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T10:26:01.546179Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation a143544b-f3f4-48bc-900f-add73db724ee · outbound
This paper cites ISPRS Journal of Photogrammetry and Remote Sensing224, 272–286 (2025) 2, 5.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding ISPRS Journal of Photogrammetry and Remote Sensing224, 272–286 (2025) 2, 5
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:15:27.577689Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation b92593f7-b2c5-4fa8-a67f-26d6be5219ef · outbound
This paper cites In: CVPR.
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:15:27.584124Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation c425d30c-9402-452c-93be-5495452b6de5 · outbound
This paper cites LLaVA-OneVision: Easy Visual Task Transfer.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding LLaVA-OneVision: Easy Visual Task Transfer
Reference 17
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T10:26:01.500026Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation e44a0dd0-2f55-474c-86a9-a31cb757dbcf · outbound
This paper cites In: ICML.
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:15:27.574205Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 9e417430-9f79-4a7d-be2b-d356eaad3b3f · outbound
This paper cites LHRS-Bot-Nova: Improved Multimodal Large Language Model for Remote Sensing Vision-Language Interpretation.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding LHRS-Bot-Nova: Improved Multimodal Large Language Model for Remote Sensing Vision-Language Interpretation
Reference 19
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T10:26:01.316488Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 5f5e0553-2571-45b0-9085-acd3c6233703 · outbound
This paper cites an unresolved cited work.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding Unresolved cited work
Reference 20
- Resolution
- unresolved
- raw_fallback, observed 2026-05-17T23:15:27.657711Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation ce18f5a6-6150-4ae2-8f1c-29a11ac3ce9d · outbound
This paper cites NeurIPS36, 34892– 34916 (2023) 4.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding NeurIPS36, 34892– 34916 (2023) 4
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:15:27.644850Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation f7b080fe-e201-4873-81be-560a3d6a5f73 · outbound
This paper cites Zoomearth: Active perception for ultra-high-resolution geospatial vision-language tasks.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding Zoomearth: Active perception for ultra-high-resolution geospatial vision-language tasks
Reference 22
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T10:26:01.359193Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 4ed4e817-79c0-40ea-99e1-b327f90eb442 · outbound
This paper cites RSUniVLM: A Unified Vision Language Model for Remote Sensing via Granularity-oriented Mixture of Experts.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding RSUniVLM: A Unified Vision Language Model for Remote Sensing via Granularity-oriented Mixture of Experts
Reference 23
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T10:26:01.278915Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 579b4017-70b8-44c4-adf2-e93e3bfa17ce · outbound
This paper cites In: ICCV.
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:15:27.654633Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation a4c78456-3dd8-4ea1-b760-0fd80a0b6bfe · outbound
This paper cites Nature Reviews Neuroscience13(11), 758–768 (2012) 4.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding Nature Reviews Neuroscience13(11), 758–768 (2012) 4
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:15:27.624004Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 855dfb92-54e9-4a0e-8027-1920179603bf · outbound
This paper cites In: ECCV.
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:15:27.637797Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 7c80d2e9-e022-4006-9b2a-8a78f9dee358 · outbound
This paper cites an unresolved cited work.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding Unresolved cited work
Reference 27
- Resolution
- unresolved
- raw_fallback, observed 2026-05-17T23:15:27.627721Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 466528d3-ba0d-4c11-837a-69181a9ef3de · outbound
This paper cites VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis
Reference 28
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T10:26:01.418886Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 4ac3132f-d77c-4366-b5d5-9fea238bf795 · outbound
This paper cites In: ICML.
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:15:27.634410Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 2b18b074-4591-446f-8e20-309ef54666b4 · outbound
This paper cites In: ICCV.
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:15:27.631168Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation a90ae10a-e2ff-44c1-b062-9ccfd38ed5d0 · outbound
This paper cites Earthmind: Towards multi-granular and multi- sensor earth observation with large multimodal models.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding Earthmind: Towards multi-granular and multi- sensor earth observation with large multimodal models
Reference 31
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T10:26:01.469106Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 76ec8b87-7db7-47eb-8f3b-52265e924568 · outbound
This paper cites Large Language Models for Captioning and Retrieving Remote Sensing Images.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding Large Language Models for Captioning and Retrieving Remote Sensing Images
Reference 32
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T10:26:01.323487Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 5179b229-de60-4840-a540-bb0ac5e28f0a · outbound
This paper cites EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues
Reference 33
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T10:26:01.450581Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation e4996d9c-c359-4ea8-8543-6ff5c326c47a · outbound
This paper cites Llava-uhd v3: Progressive visual compression for efficient native-resolution encoding in mllms.ArXiv, abs/2511.21150.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding Llava-uhd v3: Progressive visual compression for efficient native-resolution encoding in mllms.ArXiv, abs/2511.21150
Reference 34
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T10:26:01.308433Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation f85673ed-15cd-494d-a5a8-9afc8124278f · outbound
This paper cites Gemini: A Family of Highly Capable Multimodal Models.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding Gemini: A Family of Highly Capable Multimodal Models
Reference 35
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T10:26:01.388730Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 574078ba-5053-4614-a603-05b882195095 · outbound
This paper cites LLaMA: Open and Efficient Foundation Language Models.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding LLaMA: Open and Efficient Foundation Language Models
Reference 36
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T10:26:01.337700Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 33bde912-6453-4dee-b764-bcba99f4153d · outbound
This paper cites NeurIPS30(2017) 4.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding NeurIPS30(2017) 4
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:15:27.619836Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 2a72aeb5-c5e2-4db3-a5fa-df23caad0602 · outbound
This paper cites arXiv preprint arXiv:2511.20085 (2025) 5.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding arXiv preprint arXiv:2511.20085 (2025) 5
Reference 38
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T10:26:01.287593Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 1ac56322-4638-490b-968f-ae45691415a4 · outbound
This paper cites Geollava-8k: Scaling remote-sensing multimodal large language models to 8k resolution.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding Geollava-8k: Scaling remote-sensing multimodal large language models to 8k resolution
Reference 39
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T10:26:01.355789Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation d2818960-d3a9-4f77-9ae0-43b86c2c45e7 · outbound
This paper cites an unresolved cited work.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding Unresolved cited work
Reference 40
- Resolution
- unresolved
- raw_fallback, observed 2026-05-17T23:15:27.616272Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation fb1786ca-0d28-47b6-b70e-b6bb90e12976 · outbound
This paper cites arXiv:2601.02783 [cs] doi:10.48550/arXiv.2601.02783 Mingze Wang, Lili Su, Cilin Yan, Sheng Xu, Pengcheng Yuan, Xiaolong Jiang, and Baochang Zhang.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding arXiv:2601.02783 [cs] doi:10.48550/arXiv.2601.02783 Mingze Wang, Lili Su, Cilin Yan, Sheng Xu, Pengcheng Yuan, Xiaolong Jiang, and Baochang Zhang
Reference 41
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T10:26:01.409730Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation b67792b7-a70b-4d95-936d-3f363751707c · outbound
This paper cites IEEE Transactions on Geoscience and Remote Sensing63, 1–20 (2025).https://doi.org/10.1109/TGRS.2024.3510833 5.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding IEEE Transactions on Geoscience and Remote Sensing63, 1–20 (2025).https://doi.org/10.1109/TGRS.2024.3510833 5
Reference 42
- Resolution
- verified exact
- arxiv_id, observed 2026-05-10T15:30:32.177796Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation cabd839d-e94c-4be9-9616-70ef5fa93878 · outbound
This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
Reference 43
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T10:26:01.272349Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 28ac8422-a138-4282-adc0-2a41a2bbb11c · outbound
This paper cites Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization
Reference 44
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-16T09:16:17.933281Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation b220adf3-b9f3-4231-984e-0c5f72fb71e4 · outbound
This paper cites In: Proceedings of the IEEE conference on computer vision and pattern recognition.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding In: Proceedings of the IEEE conference on computer vision and pattern recognition
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:15:27.612505Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 6a36ca47-58e6-4604-9f55-dfdd194f2112 · outbound
This paper cites PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
Reference 46
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-15T12:12:14.835646Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 17c2f794-6f35-4d06-b2f0-ac5c369865f3 · outbound
This paper cites In: CVPR.
Reference 47
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:15:27.608446Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 7a846a2b-d46c-4c2f-b105-de90b785b8a6 · outbound
This paper cites mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality
Reference 48
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T10:26:01.395330Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation adac2e97-61f4-4cc5-a071-815b016206f0 · outbound
This paper cites In: AAAI.
Reference 49
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:15:27.604601Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation be2c3fbd-d08e-40fc-bb27-c0ba22ad2397 · outbound
This paper cites In: CVPR.
Reference 50
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:15:27.651528Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 4ec0b256-be82-43e1-a3ac-abe17a58e66a · outbound
This paper cites In: CVPR.
Reference 51
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:15:27.600904Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 9817257f-fe51-4311-beb9-948b26bc20e9 · outbound
This paper cites Visiontrim: Unified vision token compression for training-free mllm acceleration.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding Visiontrim: Unified vision token compression for training-free mllm acceleration
Reference 52
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T10:26:01.365392Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 9a84096e-c99e-4b89-8892-ce982fcf3b50 · outbound
This paper cites A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models
Reference 53
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T10:26:01.485770Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation e4df18e9-3d41-469c-a30f-3ec266b85c22 · outbound
This paper cites ISPRS Journal of Pho- togrammetry and Remote Sensing221, 64–77 (2025) 5.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding ISPRS Journal of Pho- togrammetry and Remote Sensing221, 64–77 (2025) 5
Reference 54
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:15:27.648413Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 74170594-6f54-4c95-b8e0-4a4440d9af1a · outbound
This paper cites arXiv preprint arXiv:2505.22654 , year=.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding arXiv preprint arXiv:2505.22654 , year=
Reference 55
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T10:26:01.368991Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 7dfed331-4316-49bf-b658-c03c40981a1b · outbound
This paper cites Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs
Reference 56
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T10:26:01.376382Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation db20ab85-52b2-44d5-b71b-5f4ee6fe9da9 · outbound
This paper cites EarthMarker: A Visual Prompting Multi-modal Large Language Model for Remote Sensing.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding EarthMarker: A Visual Prompting Multi-modal Large Language Model for Remote Sensing
Reference 57
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T10:26:01.425718Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 3f7a7faf-9c02-44dd-ae82-efd17624040d · outbound
This paper cites IEEE Transactions on Geoscience and Remote Sensing62, 1–20 (2024) 5.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding IEEE Transactions on Geoscience and Remote Sensing62, 1–20 (2024) 5
Reference 58
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T23:15:27.641514Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation a1fb4d6a-f906-41c9-87a0-b760b9169ac0 · outbound
This paper cites SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
Reference 59
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-15T14:58:32.742607Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 63f2b567-c4f1-44ba-a0af-5991e7c4ee71 · outbound
This paper cites ImageRAG: Enhancing Ultra High Resolution Remote Sensing Imagery Analysis with ImageRAG.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding ImageRAG: Enhancing Ultra High Resolution Remote Sensing Imagery Analysis with ImageRAG
Reference 60
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T10:26:01.351825Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 0992bd66-29a8-4424-a98b-afdc3fa54b5b · outbound
This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
Reference 61
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T10:26:01.384042Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Observation 1ef23b35-c07a-4c86-9071-5adf4b21dd47 · outbound
This paper cites InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models.
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
Reference 62
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T10:26:01.478342Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.
Pith citing papers
Observation 3507f4b2-4b02-42cd-bdef-1db20f1d8cb1 · inbound
PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding cites this paper.
PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding
Reference 67
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T08:23:15.837500Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.