mlsanityData to 14 Oct 2026

A Parameter-Efficient Mixture-of-Experts Framework for Cross-Modal Geo-Localization

arXiv 2510.20291 ↗First posted 23 Oct 2025cs.CV cs.AIcited by 1

On the map: Mixture-of-experts → Vision mixture-of-experts

Abstract (arXiv)

We present a winning solution to RoboSense 2025 Track 4: Cross-Modal Drone Navigation. The task retrieves the most relevant geo-referenced image from a large multi-platform corpus (satellite/drone/ground) given a natural-language query. Two obstacles are severe inter-platform heterogeneity and a domain gap between generic training descriptions and platform-specific test queries. We mitigate these with a domain-aligned preprocessing pipeline and a Mixture-of-Experts (MoE) framework: (i) platform-wise partitioning, satellite augmentation, and removal of orientation words; (ii) an LLM-based caption refinement pipeline to align textual semantics with the distinct visual characteristics of each platform. Using BGE-M3 (text) and EVA-CLIP (image), we train three platform experts using a progressive two-stage, hard-negative mining strategy to enhance discriminative power, and fuse their scores at inference. The system tops the official leaderboard, demonstrating robust cross-modal geo-localization under heterogeneous viewpoints.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts. Builds on 21 of its 38 references that are in the map. First posted on arXiv 23 Oct 2025.

Builds on

21 of 38 references.

References · 21

  1. 2024Mixtral of Expertscited by 1,823
  2. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  3. 2023EVA-CLIP: Improved Training Techniques for CLIP at Scalecited by 798
  4. 2021VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Expertscited by 425
  5. 2024Long-CLIP: Unlocking the Long-Text Capability of CLIPcited by 300
  6. 2023Alpha-CLIP: A CLIP Model Focusing on Wherever You Wantcited by 151
  7. 2024EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameterscited by 99
  8. 2023TF-CLIP: Learning Text-free CLIP for Video-based Person Re-Identificationcited by 40
  9. 2024Where am I? Cross-View Geo-localization with Natural Language Descriptionscited by 38
  10. 2024Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Modelscited by 30
  11. 2025Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimizationcited by 29
  12. 2024CLIP-CID: Efficient CLIP Distillation via Cluster-Instance Discriminationcited by 21
9 more
  1. 2024Cross-Modal and Uni-Modal Soft-Label Alignment for Image-Text Retrievalcited by 13
  2. 2025Vision-Language Models for Autonomous Driving: CLIP-Based Dynamic Scene Understandingcited by 9
  3. 2025WeatherPrompt: Multi-modality Representation Learning for All-Weather Drone Visual Geo-Localizationcited by 7
  4. 2024BLIP: Facilitating the Exploration of Undesirable Consequences of Digital Technologiescited by 6
  5. 2025EvdCLIP: Improving Vision-Language Retrieval with Entity Visual Descriptions from Large Language Modelscited by 6
  6. 2025DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrievalcited by 4
  7. 2024RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-trainingcited by 3
  8. 2025Astrea: A MOE-based Visual Understanding Model with Progressive Alignmentcited by 3
  9. 2024LowCLIP: Adapting the CLIP Model Architecture for Low-Resource Languages in Multimodal Image Retrieval Taskcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Multi-View Mixture-of-Experts with Vision-Language Reranking for Cross-View Object Geo-Localizationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026UniGeo: A Multi-modal Large Language Model for Text-Guided Cross-View Geo-Localization
  2. 2026SkyLink: A Large Vision-Language Model Driven Re-ranking Framework for Cross-View UAV geolocalization
  3. 2025SMGeo: Cross-View Object Geo-Localization with Grid-Level Mixture-of-Experts
  4. 2026Turning Generators into Retrievers: Unlocking MLLMs for Natural Language-Guided Geo-Localization
  5. 2025MobileGeo: Exploring Hierarchical Knowledge Distillation for Resource-Efficient Cross-view Drone Geo-Localization
  6. 2025Team Xiaomi EV-AD VLA: Caption-Guided Retrieval System for Cross-Modal Drone Navigation -- Technical Report for IROS 2025 RoboSense Challenge Track 4
  7. 2026S3Geo: Structure-Semantic Synergistic Learning for Cross-View Geo-Localization
  8. 2026Global Cross-Modal Geo-Localization: A Million-Scale Dataset and a Physical Consistency Learning Framework