AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Unlocking Zero-Shot Geospatial Reasoning via Indirect Rewards

Chenhui Xu, Fuxun Yu, Michael J. Bianco, Jacob Kovarskiy, Raphael Tang, Qi Zhang, Zirui Xu, Will LeVine, Brandon Dubbs, Heming Liao, Cassandra Burgess, Suvam Bag and 6 more

ICML 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Open-vocabulary alignment from VLMs · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add indirect-reward RL (cross-view pairing) after scaffolding SFT (ablation)Qwen2.5-VL-7B · CV-Cities cross-view pairing (in-distribution)accuracy: 23.1% -> 82.4%Improved
train with SFT on positive examples only instead of RL (ablation)Qwen2.5-VL-7B · CV-Cities cross-view pairing (in-distribution)accuracy: 19.0% -> 23.1%No clear effect
add scaffolding SFT before RL (ablation)Geo-R1-Zero · CV-Cities cross-view pairing (in-distribution)accuracy: 78.1% -> 82.4%Improved
add scaffolding SFT before RL (ablation)Geo-R1-Zero · CV-Cities cross-view pairing (in-distribution)completion length: 587.4 -> 378.8Improved
SFT alone causes content duplication (ablation)Geo-SFT · CV-Cities cross-view pairing (in-distribution)completion length: 204.6 -> 1127.6Hurt
apply Geo-R1 indirect-reward RLQwen2.5-VL-7B · IMAGEO-GSScity accuracy: 0.277 -> 0.327Improved
apply Geo-R1 to a different backboneInternVL3-8B · IMAGEO-GSScity accuracy: 0.146 -> 0.313Improved
apply Geo-R1 to InternVL3-8B on the in-distribution pairing taskInternVL3-8B · CV-Cities cross-view pairing (in-distribution)accuracy: 20.3% -> 84.7%Improved
indirect reward instead of task-direct RL reward (GLOBE-7B)Geo-R1 vs GLOBE-7B · MP16-Reasonaccuracy at distance thresholds: 17.98 vs 17.99 (1km); 93.56 vs 92.52 (2500km)No clear effect
Geo-R1 vs GeoCLIP task-specific modelGeo-R1 · IMAGEO-GSSmedian distance (km): 266.8987 -> 69.4008Improved
add SFT scaffolding vs RL on general-purpose benchmarks (ablation)Geo-SFT vs Geo-R1 · MEGA-Bench, GPQA, MMMUaccuracyHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy