- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes GeoEPS, a training-free framework for ultra-high-resolution remote-sensing VQA tasks. GeoEPS claims that making relevant evidence accessible (by cropping) is not enough, and therefore proposes EAP and CES to priors building and evidences searching, respectively. On XLRS-Bench and RSHR-Bench, it lifts Qwen3-VL-8B from 48.8% to 61.0% and from 41.3% to 53.7%, with consistent gains across other frozen VLMs.
Critical strengths
- The paper's motivation and identified problem are clear, and are well supported by ablations.
- The proposed method is training-free, architecture-agnostic, and easy to integrate.
- The performance gains are consistent across multiple models and benchmarks.
Critical weaknesses
- The proposed method incur additional inference costs in model calls, and no runtime or memory costs are reported. If GeoEPS and other methods are evaluated under a fixed model calls, will the gains hold still?
- CES only adds little for open-source MLLMs in Table 3, while effectively boosts performance for remote sensing MLLMs. Why?
- In Sec. B.3, it seems that the query-conditioned selection relies on three regex rules fitted to the benchmark question templates. Can it generalize?
Questions for authors
Please see weaknesses