Tag
The paper introduces FairRSFM, a biome-aware benchmark and debiasing framework that reveals ecological performance disparities in remote-sensing foundation models, evaluating Prithvi-EO-2.0, SatMAE, and DOFA across four downstream datasets alongside mitigation baselines like BOLP, Dynamic Biome Reweighting, and GroupDRO.
This paper analyzes why compression statistics for LLM pruning can be reproducible yet select suboptimal endpoints, introducing information boundaries and observation fibers to model the gap. It proposes group-resolved and model-specific mask selection methods that improve worst-group perplexity across dense LLMs and OLMoE.