Trending research and the full catalog - each paper linked to the benchmarks, methods, and models it introduces.
27 May 2026
Vision-language models (VLMs) commonly formulate visual grounding and detection as a coordinate-token generation problem, serializing each 2D box into multiple 1D tokens that are learned and decoded largely independently.
1 May 2026
Large language models are increasingly used in K-12 education, but existing benchmarks mainly test exam question answering rather than understanding how curriculum knowledge is structured and visually presented. We call this capability curriculum cognition.
Yan Shu, Nicu Sebe, Bin Ren et al. · 19 Mar 2026
Vision-language models (VLMs) have shown promise in earth observation (EO), yet they struggle with tasks that require grounding complex spatial reasoning in precise pixel-level visual representations.