ArchWorld benchmark at NeurIPS 2026 exposes regional gaps in 3D foundation model reconstruction
ang3linawang · x · 2026-10-20
- A NeurIPS 2026 paper introduces ArchWorld, a geographically diverse 3D scene benchmark measuring how well 3D foundation models reconstruct architecture from around the world.
- It also proposes ArchAttend, an inference-time intervention that reduces regional disparities in reconstruction quality.
- Further details are in the author's thread linked from the original post.
Related event: NeurIPS Paper Introduces ArchWorld 3D Reconstruction Benchmark(2 posts)→
More from Research
- Stanford and Databricks use AI agents to reproduce medical findings and test analytical robustness — ChengleiSi · 2026-10-23
- EMNLP paper: diffusion LMs internally encode latent denoising timestep representations — gsarti_ · 2026-10-23
- KU Leuven and VIB open two Group Leader professorships in AI for Biology, start 2027 — jpillowtime · 2026-10-23
- Subspace Tuning curbs LLM catastrophic forgetting by freezing principal singular directions — scottniekum · 2026-10-23
- Perceptic launches PercepticOS, an AI workspace for 'scientific superintelligence' — nathanbenaich · 2026-10-23
- EPFL's Bosselut to talk long context as test-time learning at ELLIS seminar — andre_t_martins · 2026-10-23