SplatLab autonomously reproduces 3DGS papers, proposes extensions and writes the manuscript

arXivarXivPapers

SplatLab autonomously reproduces 3DGS papers, proposes extensions and writes the manuscript
arXiv / Seemandhar Jain and Manmohan Chandraker

Seemandhar Jain and Manmohan Chandraker present SplatLab, an autonomous research system for 3D Gaussian Splatting, accepted at NeurIPS 2026. Given a research prompt, a target-paper URL, or no input at all, it reproduces a published baseline, proposes an extension, trains and ablates across Mip-NeRF 360 and LLFF, writes the manuscript, and binds every reported number to a logged training run, refusing to terminate while any claim is unbacked.

Candidates mutate plugins from a verified-reproduction backbone and are scored in a cascade-weighted Elo tournament on measured GPU PSNR. On PSNR-targeted runs, SplatLab’s manuscripts beat their reproduced targets by +0.18 to +3.78 dB, including +3.78 dB on astrophotographic nebula rendering, for which the authors say no prior 3DGS method exists.

«It Writes the Paper» Comic