Neural Latents Benchmark

Logo

A Benchmark for Models of Neural Data


About
Datasets
NLB'21 Challenge Info
NLB'21 Codepack
NLB'21 EvalAI

Challenge Guidelines

Both phases of the NLB’21 Challenge have ended. Phase 1 of the challenge ended on 1/7/2022, won by AE Studio. Phase 2 of the challenge ended on 4/3/2022 and had multiple winners, including STNDT from Trung Le and the Shlizerman lab and RNN_F from Ganga Meghanath and the Makin lab. Since Phase 2, a number of interesting and competitive models have been submitted to the benchmark, including S5 from Jimmy Smith and the Linderman lab and Langevin Flows from Yue Song and the Perona Lab. You can view the full leaderboard as of January 2026 on EvalAI.

Though the EvalAI challenge is no longer accepting submissions, you can still evaluate your methods on the now-public test data available in the repo for our codepack.