AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Energy-based Autoregressive Generation for Neural Population Dynamics

Ningling Ge, Sicheng Dai, Yu Zhu, Shan Yu

AAAI 2026 · Probabilistic and scientific modeling › Dynamical systems · approach: Latent dynamics models · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use strictly proper energy score (alpha<2) instead of alpha=2 (ablation)EAG energy loss · MC MazeDKL population spike count histogram: 0.0541 -> 0.0014Improved
use strictly proper energy score (alpha<2) instead of alpha=2 (ablation)EAG energy loss · MC MazeRMSE mean ISI: 0.051 -> 0.024Improved
vary alpha within [1,2) (ablation)EAG energy loss · MC MazeRMSE mean ISI: 0.022 to 0.033No clear effect
use energy loss instead of MSE in autoregressive transformer (ablation)EAG · MC Mazegeneration qualityImproved
replace diffusion sampling (LDNS-1000) with EAG-32 single-pass generationLDNS · MC Mazelatency: 330.64s -> 10.29sImproved
replace LDNS-1000 with EAG-32LDNS · MC MazeRMSE mean ISI: 32.4% gainImproved
replace LDNS with EAGLDNS · MC MazeRMSE mean ISI: 0.037 -> 0.024Improved
replace LDNS with EAGLDNS · Area2 BumpRMSE pairwise corr: 0.0076 -> 0.0075No clear effect
add EAG augmentation for decoder trainingNDT · MC Mazebehavior decoding: 0.776 -> 0.838Improved
add EAG augmentation for decoder trainingAutoLFADS · MC Mazebehavior decoding: 0.906 -> 0.911Improved
scale EAG augmentation from 2x to 4x (ablation)NDT · Area2 Bumpbehavior decoding: 0.621 -> 0.631No clear effect
condition on unseen velocity trajectories using EAG vs LDNSLDNS · MC Maze velocity decodingR2: 0.65 -> 0.89Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy