AI Paper Atlas

Research map / Time series / Causal and generative time series

ITPP: Learning Disentangled Event Dynamics in Marked Temporal Point Processes

Wang-Tao Zhou, Zhao Kang, Ke Yan, Ling Tian

AAAI 2026 · Time series › Causal and generative time series · approach: Generative temporal point processes · 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 channel-independent encoding/decoding instead of channel mixing (ablation)ITPP · StackOverflow and Earthquakelikelihood and prediction metricsImproved
add type-aware inverted self-attention across channels (ablation)ITPP · StackOverflow and Earthquakelikelihood and prediction metricsImproved
use ITPP over best baseline in joint NLLODE-based MTPP · StackOverflowTM-NLL: 2.198 -> 2.106Improved
use ITPP over best baseline in joint NLLODE-based MTPP · TaobaoTM-NLL: -1.176 -> -1.189Improved
use ITPP over NHP for mark predictionODE-based MTPP · MIMICF1: 0.850 (NHP) vs 0.856 (ITPP)Improved
use self-attention encoders (THP, SAHP, AttNHP) instead of RNNsMTPP baselines · StackOverflowTM-NLL: THP 2.325 vs NHP 2.233No clear effect
use channel-mixing ODE models (NeuralODE, ODE-GRU) without channel independenceODE-based MTPP · EarthquakeoverfittingHurt
add channel independence and inverted attention for overfitting resistanceITPP · Earthquaketest lossImproved

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