AI Paper Atlas

Research map / Multi-agent systems and games / Cooperative multi-agent RL

TurboTrain: Towards Efficient and Balanced Multi-Task Learning for Multi-Agent Perception and Prediction

Zewei Zhou, Seth Z. Zhao, Tianhui Cai, Zhiyu Huang, Bolei Zhou, Jiaqi Ma

ICCV 2025 · Multi-agent systems and games › Cooperative multi-agent RL · approach: MARL benchmarks and grouping · 6 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
add multi-agent spatiotemporal pretraining (ablation)V2XPnP · V2XPnP-Seq-VCEPA: 15.0 -> 43.4Improved
include multi-agent fusion module in pretraining (ablation)TurboTrain pretraining · V2XPnP-Seq-VCEPA: 40.8 -> 43.4Improved
use both point and occupancy reconstruction losses (ablation)TurboTrain pretraining · V2XPnP-Seq-VCEPA: 40.2/40.8 -> 43.4Improved
add conflict-suppressing balance stage (ablation)V2XPnP pretrained · V2XPnP-Seq-VCEPA: 43.4 -> 45.5Improved
replace conflict-suppression with GradNorm (ablation)TurboTrain Balance · V2XPnP-Seq-VCEPA: 43.4 -> 34.2Hurt
balance at every gradient step instead of hybrid free/balanced (ablation)TurboTrain Balance · V2XPnP-Seq-VCAP@0.5: 72.2 -> 0.0Hurt
shorten free/balance interval to (1000,500) (ablation)TurboTrain Balance · V2XPnP-Seq-VCEPA: 45.5 -> 38.1Hurt
lengthen free/balance interval to (3000,1500) (ablation)TurboTrain Balance · V2XPnP-Seq-VCEPA: 45.5 -> 42.8Hurt
use all historical frames in reconstruction instead of half (ablation)TurboTrain pretraining · V2XPnP-Seq-VCEPA: 38.8 -> 43.4Improved
raise mask ratio from 0.7 to 0.9 (ablation)TurboTrain pretraining · V2XPnP-Seq-VCEPA: 43.4 -> 42.1Hurt
replace manual multi-stage training with TurboTrainV2XPnP · V2XPnP-Seq-VCEPA: 41.8 -> 45.5Improved
replace manual training with TurboTrain on F-CooperF-Cooper · V2XPnP-Seq-VCAP@0.5: 66.5 -> 66.3No clear effect

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