AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

ECoSim: Data Efficient Fine-Tuning for Controllable Traffic Simulation

Yu-Hsiang Chen, WEI-JER Chang, Yi-Ting Chen, Masayoshi TOMIZUKA

ECCV 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Data-driven traffic simulation · 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
add sketch FiLM adapter trained on 1% paired data to VBD-CLVBD-CL · WOSACmADE: 2.7223 -> 0.9645Improved
add sketch FiLM adapter trained on 1% paired data to SMART-tiny-CLSFTSMART-tiny-CLSFT · WOSACmADE: 1.5044 -> 0.2561Improved
add sketch adapter to VBD-CLVBD-CL · WOSACMeta score: 0.7186 -> 0.7432Improved
add text FiLM adapter to SMART-tiny-CLSFTSMART-tiny-CLSFT · WOSACmADE: 1.5044 -> 1.3537Improved
FiLM adapter on ProSim with 1% data versus original ProSim with 100% data (sketch)ProSim · Same-backbone ProSim comparisonmADE: 1.099 -> 1.130No clear effect
FiLM adapter on ProSim with 1% data versus original ProSim with 100% data (text)ProSim · Same-backbone ProSim comparisonmADE: 2.330 -> 1.824Improved
use identity initialization versus random initialization for FiLM (ablation)FiLM adapter · WOSAC sketch (SMART, 5,000 scenarios)realism early in trainingImproved
use multiplicative FiLM instead of additive modulation (ablation)FiLM adapter · WOSAC sketch (SMART, 5,000 scenarios)mADE / convergenceImproved
use dynamic (re-encode per timestep) conditioning instead of static for sketch (ablation)FiLM adapter · WOSAC sketch controlmADE: 1.0598 -> 0.3970Improved
use dynamic instead of static conditioning for latent (ablation)FiLM adapter · WOSAC latent controlmADE: 0.4842 -> 0.3151Improved
use context-matched retrieval instead of random agent selection for long-tail transfer (ablation)Long-tail synthesis · Long-tail scenarioscollision rate: 0.3175 -> 0.1574Improved
restrict control signals to WOSAC target agents instead of all valid agents (sketch) (ablation)FiLM adapter · WOSAC sketch controlmADE: 0.2561 -> 0.4602Hurt

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