AI Paper Atlas

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

From Discriminative to Generative: A Diffusion-Based Paradigm for Multi-Agent Collaborative Perception

Kexin Gong, Puyi Yao, Guiyang Luo, Quan Yuan, Tiange Fu, Hui Zhang, Jinglin Li

AAAI 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Collaborative multi-agent perception · 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 diffusion-based generative supervision (ablation)DiGS-CP two-stage fusion · OPV2VAP@0.7: 89.07% -> 93.53%Improved
add generative supervision (ablation)DiGS-CP two-stage fusion · OPV2VAP@0.5: 95.35% -> 96.75%Improved
use cross-attention conditioning instead of mean-based conditioning (ablation)DiGS-CP diffusion U-Net · OPV2VAP@0.7: 92.39% -> 93.53%Improved
use cross-attention conditioning instead of concatenation (ablation)DiGS-CP diffusion U-Net · OPV2VAP@0.7: 92.63% -> 93.53%Improved
add distance-weighted fusion instead of confidence-only weighting (ablation)DiGS-CP · OPV2VAP@0.7: 93.12% -> 93.53%Improved
train with generative supervision (cross-domain OPV2V to V2XSet)DiGS-CP · V2XSet cross-domainAP@0.7 drop: 0.8301 -> 0.8199 (drop 1.02%) vs baselines dropping 12.12% to 17.83%Improved
set confidence threshold tau to 0.2 rather than 0.1, 0.3 or 0.4 (ablation)DiGS-CP stage 1 · OPV2VAP@0.3/0.5/0.7Mixed
increase diffusion steps T from 500 to 1000, then beyond (ablation)DiGS-CP diffusion model · OPV2VAP@0.3/0.5/0.7Mixed
DiGS-CP vs CoSDH on OPV2V AP@0.5DiGS-CP · OPV2VAP@0.5: 96.83% -> 96.75%No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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