AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Interactive Person Retrieval via Multi-Turn Multimodal Conversation

Yang Bai, Tingfeng Wang, Bin Yang, Min Cao, Jinqiao Wang, Mang Ye

ICML 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Multimodal retrieval-augmented modeling

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 ATE (per-turn encoding) in place of concatenating the dialogue: accuracy (ablation)MNEMO · MInterPEDES MInterPRR-1: 91.51 -> 88.90Hurt
add ATE in place of concatenating the dialogue: training time (ablation)MNEMO · MInterPEDES MInterPRtraining time (ms): 661.78 -> 176.25Improved
add ATE in place of concatenating the dialogue: inference time (ablation)MNEMO · MInterPEDES MInterPRinference time (ms): 63.76 -> 22.77Improved
add DMA on top of ATE (ablation)MNEMO · MInterPEDES MInterPRR-1: 88.90 -> 92.26Improved
add DMA on top of ATE (ablation)MNEMO · MInterPEDES MInterPRmAP: 76.99 -> 80.31Improved
add DMA on top of ATE: extra inference cost (ablation)MNEMO · MInterPEDES MInterPRinference time (ms): 22.77 -> 24.07No clear effect
full MNEMO (ATE+DMA) vs concatenation baseline (ablation)MNEMO · MInterPEDES MInterPRR-1: 91.51 -> 92.26Improved
increase static memory queries from 0 to 16 (ablation)DMA · MInterPEDES MInterPRR-1Improved
increase static memory queries beyond 16 (ablation)DMA · MInterPEDES MInterPRR-1No clear effect
remove dynamic memory queries (ablation)DMA · MInterPEDES MInterPRR-1Hurt
increase dynamic memory queries beyond 16 (ablation)DMA · MInterPEDES MInterPRR-1Hurt
add visual feedback turns on top of question-answering dialogueMNEMO vs MInterPR scenario · MInterPEDESR-1: 78.09 -> 92.26Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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