AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Personalizing MLLMs via Reinforced Multimodal Reference Game

Deepayan Das, Davide Talon, Yiming Wang, Massimiliano Mancini, Elisa Ricci

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Unified any-modality language models · 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
train speaker with reference game (RRG) vs zero-shot speaker (ablation)Qwen2-VL-7B · MyVLM captioningF1: 89.3 -> 95.0Improved
train speaker with reference game vs zero-shot speaker (ablation)Qwen2-VL-7B · Yo'LLaVA recognitionWtd: 89.3 -> 94.7Improved
train speaker instead of listener (ablation)RRG · MyVLM recognitionWtd: 89.7 -> 91.8Improved
train speaker instead of listener (ablation)RRG · Yo'LLaVA captioningF1: 86.3 -> 88.6Improved
add reference game with distractors vs pairwise speaker-training (ablation)RRG · MyVLM captioningF1: 92.3 -> 95.0Improved
soft normalized reward instead of binary reward (ablation)RRG · MyVLM captioningF1: 93.4 -> 95.0Improved
soft normalized reward instead of binary reward (ablation)RRG · Yo'LLaVA captioningF1: 85.5 -> 88.6Improved
soft normalized reward instead of binary reward (ablation)RRG · MyVLM recognitionWtd: 92.3 -> 91.8Hurt
use hard instead of easy candidates (ablation)RRG · MyVLM captioningF1: 92.7 -> 95.0Improved
use hard instead of half-easy candidates (ablation)RRG · MyVLM captioningF1: 93.8 -> 95.0Improved
add hard negatives to hard positives (ablation)RRG · MyVLM captioningF1: 92.1 -> 95.0Improved
add hard positives to hard negatives (ablation)RRG · MyVLM captioningF1: 92.7 -> 95.0Improved

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