AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

ObjecTok: Learning Holistic and Robust Object Tokens for MLLMs

Sihan Wang, Xiyao Liu, Lianqing Liu, Zhi Han

AAAI 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Decoding-time hallucination mitigation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes ObjecTok, a framework that represents each object in an image with a single holistic object token instead of patch tokens, aiming to improve MLLM perception and reduce object hallucination.

Problem

Patch-based visual tokenization in multimodal large language models breaks object integrity, limiting perception and causing object-related hallucinations.

Approach

Generate one holistic token per object in an image so that each object is represented as an integral unit rather than fragmented across patches.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add object tokens to LLaVA-1.5ObjecTok-LLaVA · POPE (total)F1: 85.95 -> 88.31Improved
add geometric decoder in object encoder training (ablation)ObjecTok-LLaVA · MME Positionscore: 113.33 -> 140.00Improved
add geometric decoder in object encoder training (ablation)ObjecTok-LLaVA · MME Countscore: 165.00 -> 178.33Improved
add confidence embeddings (ablation)ObjecTok-LLaVA · MME Existencescore: 145.00 -> 195.00Improved
add confidence embeddings (ablation)ObjecTok-LLaVA · MME Positionscore: 140.00 -> 140.00No clear effect
add patch tokens alongside object tokens (ablation)ObjecTok-LLaVA · MME Commonsense Reasoningscore: 93.57 -> 137.86Improved
add patch tokens alongside object tokens (ablation)ObjecTok-LLaVA · MME Colorscore: 88.33 -> 170.00Improved
add object tokens to LLaVA-1.5ObjecTok-LLaVA · POPE AdversarialF1: 84.46 -> 85.60Improved

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