AI Paper Atlas

Research map / Benchmarks / MuirBench

MuirBench leaderboard

14 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on MuirBench. Best accuracy: 81.8 (CoViP, ICML 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

MuirBench · accuracy

14 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
181.8CoViP
Qwen3-VL-8B
Contextualized Visual Personalization in Vision-Language Models
ICML 2026 · Table 4
Multimodal LLMs
277.2L2-VMAS
Qwen3-VL-8B-Thinking
Dual Latent Memory for Visual Multi-agent System
ICML 2026 · Table 4
LLM agents
369.8Complete VisMem
Qwen2.5-VL-7B
VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models
CVPR 2026 · Table 4
Multimodal LLMs
462Qwen2.5-VL-7B + CAPL
Qwen2.5-VL-7B
Looking Back and Forth: Cross-Image Attention Calibration and Attentive Preference Learning for Multi-Image Hallucination Mitigation
ECCV 2026 · Table 1
Multimodal LLMs
561.5Vision-G1
Qwen2.5-VL-7B
Vision-G1: Towards General Reasoning Vision-Language Models via Reinforcement Learning
AAAI 2026 · Table 3
Multimodal LLMs
658.2GeM-VG
Qwen2-VL-7B
GeM-VG: Towards Generalized Multi-image Visual Grounding with Multimodal Large Language Models
AAAI 2026 · Table 4
Multimodal LLMs
754.9+ AR (Ours)
Qwen3-VL-8B
Multiple Images Distract Large Multimodal Models via Attention Fragmentation
ECCV 2026 · Table 1
Multimodal LLMs
848.6LLaVA-OV + CcDPO
LLaVA-OV-7B
Zooming from Context to Cue: Hierarchical Preference Optimization for Multi-Image MLLMs
NeurIPS 2025 · Table: Main results on general
Multimodal LLMs
948.3LLaDA-V
LLaDA-8B-Instruct
LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning
CVPR 2026 · Table 2
Multimodal LLMs
1046.7SFT + SPO (ours)
SFT-7B (LLaVA-OV-7B)
Structured Policy Optimization: Enhance Large Vision-Language Model via Self-referenced Dialogue
ICCV 2025 · Table 2
Multimodal LLMs
4 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.