Pith. sign in

REVIEW 8 cited by

Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2501.05767 v3 pith:O3P5L7RM submitted 2025-01-10 cs.CL cs.AIcs.CV

Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models

You Li , Heyu Huang , Chi Chen , Kaiyu Huang , Chao Huang , Zonghao Guo , Zhiyuan Liu , Jinan Xu
show 3 more authors
Yuhua Li Ruixuan Li Maosong Sun
This is my paper
classification cs.CL cs.AIcs.CV
keywords groundingmulti-imageexistingfree-formimagesmllmsmodelmodels
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

The recent advancement of Multimodal Large Language Models (MLLMs) has significantly improved their fine-grained perception of single images and general comprehension across multiple images. However, existing MLLMs still face challenges in achieving precise grounding in complex multi-image scenarios. To address this, we first explore a Chain-of-Thought (CoT) framework that integrates single-image grounding with multi-image comprehension. While partially effective, it remains unstable and struggles to capture abstract visual information due to its non-end-to-end nature. Therefore, we introduce Migician, the first multi-image grounding model capable of performing free-form and accurate grounding across multiple images. To support this, we present the MGrounding-630k dataset, which comprises data for several multi-image grounding tasks derived from existing datasets, along with newly generated free-form grounding instruction-following data. Furthermore, we propose MIG-Bench, a comprehensive benchmark specifically designed for evaluating multi-image grounding capabilities. Experimental results demonstrate that our model achieves significantly superior multi-image grounding capabilities, outperforming the best existing MLLMs by 24.94% and even surpassing much larger 70B models. Our code, model, dataset, and benchmark are fully open-sourced at https://migician-vg.github.io/.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. DiCoBench: Benchmarking Multi-Image Fine-Grained Perception via Differential and Commonality Visual Cues

    cs.CV 2026-06 unverdicted novelty 7.0

    DiCoBench is a new high-resolution multi-image benchmark exposing large gaps between top MLLMs and human performance (98.3%) on differential and commonality visual cue perception.

  2. CGC: Compositional Grounded Contrast for Fine-Grained Multi-Image Understanding

    cs.CV 2026-04 unverdicted novelty 7.0

    CGC improves fine-grained multi-image understanding in MLLMs by constructing contrastive training instances from existing single-image annotations and adding a rule-based spatial reward, achieving SOTA on MIG-Bench an...

  3. Training Multi-Image Vision Agents via End2End Reinforcement Learning

    cs.CV 2025-12 unverdicted novelty 7.0

    IMAgent trains a multi-image vision agent via pure end-to-end RL with visual reflection tools and a two-layer motion trajectory masking strategy, reaching SOTA on single- and multi-image benchmarks while revealing too...

  4. RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension

    cs.CV 2025-12 conditional novelty 6.0

    RefBench-PRO organizes REC into attribute, position, interaction, relation, commonsense, and reject tasks; no tested MLLM exceeds 72%, and Ref-R1 raises Qwen2.5-VL-7B from 57.6 to 69.4 on it.

  5. From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models

    cs.CL 2026-06 unverdicted novelty 5.0

    The survey formalizes MLLM perception as a unified vision-language capability and traces its evolution via a new five-stage taxonomy while outlining future challenges.

  6. Does Seeing More Mean Knowing More? Mono-Anchored Advantage Normalization for Multi-Source Visual Reasoning

    cs.CV 2026-05 unverdicted novelty 5.0

    MARS introduces mono-anchored advantage normalization to quantify information gain from multi-source integration in RLVR, yielding 3.2% and 4.9% gains on GRPO and DAPO.

  7. Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning

    cs.CV 2025-07 unverdicted novelty 4.0

    A pipeline of chain-of-thought data synthesis, LoRA-based supervised fine-tuning, rejection sampling, and rule-based reinforcement learning raises multi-image grounding accuracy by 9.04% on MIG-Bench and 4.41% on aver...

  8. Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey

    cs.CV 2025-03 unverdicted novelty 2.0

    The paper provides the first comprehensive survey of multimodal chain-of-thought reasoning, including foundational concepts, a taxonomy of methodologies, application analyses, challenges, and future directions.