7 citations · 23 across the 49 of their papers we have counts for
46 papers · 1 filter
Capturing Token Tendencies for Training-Free Token Pruning in Multimodal Large Language Models
Jie Ma, Zhike Qiu, Jie Gao +4
While visual token pruning is essential for efficient Multimodal Large Language Models (MLLMs), existing training-free methods suffer from a critical limitation: they rely on stati…
An Extensive Benchmark for Single-round and Multi-round Instruction-based Image Editing
Yiwei Ma, Ke Ye, Weihuang Lin +4
In recent years, there have been notable advancements in the area of instruction-based image editing (IIE), which focuses on the automatic alteration of input images using a model.…
Look Less, Reason More: Block-wise Attention Skipping for Efficient Multimodal LLMs
Jie Ma, Zhike Qiu, Jiayi Ji +2
Multimodal Large Language Models (MLLMs) face a significant inference bottleneck due to the quadratic computational cost of self-attention over long visual token sequences. However…
ForensicConcept: Transferable Forensic Concepts for AIGI Detection
Menyanshu Zhou, Ziyin Zhou, Ke Sun +4
AI-generated image detectors achieve high accuracy on in-distribution data but often fail on unseen generators. A key obstacle to understanding this failure is the black-box nature…
Evading Visual Aphasia: Contrastive Adaptive Semantic Token Pruning for Vision-Language Models
Jie Ma, Yihang Liu, Zhike Qiu +2
Are low-attention visual tokens truly redundant in vision-language reasoning? Existing pruning methods often assume so, ranking visual tokens by shallow text-to-image attention and…
EvoTale: Continual Character Customization for Expanding Story Worlds
Jinlu Zhang, Qiyun Wang, Baoxiang Du +6
Character-centric story visualization aims to synthesize coherent image sequences that depict narrative events and interactions while preserving recurring character identities. In…
Test-Time Computing for Referring Multimodal Large Language Models
Mingrui Wu, Hao Chen, Jiayi Ji +5
We propose ControlMLLM++, a novel test-time adaptation framework that injects learnable visual prompts into frozen multimodal large language models (MLLMs) to enable fine-grained r…
MICON-Bench: Benchmarking and Enhancing Multi-Image Context Image Generation in Unified Multimodal Models
Mingrui Wu, Hang Liu, Jiayi Ji +2
Recent advancements in Unified Multimodal Models (UMMs) have enabled remarkable image understanding and generation capabilities. However, while models like Gemini-2.5-Flash-Image s…
CSMCIR: CoT-Enhanced Symmetric Alignment with Memory Bank for Composed Image Retrieval
Zhipeng Qian, Zihan Liang, Yufei Ma +7
Composed Image Retrieval (CIR) enables users to search for target images using both a reference image and manipulation text, offering substantial advantages over single-modality re…
M4-BLIP: Advancing Multi-Modal Media Manipulation Detection through Face-Enhanced Local Analysis
Hang Wu, Ke Sun, Jiayi Ji +2
In the contemporary digital landscape, multi-modal media manipulation has emerged as a significant societal threat, impacting the reliability and integrity of information dissemina…
CIR-CoT: Towards Interpretable Composed Image Retrieval via End-to-End Chain-of-Thought Reasoning
Weihuang Lin, Yiwei Ma, Jiayi Ji +2
Composed Image Retrieval (CIR), which aims to find a target image from a reference image and a modification text, presents the core challenge of performing unified reasoning across…
HRSeg: High-Resolution Visual Perception and Enhancement for Reasoning Segmentation
Weihuang Lin, Yiwei Ma, Xiaoshuai Sun +4
The reasoning segmentation task involves segmenting objects within an image by interpreting implicit user instructions, which may encompass subtleties such as contextual cues and o…
MIHBench: Benchmarking and Mitigating Multi-Image Hallucinations in Multimodal Large Language Models
Jiale Li, Mingrui Wu, Zixiang Jin +5
Despite growing interest in hallucination in Multimodal Large Language Models, existing studies primarily focus on single-image settings, leaving hallucination in multi-image scena…
Inter2Former: Dynamic Hybrid Attention for Efficient High-Precision Interactive
You Huang, Lichao Chen, Jiayi Ji +3
Interactive segmentation (IS) improves annotation efficiency by segmenting target regions from user prompts, with widespread applications in real-world scenarios. Current approache…
AIGI-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Models
Ziyin Zhou, Yunpeng Luo, Yuanchen Wu +7
The rapid development of AI-generated content (AIGC) technology has led to the misuse of highly realistic AI-generated images (AIGI) in spreading misinformation, posing a threat to…
SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence
Ziyang Gong, Wenhao Li, Oliver Ma +7
Multimodal Large Language Models (MLLMs) have achieved remarkable progress in various multimodal tasks. To pursue higher intelligence in space, MLLMs require integrating multiple s…
RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning
Mingrui Wu, Lu Wang, Pu Zhao +14
Despite recent progress in text-to-image (T2I) generation, existing models often struggle to faithfully capture user intentions from short and under-specified prompts. While prior…
An Efficient and Mixed Heterogeneous Model for Image Restoration
Yubin Gu, Yuan Meng, Kaihang Zheng +5
Image restoration~(IR), as a fundamental multimedia data processing task, has a significant impact on downstream visual applications. In recent years, researchers have focused on d…
Zooming In on Fakes: A Novel Dataset for Localized AI-Generated Image Detection with Forgery Amplification Approach
Lvpan Cai, Haowei Wang, Jiayi Ji +4
The rise of AI-generated image tools has made localized forgeries increasingly realistic, posing challenges for visual content integrity. Although recent efforts have explored loca…
MLLM-Selector: Necessity and Diversity-driven High-Value Data Selection for Enhanced Visual Instruction Tuning
Yiwei Ma, Guohai Xu, Xiaoshuai Sun +4
Visual instruction tuning (VIT) has emerged as a crucial technique for enabling multi-modal large language models (MLLMs) to follow user instructions adeptly. Yet, a significant ga…
QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension
Yongdong Luo, Wang Chen, Xiawu Zheng +8
Recent advances in long video understanding typically mitigate visual redundancy through visual token pruning based on attention distribution. However, while existing methods emplo…
IPDN: Image-enhanced Prompt Decoding Network for 3D Referring Expression Segmentation
Qi Chen, Changli Wu, Jiayi Ji +3
3D Referring Expression Segmentation (3D-RES) aims to segment point cloud scenes based on a given expression. However, existing 3D-RES approaches face two major challenges: feature…
RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation
Changli Wu, Qi Chen, Jiayi Ji +7
3D Referring Expression Segmentation (3D-RES) aims to segment 3D objects by correlating referring expressions with point clouds. However, traditional approaches frequently encounte…
Mixed Degradation Image Restoration via Local Dynamic Optimization and Conditional Embedding
Yubin Gu, Yuan Meng, Xiaoshuai Sun +3
Multiple-in-one image restoration (IR) has made significant progress, aiming to handle all types of single degraded image restoration with a single model. However, in real-world sc…