7 citations · 23 across the 49 of their papers we have counts for
51 papers
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…
One Reflection Is Not Enough: Self-Correcting Autonomous Research via Multi-Hypothesis Failure Attribution
Jie Ma, Binfei Chu, Jie Gao +6
Autonomous research agents can now draft hypotheses, write code, run experiments, and produce papers, but they remain brittle when experiments fail. Under the prevailing paradigm,…
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…
Plan Before Search: Search Agents Need Plan
Zhipeng Qian, Zihan Liang, Yufei Ma +7
Training large language models as retrieval-augmented reasoning agents typically combines reinforcement learning with an SFT cold start distilled from a stronger model. However, th…
Look on Demand: A Cognitive Scheduling Framework for Visual Evidence Acquisition in Multimodal Reasoning
Yang Zhang, Xiaoshuai Sun, Rui Zhao +5
Existing multimodal reasoning approaches predominantly follow two paradigms: converting visual inputs into text prior to reasoning, or performing end-to-end reasoning within a unif…
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…