2 citations · 3 across the 26 of their papers we have counts for
29 papers
Visual Jev Rewards: Reference-Bound Verification for Multi-Subject Image Generation
Baoteng Li, Wenzhuo Wu, Kongming Liang +1
Multi-subject image generation requires rewards that verify whether requested attributes, actions, and relations hold for the specified reference subjects. Subject presence alone d…
VOR-Bench: A Human Perception-Driven Benchmark for Video Object Removal
Haonan Huang, Tianrui Qiu, Xianghao Zang +10
Despite its crucial role in video object removal (VOR), existing evaluation paradigms face two critical limitations: questionable references and a misalignment between tradi- tiona…
VGIF-Score: Interpretable and Diagnostic Evaluation of Spatio-Temporal Instruction Following in Video Generation
Songyu Xu, Xin Wang, Qiang Chen +6
Recent video generation models (VGMs) have made substantial progress in visual fidelity, yet their ability to follow long, compositional instructions remains insufficiently evaluat…
MMBench-Live: A Continuously Evolving Benchmark for Multimodal Models
Yuanzhi Liu, Shousheng Zhao, Bo Zhou +2
Evaluation benchmarks are essential for assessing vision-language models (VLMs), but most multimodal benchmarks are static, making them vulnerable to temporal staleness, data conta…
Curriculum Group Policy Optimization: Adaptive Sampling for Unleashing the Potential of Text-to-Image Generation
Baoteng Li, Xianghao Zang, Xinran Wang +8
Text-to-Image (T2I) generation has achieved remarkable progress in recent years. Meanwhile, reinforcement learning methods, particularly those based on Group Relative Policy Optimi…
DataEvolver: Let Your Data Build and Improve Itself via Goal-Driven Loop Agents
Qisong Zhang, Wenzhuo Wu, Zhuangzhuang Jia +7
Constructing controllable visual data is a major bottleneck for image editing and multimodal understanding. Useful supervision is rarely produced by a single rendering pass; instea…
DetailVerifyBench: A Benchmark for Dense Hallucination Localization in Long Image Captions
Xinran Wang, Yuxuan Zhang, Xiao Zhang +7
Accurately detecting and localizing hallucinations is a critical task for ensuring high reliability of image captions. In the era of Multimodal Large Language Models (MLLMs), capti…
Generative Visual Chain-of-Thought for Image Editing
Zijin Yin, Tiankai Hang, Yiji Cheng +9
Existing image editing methods struggle to perceive where to edit, especially under complex scenes and nuanced spatial instructions. To address this issue, we propose Generative Vi…
Benchmarking Semantic Segmentation Models via Appearance and Geometry Attribute Editing
Zijin Yin, Bing Li, Kongming Liang +4
Semantic segmentation takes pivotal roles in various applications such as autonomous driving and medical image analysis. When deploying segmentation models in practice, it is criti…
Hepato-LLaVA: An Expert MLLM with Sparse Topo-Pack Attention for Hepatocellular Pathology Analysis on Whole Slide Images
Yuxuan Yang, Zhonghao Yan, Yi Zhang +6
Hepatocellular Carcinoma diagnosis relies heavily on the interpretation of gigapixel Whole Slide Images. However, current computational approaches are constrained by fixed-resoluti…
Geometric Image Editing via Effects-Sensitive In-Context Inpainting with Diffusion Transformers
Shuo Zhang, Wenzhuo Wu, Huayu Zhang +8
Recent advances in diffusion models have significantly improved image editing. However, challenges persist in handling geometric transformations, such as translation, rotation, and…
Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting
Muxi Diao, Lele Yang, Wuxuan Gong +6
Supervised Fine-Tuning (SFT) is the standard paradigm for domain adaptation, yet it frequently incurs the cost of catastrophic forgetting. In sharp contrast, on-policy Reinforcemen…
AutoRed: A Free-form Adversarial Prompt Generation Framework for Automated Red Teaming
Muxi Diao, Yutao Mou, Keqing He +6
The safety of Large Language Models (LLMs) is crucial for the development of trustworthy AI applications. Existing red teaming methods often rely on seed instructions, which limits…
MedReasoner: Reinforcement Learning Drives Reasoning Grounding from Clinical Thought to Pixel-Level Precision
Zhonghao Yan, Muxi Diao, Yuxuan Yang +7
Accurately grounding regions of interest (ROIs) is critical for diagnosis and treatment planning in medical imaging. While multimodal large language models (MLLMs) combine visual p…
FairHuman: Boosting Hand and Face Quality in Human Image Generation with Minimum Potential Delay Fairness in Diffusion Models
Yuxuan Wang, Tianwei Cao, Huayu Zhang +3
Image generation has achieved remarkable progress with the development of large-scale text-to-image models, especially diffusion-based models. However, generating human images with…
Harnessing Caption Detailness for Data-Efficient Text-to-Image Generation
Xinran Wang, Muxi Diao, Yuanzhi Liu +4
Training text-to-image (T2I) models with detailed captions can significantly improve their generation quality. Existing methods often rely on simplistic metrics like caption length…
CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generation
Xinran Wang, Songyu Xu, Xiangxuan Shan +6
Cinematography is a cornerstone of film production and appreciation, shaping mood, emotion, and narrative through visual elements such as camera movement, shot composition, and lig…
DriveRX: A Vision-Language Reasoning Model for Cross-Task Autonomous Driving
Muxi Diao, Lele Yang, Hongbo Yin +5
Effective autonomous driving hinges on robust reasoning across perception, prediction, planning, and behavior. However, conventional end-to-end models fail to generalize in complex…
Toward Generalizable Forgery Detection and Reasoning
Yueying Gao, Dongliang Chang, Bingyao Yu +5
Accurate and interpretable detection of AI-generated images is essential for mitigating risks associated with AI misuse. However, the substantial domain gap among generative models…
PGP-SAM: Prototype-Guided Prompt Learning for Efficient Few-Shot Medical Image Segmentation
Zhonghao Yan, Zijin Yin, Tianyu Lin +3
The Segment Anything Model (SAM) has demonstrated strong and versatile segmentation capabilities, along with intuitive prompt-based interactions. However, customizing SAM for medic…
OmniEraser: Remove Objects and Their Effects in Images with Paired Video-Frame Data
Runpu Wei, Zijin Yin, Shuo Zhang +8
Inpainting algorithms have achieved remarkable progress in removing objects from images, yet still face two challenges: 1) struggle to handle the object's visual effects such as sh…
From Simple to Professional: A Combinatorial Controllable Image Captioning Agent
Xinran Wang, Muxi Diao, Baoteng Li +3
The Controllable Image Captioning Agent (CapAgent) is an innovative system designed to bridge the gap between user simplicity and professional-level outputs in image captioning tas…
Detailed Object Description with Controllable Dimensions
Xinran Wang, Haiwen Zhang, Baoteng Li +5
Object description plays an important role for visually impaired individuals to understand and compare the differences between objects. Recent multimodal large language models(MLLM…
Polyp-E: Benchmarking the Robustness of Deep Segmentation Models via Polyp Editing
Runpu Wei, Zijin Yin, Kongming Liang +6
Automatic polyp segmentation is helpful to assist clinical diagnosis and treatment. In daily clinical practice, clinicians exhibit robustness in identifying polyps with both locati…