18 papers
Geometry-guided Emotion Modulation for Controllable and Photorealistic Emotional Talking Face Generation
Chenggong Hu, Shaoyin Ma, Yi Wang +3
Audio-driven emotional talking face generation aims to synthesize realistic videos with expressive facial dynamics. However, existing methods struggle to balance controllability an…
FlowForm: Synergizing Fluid Physics with Topological Consistency for Satellite Flood Synthesis
Zhang Weihui, Wang Ruizhi, Xu Hongye +3
Developing robust flood assessment models requires high-quality paired satellite imagery, yet such data remain scarce for flood-specific image generation. Although generative model…
Evolutionary Negative Module Pruning for Better LoRA Merging
Anda Cao, Zhuo Gou, Yi Wang +5
Merging multiple Low-Rank Adaptation (LoRA) experts into a single backbone is a promising approach for efficient multi-task deployment. While existing methods strive to alleviate i…
Beyond Matching to Tiles: Bridging Unaligned Aerial and Satellite Views for Vision-Only UAV Navigation
Kejia Liu, Haoyang Zhou, Ruoyu Xu +3
Recent advances in cross-view geo-localization (CVGL) methods have shown strong potential for supporting unmanned aerial vehicle (UAV) navigation in GNSS-denied environments. Howev…
Rethinking Token Reduction for Large Vision-Language Models
Yi Wang, Haofei Zhang, Qihan Huang +7
Large Vision-Language Models (LVLMs) excel in visual understanding and reasoning, but the excessive visual tokens lead to high inference costs. Although recent token reduction meth…
-RSMDE: 40 Faster and High-Fidelity Remote Sensing Monocular Depth Estimation
Ruizhi Wang, Weihan Li, Zunlei Feng +5
Real-time, high-fidelity monocular depth estimation from remote sensing imagery is crucial for numerous applications, yet existing methods face a stark trade-off between accuracy a…
DriveFix: Spatio-Temporally Coherent Driving Scene Restoration
Heyu Si, Brandon James Denis, Muyang Sun +9
Recent advancements in 4D scene reconstruction, particularly those leveraging diffusion priors, have shown promise for novel view synthesis in autonomous driving. However, these me…
SpatiaLQA: A Benchmark for Evaluating Spatial Logical Reasoning in Vision-Language Models
Yuechen Xie, Xiaoyan Zhang, Yicheng Shan +6
Vision-Language Models (VLMs) have been increasingly applied in real-world scenarios due to their outstanding understanding and reasoning capabilities. Although VLMs have already d…
Syn-GRPO: Self-Evolving Data Synthesis for MLLM Perception Reasoning
Qihan Huang, Haofei Zhang, Rong Wei +4
RL (reinforcement learning) methods (e.g., GRPO) for MLLM (Multimodal LLM) perception ability has attracted wide research interest owing to its remarkable generalization ability. N…
HuggingR: A Progressive Reasoning Framework for Discovering Optimal Model Companions
Shaoyin Ma, Chenggong Hu, Huiqiong Wang +3
Building effective LLM agents increasingly requires selecting appropriate AI models as tools from large open repositories (e.g., HuggingFace with > 2M models) based on natural lang…
Training Data Provenance Verification: Did Your Model Use Synthetic Data from My Generative Model for Training?
Yuechen Xie, Jie Song, Huiqiong Wang +1
High-quality open-source text-to-image models have lowered the threshold for obtaining photorealistic images significantly, but also face potential risks of misuse. Specifically, s…
D-DPM: Dual Denoising for Quantized Diffusion Probabilistic Models
Qian Zeng, Jie Song, Han Zheng +2
Diffusion models have achieved cutting-edge performance in image generation. However, their lengthy denoising process and computationally intensive score estimation network impede…
Towards Enhanced Image Generation Via Multi-modal Chain of Thought in Unified Generative Models
Yi Wang, Mushui Liu, Wanggui He +13
Unified generative models have shown remarkable performance in text and image generation. For image synthesis tasks, they adopt straightforward text-to-image (T2I) generation. Howe…
Dataset Ownership Verification in Contrastive Pre-trained Models
Yuechen Xie, Jie Song, Mengqi Xue +5
High-quality open-source datasets, which necessitate substantial efforts for curation, has become the primary catalyst for the swift progress of deep learning. Concurrently, protec…
PatchDPO: Patch-level DPO for Finetuning-free Personalized Image Generation
Qihan Huang, Weilong Dai, Jinlong Liu +4
Finetuning-free personalized image generation can synthesize customized images without test-time finetuning, attracting wide research interest owing to its high efficiency. Current…
LG-CAV: Train Any Concept Activation Vector with Language Guidance
Qihan Huang, Jie Song, Mengqi Xue +6
Concept activation vector (CAV) has attracted broad research interest in explainable AI, by elegantly attributing model predictions to specific concepts. However, the training of C…
On the Evaluation Consistency of Attribution-based Explanations
Jiarui Duan, Haoling Li, Haofei Zhang +5
Attribution-based explanations are garnering increasing attention recently and have emerged as the predominant approach towards \textit{eXplanable Artificial Intelligence}~(XAI). H…
Angle Robustness Unmanned Aerial Vehicle Navigation in GNSS-Denied Scenarios
Yuxin Wang, Zunlei Feng, Haofei Zhang +4
Due to the inability to receive signals from the Global Navigation Satellite System (GNSS) in extreme conditions, achieving accurate and robust navigation for Unmanned Aerial Vehic…