1 citations · 1 across the 15 of their papers we have counts for
17 papers
UniTac: A Unified Multimodal Model for Cross-Sensor Tactile Understanding and Generation
Jiahang Tu, Fengyu Yang, Chenyang Ma +8
Unified multimodal models (UMMs) have shown great promise in integrating understanding and generation across diverse modalities. However, existing research rarely extends this para…
FG-OrIU: Towards Better Forgetting via Feature-Gradient Orthogonality for Incremental Unlearning
Qian Feng, JiaHang Tu, Mintong Kang +3
Incremental unlearning (IU) is critical for pre-trained models to comply with sequential data deletion requests, yet existing methods primarily suppress parameters or confuse knowl…
Mass Concept Erasure in Diffusion Models with Concept Hierarchy
Jiahang Tu, Ye Li, Yiming Wu +3
The success of diffusion models has raised concerns about the generation of unsafe or harmful content, prompting concept erasure approaches that fine-tune modules to suppress speci…
Unleashing High-Quality Image Generation in Diffusion Sampling Using Second-Order Levenberg-Marquardt-Langevin
Fangyikang Wang, Hubery Yin, Lei Qian +9
The diffusion models (DMs) have demonstrated the remarkable capability of generating images via learning the noised score function of data distribution. Current DM sampling techniq…
Efficiently Access Diffusion Fisher: Within the Outer Product Span Space
Fangyikang Wang, Hubery Yin, Shaobin Zhuang +7
Recent Diffusion models (DMs) advancements have explored incorporating the second-order diffusion Fisher information (DF), defined as the negative Hessian of log density, into vari…
IAP: Improving Continual Learning of Vision-Language Models via Instance-Aware Prompting
Hao Fu, Hanbin Zhao, Jiahua Dong +3
Recent pre-trained vision-language models (PT-VLMs) often face a Multi-Domain Task Incremental Learning (MTIL) scenario in practice, where several classes and domains of multi-moda…
TAIL: Text-Audio Incremental Learning
Yingfei Sun, Xu Gu, Wei Ji +3
Many studies combine text and audio to capture multi-modal information but they overlook the model's generalization ability on new datasets. Introducing new datasets may affect the…
CE-SDWV: Effective and Efficient Concept Erasure for Text-to-Image Diffusion Models via a Semantic-Driven Word Vocabulary
Jiahang Tu, Qian Feng, Jiahua Dong +4
Large-scale text-to-image (T2I) diffusion models have achieved remarkable generative performance about various concepts. With the limitation of privacy and safety in practice, the…
BELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Models
Fangyikang Wang, Hubery Yin, Yuejiang Dong +5
The inversion of diffusion model sampling, which aims to find the corresponding initial noise of a sample, plays a critical role in various tasks. Recently, several heuristic exact…
LW2G: Learning Whether to Grow for Prompt-based Continual Learning
Qian Feng, Da-wei Zhou, Hanbin Zhao +4
Recent Prompt-based Continual learning (PCL) has achieved remarkable performance with pre-trained models. These approaches expand a prompt pool by adding a new set of prompts while…
TextToucher: Fine-Grained Text-to-Touch Generation
Jiahang Tu, Hao Fu, Fengyu Yang +3
Tactile sensation plays a crucial role in the development of multi-modal large models and embodied intelligence. To collect tactile data with minimal cost as possible, a series of…
DriveDiTFit: Fine-tuning Diffusion Transformers for Autonomous Driving
Jiahang Tu, Wei Ji, Hanbin Zhao +3
In autonomous driving, deep models have shown remarkable performance across various visual perception tasks with the demand of high-quality and huge-diversity training datasets. Su…
NeuroBind: Towards Unified Multimodal Representations for Neural Signals
Fengyu Yang, Chao Feng, Daniel Wang +8
Understanding neural activity and information representation is crucial for advancing knowledge of brain function and cognition. Neural activity, measured through techniques like e…
PECTP: Parameter-Efficient Cross-Task Prompts for Incremental Vision Transformer
Qian Feng, Hanbin Zhao, Chao Zhang +4
Incremental Learning (IL) aims to learn deep models on sequential tasks continually, where each new task includes a batch of new classes and deep models have no access to task-ID i…
APISR: Anime Production Inspired Real-World Anime Super-Resolution
Boyang Wang, Fengyu Yang, Xihang Yu +2
While real-world anime super-resolution (SR) has gained increasing attention in the SR community, existing methods still adopt techniques from the photorealistic domain. In this pa…
Neural Sinkhorn Gradient Flow
Huminhao Zhu, Fangyikang Wang, Chao Zhang +2
Wasserstein Gradient Flows (WGF) with respect to specific functionals have been widely used in the machine learning literature. Recently, neural networks have been adopted to appro…
GAD-PVI: A General Accelerated Dynamic-Weight Particle-Based Variational Inference Framework
Fangyikang Wang, Huminhao Zhu, Chao Zhang +2
Particle-based Variational Inference (ParVI) methods approximate the target distribution by iteratively evolving finite weighted particle systems. Recent advances of ParVI methods…