1 citations · 1 across the 7 of their papers we have counts for
8 papers
DECODE: Tackling Representation and Decision Degradation in Continual AI-Generated Image Detection
Zihao Cai, Xinghan Li, Ruiyan Yang +3
As generative models continue to evolve, AI-generated image detectors must incrementally adapt to emerging generative domains while preserving knowledge acquired from previous ones…
From Scenes to Elements: Multi-Granularity Evidence Retrieval for Verifiable Multimodal RAG
Guanhua Chen, Chuyue Huang, Yutong Yao +4
Multimodal Retrieval-Augmented Generation (RAG) systems retrieve evidence at coarse granularities (entire images or scenes), creating a mismatch with fine-grained user queries and…
Revealing the Implicit Noise-based Imprint of Generative Models
Xinghan Li, Yue Yu, Xue Song +2
With the rapid advancement of vision generation models, the potential security risks stemming from synthetic visual content have garnered increasing attention, posing significant c…
LoRA of Change: Learning to Generate LoRA for the Editing Instruction from A Single Before-After Image Pair
Xue Song, Jiequan Cui, Hanwang Zhang +4
In this paper, we propose the LoRA of Change (LoC) framework for image editing with visual instructions, i.e., before-after image pairs. Compared to the ambiguities, insufficient s…
Doubly Abductive Counterfactual Inference for Text-based Image Editing
Xue Song, Jiequan Cui, Hanwang Zhang +3
We study text-based image editing (TBIE) of a single image by counterfactual inference because it is an elegant formulation to precisely address the requirement: the edited image s…
Identity-Driven Multimedia Forgery Detection via Reference Assistance
Junhao Xu, Jingjing Chen, Xue Song +3
Recent advancements in "deepfake" techniques have paved the way for generating various media forgeries. In response to the potential hazards of these media forgeries, many research…
Transferability Estimation Based On Principal Gradient Expectation
Huiyan Qi, Lechao Cheng, Jingjing Chen +4
Transfer learning aims to improve the performance of target tasks by transferring knowledge acquired in source tasks. The standard approach is pre-training followed by fine-tuning…
Eternal solutions in exponential self-similar form for a quasilinear reaction-diffusion equation with critical singular potential
Razvan Gabriel Iagar, Marta Latorre, Ariel Sánchez
We prove existence and uniqueness of self-similar solutions with exponential form to the following quasilinear reaction-diffusion…