Advances in image generation have made visual authenticity increasingly difficult to assess. Although image forensics now examines both generation artifacts and higher-level visual inconsistencies, a plausible image can still contradict real-world facts or rules. We introduce WorldFact-Bench to evaluate image-world con...
Zhuo Chen, Zheng-Xian Wu, Yu Yu et al.· 0 citations
Large Language Models (LLMs) serving as long-term dialogue agents require memory systems that support reliable reasoning over extended interactions. However, existing Retrieval-Augmented Generation (RAG) frameworks typically treat memory as passive storage, making it difficult to distinguish source-attributed beliefs f...
Zi-Rui Liao, Zheng-Xian Wu, Zhuo Chen et al.· 0 citations
Open-UniMo, a unified Large Motion-Language Model (LMLM) trained on million-scale open-world motion-language data, and Open-MoBench, a VLM-guided benchmark for assessing text-to-motion (T2M) generation, motion-to-text (M2T) understanding, and bidirectional consistency are proposed.
Guo-Cun Wang, Kenkun Liu, Guo-Rui Song et al.· 0 citations
This work identifies a vulnerability specific to diffusion generation: because the visual embedding conditions every reverse denoising step rather than acting as a one-time prefix, adversarial visual semantics are repeatedly propagated and amplified across the generation trajectory, a phenomenon the authors term cross-...
Guo-Rui Song, Run-Qing Tang, Jing-Ye Zhang et al.· 0 citations
A Video Compression framework built upon a foundational flow model that enables the compressor to harness generative video flow priors effectively, which reduces bit consumption by 58\% and achieves one-step decoding and reconstructions with high perceptual fidelity.
Yichong Xia, Qin-Hong Wu, Bin Chen et al.· 1 citation· ⚡1
R3G, a modular Reasoning-Retrieval-Reranking framework, first produces a brief reasoning plan that specifies the required visual cues, then adopts a two-stage strategy, with coarse retrieval followed by fine-grained reranking, to select evidence images.
Zhuo Chen, Zhengxian Wu, Zi-Rui Liao et al.· IEEE International Conferenc...· 4 citations
KBMR is proposed, the first MLLM-based embedding retriever tailored for KB-VQA, and an MLLM-based semantic discriminator that generates continuous entity-consistency weights is introduced to tackle the challenge of noisy supervision in Wikipedia-scale retrieval.
Hang-Rui Xu, Zheng-Xian Wu, Yu Yu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
