7 papers
Bridging the Manifold Gap: Riemannian Residual Line Search for One-Step Image Editing
Hongzhu Yi, Zhongtian Luo, Tong Li +2
One-step diffusion editors are fast because they avoid inversion and iterative optimization, but a single transport update must be aggressive enough to realize the target prompt an…
Delta-JEPA: Learning Action-Sensitive World Models via Latent Difference Decoding
Zhenghao Zhang, Yuanxiang Wang, Zhenyu Guan +11
Learning visual world models for planning requires compact latent dynamics that remain sensitive to actions, yet reconstruction-free joint-embedding objectives can collapse to acti…
VDE Bench: Evaluating The Capability of Image Editing Models to Modify Visual Documents
Hongzhu Yi, Yujia Yang, Yuanxiang Wang +18
In recent years, image editing models have made significant progress, enabling users to manipulate visual content in a flexible and interactive manner through natural language inst…
RPO:Reinforcement Fine-Tuning with Partial Reasoning Optimization
Hongzhu Yi, Xinming Wang, Zhenghao zhang +12
Within the domain of large language models, reinforcement fine-tuning algorithms necessitate the generation of a complete reasoning trajectory beginning from the input query, which…
Dynamic Deep Graph Learning for Incomplete Multi-View Clustering with Masked Graph Reconstruction Loss
Zhenghao Zhang, Jun Xie, Xingchen Chen +11
The prevalence of real-world multi-view data makes incomplete multi-view clustering (IMVC) a crucial research. The rapid development of Graph Neural Networks (GNNs) has established…
JTCSE: Joint Tensor-Modulus Constraints and Cross-Attention for Unsupervised Contrastive Learning of Sentence Embeddings
Tianyu Zong, Hongzhu Yi, Bingkang Shi +2
Unsupervised contrastive learning has become a hot research topic in natural language processing. Existing works usually aim at constraining the orientation distribution of the rep…