12 papers
PartCo: Part-Level Correspondence Priors Enhance Category Discovery
Fernando Julio Cendra, Kai Han
Generalized Category Discovery (GCD) aims to identify both known and novel categories within unlabeled data by leveraging a set of labeled examples from known categories. Existing…
Multimodal Latent Reasoning via Hierarchical Visual Cues Injection
Yiming Zhang, Qiangyu Yan, Borui Jiang +1
The advancement of multimodal large language models (MLLMs) has enabled impressive perception capabilities. However, their reasoning process often remains a "fast thinking" paradig…
Mitigating Structural Overfitting: A Distribution-Aware Rectification Framework for Missing Feature Imputation
Yifan Song, Fenglin Yu, Yihong Luo +4
Incomplete node features are ubiquitous in real-world scenarios such as user profiling and cold-start recommendation, which severely hinders the practical deployment of graph learn…
When Deepfake Detection Meets Graph Neural Network:a Unified and Lightweight Learning Framework
Haoyu Liu, Chaoyu Gong, Mengke He +3
The proliferation of generative video models has made detecting AI-generated and manipulated videos an urgent challenge. Existing detection approaches often fail to generalize acro…
Context-Aware Initialization for Reducing Generative Path Length in Diffusion Language Models
Tongyuan Miao, Gary Huang, Kai Jun Han +1
Diffusion Large Language Models (DLLMs) enable fully parallel token decoding but often remain impractical at inference time due to the many denoising iterations required to refine…
HyperVL: An Efficient and Dynamic Multimodal Large Language Model for Edge Devices
HyperAI Team, Yuchen Liu, Kaiyang Han +26
Current multimodal large lanauge models possess strong perceptual and reasoning capabilities, however high computational and memory requirements make them difficult to deploy direc…