Chengliang Liu

A generative foundation model for computational brain imaging

Computational brain imaging is constrained by a mismatch between increasingly diverse tasks and scarce, heterogeneous clinical data. Although existing brain foundation models transfer pretrained representations, their knowledge remains entangled within model-specific features and fixed architectures. This paper propose...

When Semantically Consistent Encoding Meets View-Label Heterogeneity Modeling: A Unified Framework for Incomplete Multi-View Multi-Label Learning.

Incomplete multi-view multi-label learning requires not only robust semantic aggregation from partially observed views, but also label-aware exploitation of view-specific evidence. Existing approaches usually emphasize either shared representation learning or decision-level fusion. The former improves robustness agains...

Representation--Behavior Alignment for Explainable Weakly-Supervised Video Anomaly Detection

Representation--Behavior Alignment (RBA) is proposed, a parameter-efficient method that adapts layers using video-level labels alone while updating about 0.012\% of the backbone parameters, and it produces anomaly decisions and explanations through a single generative process.

RoMod: Temporal Routing Modulation via Mixture-of-Experts for Video Anomaly Detection

RoMod is proposed, an efficient VAD framework trained with only \(5\%\) of weakly labeled videos that achieves state-of-the-art performance while running substantially faster than dense backbones of comparable size.

Semantic Invariant Representation Learning and Data-Driven Label Prototype Modeling for Incomplete Multi-view Multi-label Classification

Noise-Induced Cross-Modal Information Interaction and Dual-Prompt Learning for Medical Image Segmentation

Accurate medical image segmentation plays a vital role in clinical diagnostics by facilitating the precise delineation of anatomical structures and pathological regions. However, the performance of existing segmentation methods is often constrained by the scarcity of high-quality annotated datasets, as manual labeling...

VideoVIBE: A Video-Grounded Diagnostic Benchmark for One-Shot Interactive Website Generation

VideoVIBE is introduced, a video-grounded benchmark that transforms human-operated webpage recordings into fine-grained diagnostic tasks and V2Lens is proposed, a training-free, evidence-grounded multi-agent system that challenges and selectively refines initial video-based diagnoses through targeted visual and source-...