3 papers
cs.CV2026
TBSG-Net: Temporal Bipartite Scene Graph Network for Fine-Grained Video Moment Retrieval
Ji Huang, Yongsheng Dai, Tianyu Ren +2
Recent advances in proposal-free Video Moment Retrieval (VMR) have highlighted the effectiveness of Static Scene Graphs (SSGs). By modeling objects and their relations at the frame…
cs.LG2026
Autonomous mechanistic discovery of colorectal cancer vulnerabilities via multi-scale AI swarms
Christopher Baker, Tianyu Ren, Karen Rafferty +2
The acceleration of automated scientific discovery has been fundamentally bottlenecked by the epistemic gap between the semantic reasoning of large language models (LLMs) and the d…
cs.LG2026
Latent World Recovery for Multimodal Learning with Missing Modalities
Hui Wang, Tianyu Ren, Joseph Butler +3
We study multimodal learning under missing modalities, with particular motivation from bioscience applications in which heterogeneous modalities are often only partially available…