4 papers
Drift Variation Autoencoder: Unifying Generation and Representation Learning through Conditional Posterior Flow Matching
Jiarui Cao
Stochastic masking, cropping, or modality removal makes deterministic reconstruction an incomplete target: one observation can admit many clean completions. This work takes the cor…
Beyond English: Uncovering the Multilingual Gap in Vision-Language-Action Models
Hanyang Chen, Hongliang Li, Jiarui Cao +6
Vision-Language-Action models have recently demonstrated promising capabilities in learning generalist robot policies from large-scale multimodal data. However, most existing VLA s…
Quantum-Gated Task-interaction Knowledge Distillation for Pre-trained Model-based Class-Incremental Learning
Linjie Li, Huiyu Xiao, Jiarui Cao +2
Class-incremental learning (CIL) aims to continuously accumulate knowledge from a stream of tasks and construct a unified classifier over all seen classes. Although pretrained mode…
Gradient Flow Drifting: Generative Modeling via Wasserstein Gradient Flows of KDE-Approximated Divergences
Jiarui Cao, Zixuan Wei, Yuxin Liu
We reveal a precise mathematical framework about a new family of generative models which we call Gradient Flow Drifting. With this framework, we prove an equivalence between the re…