Publications

LikePhys: Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference

Inference-time Physics Alignment of Video Generative Models with Latent World Models

SpatialBot: Precise Spatial Understanding with Vision Language Models

RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Model

Not Just Pretty Pictures: Toward Interventional Data Augmentation Using Text-to-Image Generators

Real-Fake: Effective Training Data Synthesis Through Distribution Matching

Hidden in Plain Sight: Evaluating Abstract Shape Recognition in Vision-Language Models

Efficient multimodal learning from data-centric perspective

kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies

SynArtifact: Classifying and Alleviating Artifacts in Synthetic Images via Vision-Language Model

Off the Radar: Uncertainty-Aware Radar Place Recognition with Introspective Querying and Map Maintenance