Zhiyang Xu

LaTtE-Flow: Layerwise Timestep-Expert Flow-based Transformer

COMPASS: A Multi-Turn Benchmark for Tool-Mediated Planning & Preference Optimization

BLIP3-o: A Family of Fully Open Unified Multimodal Models—Architecture, Training and Dataset

Transfer between Modalities with MetaQueries

AR-RAG: Autoregressive Retrieval Augmentation for Image Generation

LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models

Modality-Specialized Synergizers for Interleaved Vision-Language Generalists

SPARTUN3D: Situated Spatial Understanding of 3D World in Large Language Model

RoRA-VLM: Robust Retrieval-Augmented Vision Language Models

Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models