9 papers
DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation
Zhuchenyang Liu, Ziyi Wang, Yao Zhang +1
Visual document retrieval (VDR) is dominated by multi-billion-parameter models that are slow to index at full corpus scale and expensive to serve. Prior compression routes either t…
Evidence Attribution in Visual Document Understanding without Coordinates or Region Labels
Zhuchenyang Liu, Yao Zhang, Yu Xiao
Reliable visual document understanding requires a model to attribute each answer to the evidence regions that support it. Recent benchmarks and systems express this step through a…
Fine-grained Motion Retrieval via Joint-Angle Motion Images and Token-Patch Late Interaction
Yao Zhang, Zhuchenyang Liu, Yanlan He +2
Text-motion retrieval aims to learn a semantically aligned latent space between natural language descriptions and 3D human motion skeleton sequences, enabling bidirectional search…
Encoder-Free Human Motion Understanding via Structured Motion Descriptions
Yao Zhang, Zhuchenyang Liu, Thomas Ploetz +1
The world knowledge and reasoning capabilities of text-based large language models (LLMs) are advancing rapidly, yet current approaches to human motion understanding, including mot…
Benchmarking and Mechanistic Analysis of Vision-Language Models for Cross-Depiction Assembly Instruction Alignment
Zhuchenyang Liu, Yao Zhang, Yu Xiao
2D assembly diagrams are often abstract and hard to follow, creating a need for intelligent assistants that can monitor progress, detect errors, and provide step-by-step guidance.…
NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval
Zhuchenyang Liu, Yao Zhang, Yu Xiao
Vision-Language Model (VLM) based retrievers have advanced visual document retrieval (VDR) to impressive quality. They require the same multi-billion parameter encoder for both doc…