Zhuchenyang Liu
PulseAugur coverage of Zhuchenyang Liu — every cluster mentioning Zhuchenyang Liu across labs, papers, and developer communities, ranked by signal.
-
NanoVDR distills 2B VLM to 69M text encoder for faster visual document retrieval
Researchers have developed NanoVDR, a novel approach to visual document retrieval that significantly reduces computational costs. By distilling a large 2B parameter vision-language model (VLM) into a much smaller 69M pa…
-
New Benchmark Tests Vision-Language Models on IKEA Assembly Instructions
Researchers have developed IKEA-Bench, a new benchmark designed to evaluate the performance of Vision-Language Models (VLMs) in understanding and aligning assembly instructions from diagrams with real-world video feeds.…
-
New pruning method slashes visual document retrieval model size
Researchers have developed Structural Anchor Pruning (SAP), a novel training-free method to compress visual document retrieval models. SAP addresses the significant storage overhead of multi-vector indexes in these mode…