Suyuchen Wang

GraphOmni: A Comprehensive and Extensible Benchmark Framework for Large Language Models on Graph-theoretic Tasks

SCOPE: Selective Cross-modal Orchestration of Visual Perception Experts

Metadata-Agnostic Decentralized Learning

Improving GUI Grounding with Explicit Position-to-Coordinate Mapping

AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding

VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text

System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts

MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation

BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks