Scholar
Zirui Wang
Google Scholar ID: GgD-B68AAAAJ
Apple AI/ML
Citations & Impact
Citations
11,182
H-index
19
i10-index
23
Publications
20
Co-authors
14
list available
Publications
Resume (English only)
Academic Achievements
- Post-training lead for Apple Intelligence Foundation Language Models
- CoCa: Contrastive Captioners are Image-Text Foundation Models (TMLR 2022, co-first author)
- SimVLM: Simple Visual Language Model Pretraining with Weak Supervision (ICLR 2022)
- MMAU: A Holistic Benchmark of Agent Capabilities Across Diverse Domains (Arxiv 2024)
- ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities (Arxiv 2024)
- Understanding Alignment in Multimodal LLMs: A Comprehensive Study (Arxiv 2024)
- Ferret: Refer and Ground Anything Anywhere at Any Granularity (ICLR 2024)
- MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training (Arxiv 2024)
- Revisiting MoE and Dense Speed-Accuracy Comparisons for LLM Training (Arxiv 2024)
- REVEAL: Retrieval-Augmented Visual-Language Pre-Training With Multi-Source Multimodal Knowledge Memory (CVPR 2023)
- Guiding Image Captioning Models Toward More Specific Captions (CVPR 2023)
