Scholar
Peng Tang
Google Scholar ID: h_oYR-IAAAAJ
Meta
Multi-modal LLM
Vision Language
Computer Vision
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
2,901
H-index
20
i10-index
22
Publications
20
Co-authors
0
Contact
Email
tangpeng723@gmail.com
CV
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
26 items
Towards Personalized Differentially Private Learning for Decentralized Local Graphs
2026
Cited
0
EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments
2026
Cited
0
LLMZero: Discovering Adaptive Training Strategies for RL Post-Training via LLM Agents
2026
Cited
0
Open-Vocabulary Semantic Segmentation Network Integrating Object-Level Label and Scene-Level Semantic Features for Multimodal Remote Sensing Images
2026
Cited
0
PCR: A Prefetch-Enhanced Cache Reuse System for Low-Latency RAG Serving
2026
Cited
0
CLEAR: Context-Aware Learning with End-to-End Mask-Free Inference for Adaptive Video Subtitle Removal
2026
Cited
0
Learning to Explore: Policy-Guided Outlier Synthesis for Graph Out-of-Distribution Detection
2026
Cited
0
Towards Generalized Multi-Image Editing for Unified Multimodal Models
arXiv.org · 2026
Cited
0
Load more
Resume (English only)
Academic Achievements
Two papers for GUI/web agents are accepted to ACL 2025 Findings.
One paper for transformer decoder inference acceleration is accepted to NAACL 2024 Findings.
One paper for text-based VQA is accepted to NAACL 2024 Industry Track.
One paper for reasoning-based chart VQA is accepted to CVPR 2024.
One paper for document understanding and one paper for VL model knowledge distillation are accepted to AAAI 2024.
Research Experience
Currently a Research Scientist at Meta.
Worked as an intern in the Internet Media group at Microsoft Research Asia, advised by Chunyu Wang and Jingdong Wang.
Worked as a visiting student in the CCVL group at Johns Hopkins University, advised by Prof. Alan Yuille.
Worked as an intern at Tencent AI Lab, advised by Lin Ma and Zequn Jie.
Worked as an Applied Scientist at Amazon AWS AI Labs and Salesforce Research.
Background
Research interests: Computer Vision and Multi-modal LLM.
Co-authors
0 total
Co-authors: 0 (list not available)