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
22 items
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
FFP-300K: Scaling First-Frame Propagation for Generalizable Video Editing
arXiv.org · 2026
Cited
0
The devil is in the details: Enhancing Video Virtual Try-On via Keyframe-Driven Details Injection
2025
Cited
0
MoE-SpeQ: Speculative Quantized Decoding with Proactive Expert Prefetching and Offloading for Mixture-of-Experts
2025
Cited
0
FedTopo: Topology-Informed Representation Alignment in Federated Learning under Non-I.I.D. Conditions
2025
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)
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up