Awesome AI for Science
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Pengtao Xie — most-cited papers & profile · AI for Science
← authors
·
overview
Pengtao Xie
11
papers ·
1
citations ·
34
h-index
University of California San Diego
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
BLO-SAM: Bi-level Optimization Based Overfitting-Preventing Finetuning of SAM
2024 · 1 citations
LLMs Know When They Know, but Do Not Act on It: A Metacognitive Harness for Test-time Scaling
2026
SteganoBackdoor: Stealthy and Data-Efficient Backdoor Attacks on Language Models
2025
DreamPRM-Code: Function-as-Step Process Reward Model with Label Correction for LLM Coding
2025
DreamPRM-Code: Function-as-Step Process Reward Model with Label Correction for LLM Coding
2025
S-Chain: Structured Visual Chain-of-Thought For Medicine
2025
DreamPRM: Domain-Reweighted Process Reward Model for Multimodal Reasoning
2025
Defense against Prompt Injection Attacks via Mixture of Encodings
2025
AM-SAM: Automated Prompting and Mask Calibration for Segment Anything Model
2024
BiDoRA: Bi-level Optimization-Based Weight-Decomposed Low-Rank Adaptation
2024
Topics
cs.LG
cs.AI
Evaluation
cs.CV
Adversarial ML
LLM Security
Vulnerability Detection
Code Generation
Code Models
Testing