Awesome Reinforcement Learning
📄
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
Guangtao Zhai — most-cited papers & profile · Reinforcement Learning
← authors
·
overview
Guangtao Zhai
11
papers ·
0
citations ·
72
h-index
Shanghai Jiao Tong University · Beijing Academy of Artificial Intelligence · Shanghai Artificial Intelligence Laboratory
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
RoboProcessBench: Benchmarking Process-Aware Understanding in Vision-Language Robotic Manipulation
2026
Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating
2026
UniDial-EvalKit: A Unified Toolkit for Evaluating Multi-Faceted Conversational Abilities
2026
UniDial-EvalKit: A Unified Toolkit for Evaluating Multi-Faceted Conversational Abilities
2026
Embodied Image Compression
2025
User-centric Subjective Leaderboard by Customizable Reward Modeling
2025
Redundancy Principles for MLLMs Benchmarks
2025
OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference
2025
LMM4LMM: Benchmarking and Evaluating Large-multimodal Image Generation with LMMs
2025
EEmo-Bench: A Benchmark for Multi-modal Large Language Models on Image Evoked Emotion Assessment
2025
REF-VLM: Triplet-Based Referring Paradigm for Unified Visual Decoding
2025
Topics
cs.CL
Benchmarks
Vision-Language Models
Manipulation
Fine-Tuning
Visual QA & Reasoning
Safety & Alignment
Training Techniques
Efficiency
Perception