Yizhou Wang
Peking University professor; director of PKU CFCS; senior author on PKU-SafeRLHF / BeaverTails and a long line of vision and alignment papers.
- Role
- professor
- Currently at
- Peking University
- Unknown
- GitHub
- Unknown
- Scholar
- scholar.google.com/citations
- Papers
- 26
Cite
Notes
Only stored in your browser.
Authored papers
26Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks
arXiv 2026
A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers
arXiv 2025
Trajectory Prediction Meets Large Language Models: A Survey
arXiv 2025
Efficient Reasoning with Hidden Thinking
arXiv 2025
SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence
arXiv 2025
Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows
arXiv 2025
SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines
arXiv 2025
Cautious Next Token Prediction
arXiv 2025
Boosting Large Language Models with Mask Fine-Tuning
arXiv 2025
EmpathyAgent: Can Embodied Agents Conduct Empathetic Actions?
arXiv 2025
Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models
arXiv 2024
SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens
CVPR 2025 1
Real-time Holistic Robot Pose Estimation with Unknown States
arXiv 2024
BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset
NeurIPS
Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World
arXiv 2023
3D Human Mesh Estimation from Virtual Markers
3d-human-mesh-estimation-from-virtual-markers
UniHCP: A Unified Model for Human-Centric Perceptions
CVPR 2023 1
Making Reconstruction-based Method Great Again for Video Anomaly Detection
arXiv 2023
Safe RLHF: Safe Reinforcement Learning from Human Feedback
arXiv 2023
Explainable Anomaly Detection in Images and Videos: A Survey
arXiv 2023
GFPose: Learning 3D Human Pose Prior with Gradient Fields
CVPR 2023 1
MotionBERT: A Unified Perspective on Learning Human Motion Representations
ICCV 2023 1
Rethinking Adam: A Twofold Exponential Moving Average Approach
adapting-stepsizes-by-momentumized-gradients-1
Which Invariance Should We Transfer? A Causal Minimax Learning Approach
arXiv 2021
Self-Directed Online Machine Learning for Topology Optimization
arXiv 2020
AI Challenger : A Large-scale Dataset for Going Deeper in Image Understanding
arXiv 2017
Affiliations
Frequent co-authors
10from 26 papers