Pengxiang Li
- The Curse of Depth in Large Language Models
2025/02/09 by Wenfang Sun, Sun, Wenfang, Xinyuan Song +9 · 6 voices · 14 citations
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques
- Automated Evaluation of Large Vision-Language Models on Self-driving Corner Cases
2024/04/16 by Kai Chen, Yanze Li, Chen, Kai +23 · 23 citations
Computer Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Multimodal Machine Learning Applications
- InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection
2025/01/08 by Yuhang Liu, Liu, Yuhang, Pengxiang Li +16 · 28 citations
Computer Science · #Speech and dialogue systems #Natural Language Processing Techniques #Multi-Agent Systems and Negotiation
- Adaptive Chain-of-Focus Reasoning via Dynamic Visual Search and Zooming for Efficient VLMs
2025/05/21 by Xintong Zhang, Zhi Gao, Zhang, Xintong +18 · 27 citations
Computer Science · #Advanced Text Analysis Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Semantic Web and Ontologies #Speech and dialogue systems
- Learning Personalized Driving Styles via Reinforcement Learning from Human Feedback
2025/03/13 by Derun Li, Changye Li, Li, Derun +21 · 22 citations
Engineering · Computer Science · #Autonomous Vehicle Technology and Safety #Human Motion and Animation #Robotic Path Planning Algorithms
- TransDiffuser: Diverse Trajectory Generation with Decorrelated Multi-modal Representation for End-to-end Autonomous Driving
2025/05/14 by Xuefeng Jiang, Jiang, Xuefeng, Yuan Ma +16 · 12 citations
Computer Science · Engineering · #Autonomous Vehicle Technology and Safety #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Robotic Path Planning Algorithms #Robotics (cs.RO) #Robotics and Sensor-Based Localization
- Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking
2025/05/26 by Pengxiang Li, Li, Pengxiang, Shilin Yan +10 · 10 citations
Engineering · Computer Science · #Guidance and Control Systems #Target Tracking and Data Fusion in Sensor Networks #Inertial Sensor and Navigation
- TrackDiffusion: Tracklet-Conditioned Video Generation via Diffusion Models
2023/12/01 by Pengxiang Li, Li, Pengxiang, Kai Chen +14 · 3 citations
Engineering · Computer Science · #Evacuation and Crowd Dynamics #Time Series Analysis and Forecasting #Target Tracking and Data Fusion in Sensor Networks
- Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning
2025/04/30 by Pengxiang Li, Li, Pengxiang, Zhi Gao +18 · 7 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Natural Language Processing Techniques #Semantic Web and Ontologies #Speech and dialogue systems
- Outlier-weighed Layerwise Sampling for LLM Fine-tuning
2024/05/28 by Pengxiang Li, Yin Lu, Li, Pengxiang +5 · 2 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Image and Signal Denoising Methods #Machine Learning (cs.LG) #Neural Networks and Applications #Speech and Audio Processing
- FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models
2024/07/16 by Pengxiang Li, Li, Pengxiang, Zhi Gao +15 · 2 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Speech and dialogue systems
- InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization
2025/08/07 by Yuhang Liu, Zeyu Liu, Liu, Yuhang +20 · 7 citations
Computer Science · #Augmented Reality Applications #Context-Aware Activity Recognition Systems
- Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation
2025/09/28 by Pengxiang Li, Li, Pengxiang, Zechen Hu +32 · 2 citations
Computer Science · #Robotic Path Planning Algorithms #Fuzzy Logic and Control Systems #Neural Networks and Applications
- Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents
2026/07/30 by Hanzhang Zhou, Panrong Tong, Xu Zhang +13 · 1 voice
Computer Science · #cs.AI #cs.CV
- Adjacency-degree algebras and spectral determination of graphs
2026/07/23 by Zhipeng Lu, Pengxiang Li
#math.CO #math.SP