Profiles2025-2026
Xinyuan Chang
Amap, Alibaba Group
9Papers
0Last author
15Unique co-authors
1First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers9
- JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language NavigationAuthor 3 of 10ICLR 2026 · 124 citations
- MindDriver: Introducing Progressive Multimodal Reasoning for Autonomous DrivingAuthor 4 of 10CVPR 2026 · 13 citations
- PriorDrive: Enhancing Online HD Mapping with Unified Vector PriorsAuthor 2 of 8AAAI 2026 · 12 citations
- Persistent Autoregressive Mapping with Traffic Rules for Autonomous DrivingAuthor 2 of 11AAAI 2026 · 7 citations
- UniMapGen: A Generative Framework for Large-Scale Map Construction from Multi-modal DataAuthor 3 of 9AAAI 2026 · 6 citations
- Online Navigation Refinement: Achieving Lane-Level Guidance by Associating Standard-Definition and Online Perception MapsAuthor 4 of 10ICLR 2026 · 2 citations
- FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous DrivingAuthor 2 of 8NeurIPS 2025 · 228 citations
- SeqGrowGraph: Learning Lane Topology as a Chain of Graph ExpansionsAuthor 3 of 8ICCV 2025 · 1 citation
- Driving by the Rules: A Benchmark for Integrating Traffic Sign Regulations into Vectorized HD MapAuthor 1 of 6CVPR 2025
