Jie Huang
Source-listed: 2024 master's candidate · Institute of Computing Technology, Chinese Academy of Sciences
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Revisiting Multimodal Positional Encoding in Vision–Language ModelsSaved credit: First author · 2025Explore people connected to this work →
- RefHCM: A Unified Model for Referring Perceptions in Human-Centric ScenariosSaved credit: First author · 2024Explore people connected to this work →
- Multimodal-RoPEsSaved credit: Maintainer · 2025Explore people connected to this work →
- RefHCM official implementationSaved credit: First author · 2024Explore people connected to this work →
- Qwen3-VL Technical ReportSaved credit: Contributor · 2025Explore people connected to this work →