← 返回名录条目信息来自其公开主页与公开发布内容。按本站规范，页面不展示任何联系方式。 需要更正或删除？通过收录与更正通道提交，24 小时内处理。
X
Xinmu-Tantai
CV → Multimodal Learning （CLIP）→ AI Infra & Inference → VLA & Reinforcement Learning
- 公司
- Xi'an Jiaotong University
- 位置
- No.28 Xianning West Road, Xi'an, Shaanxi 710049, P.R. China
- Stars
- 24
- 粉丝 / 仓库
- 5
代表作品 / 项目
- GMamba-GSSM⭐ 12Official PyTorch implementation of “Enabling True Global Perception in State Space Models for Visual Tasks” (ICLR 2026).
- SynFSNet⭐ 8AFSIFormer: Adaptive Frequency–Spatial Interaction Attention Mechanism for Aerial Image Semantic Segmentation (IEEE TGRS2025))
- PPCM⭐ 2Official implementation of Many Paths, One Pass: Parallel Causal Modeling for Speculative Decoding.
- Trove⭐ 1Personal_Knowledge_Base
- VEGA⭐ 1Official implementation of Beyond Feature Alignment: Heterogeneous Visual Evidence Matching for Remote Sensing Image–Text Retrieval.