Scholar
Haoxiang Shi
Google Scholar ID: G8AeBN4AAAAJ
Waseda University
Nature Language Processing
Dense Retrieve
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
606
H-index
7
i10-index
6
Publications
15
Co-authors
3
list available
Contact
No contact links provided.
Publications
10 items
AV-SyncBench: Decoupled Benchmarking of Temporal and Semantic Audio-Visual Synchronization
2026
Cited
0
FreeSonic: Training-Free Temporal-Aware Decoupled Attention for Precise Audio Editing
2026
Cited
0
Beyond Waypoints: A Trajectory-Centric Waypointing Paradigm for Vision-Language Navigation
2026
Cited
0
VoiceGiraffe: A Benchmark for Extreme Long-Context Audio-Language Understanding
2026
Cited
0
OneLatent: Single-Token Compression for Visual Latent Reasoning
2026
Cited
0
VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions
2025
Cited
0
Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation
2025
Cited
0
DAgger Diffusion Navigation: DAgger Boosted Diffusion Policy for Vision-Language Navigation
2025
Cited
0
Load more
Resume (English only)
Co-authors
3 total
Jiaan Wang
WeChat AI, Tencent
Rongsheng Zhang
Fuxi AI Lab, NetEase Inc., Hangzhou, China
Yinhe Zheng
Alibaba
