Jingkuan Song
- Papers
- 11
Cite
Notes
Only stored in your browser.
Authored papers
11OmniCharacter: Towards Immersive Role-Playing Agents with Seamless Speech-Language Personality Interaction
arXiv 2025
A Survey on Efficient Vision-Language-Action Models
arXiv 2025
Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves
CVPR 2025 1
CoIN: A Benchmark of Continual Instruction tuNing for Multimodel Large Language Model
arXiv 2024
RoScenes: A Large-scale Multi-view 3D Dataset for Roadside Perception
arXiv 2024
Text-Video Retrieval with Global-Local Semantic Consistent Learning
arXiv 2024
A Closer Look at Few-shot Classification Again
arXiv 2023
Prototype-based Embedding Network for Scene Graph Generation
CVPR 2023 1
Part-Aware Transformer for Generalizable Person Re-identification
ICCV 2023 1
DETA: Denoised Task Adaptation for Few-Shot Learning
ICCV 2023 1
Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression
CVPR 2022 1
Affiliations
Frequent co-authors
10from 11 papers