Прати
Shaobo Wang
Shaobo Wang
Shanghai Jiao Tong University
Верификована је имејл адреса на sjtu.edu.cn - Почетна страница
Наслов
Навело
Навело
Година
Think2Drive: Efficient Reinforcement Learning by Thinking with Latent World Model for Autonomous Driving (in CARLA-v2)
Q Li, X Jia, S Wang, J Yan
(ECCV 2024) The Eighteenth European Conference on Computer Vision ECCV 2024, 2024
222024
Visualizing the Emergence of Intermediate Visual Patterns in DNNs
M Li, S Wang, Q Zhang
(NeurIPS 2021) Thirty-Fifth Annual Conference on Neural Information …, 2021
142021
Unveiling induction heads: Provable training dynamics and feature learning in transformers
S Chen, H Sheen, T Wang, Z Yang
(NeurIPS 2024) The Thirty-Eighth Annual Conference on Neural Information …, 2024
92024
Trap of feature diversity in the learning of mlps
D Liu, S Wang, J Ren, K Wang, S Yin, H Deng, Q Zhang
arXiv preprint arXiv:2112.00980, 2021
72021
Not all samples should be utilized equally: Towards understanding and improving dataset distillation
S Wang, Y Yang, Q Wang, K Li, L Zhang, J Yan
arXiv preprint arXiv:2408.12483, 2024
42024
Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More
Z Wen, Y Gao, S Wang, J Zhang, Q Zhang, W Li, C He, L Zhang
arXiv preprint arXiv:2502.11494, 2025
2025
Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Models
S Wang, H Tang, M Wang, H Zhang, X Liu, W Li, X Hu, L Zhang
(ICLR 2025) The Thirteenth International Conference on Learning Representations, 2024
2024
DRUPI: Dataset Reduction Using Privileged Information
S Wang, Y Yang, S Zhang, C Sun, W Li, X Hu, L Zhang
arXiv preprint arXiv:2410.01611, 2024
2024
Unified Batch Normalization: Identifying and Alleviating the Feature Condensation in Batch Normalization and a Unified Framework
S Wang, X Zhang, D Liu, J Yan
arXiv preprint arXiv:2311.15993, 2023
2023
Систем тренутно не може да изврши ову радњу. Пробајте поново касније.
Чланци 1–9