ST
Shuhan Tan
cs.CVcs.AIcs.ROcs.LGstat.MLcs.CLcs.MA
On Valency
published · living versionsW_z6b3gjgg·v1 · currentpublished
Should the Action Expert Train the VLM? Action-Token Supervision and Gradient Routing in Mixture-of-Transformer VLAs
with Asher James Hancock, Boyi Li, Yuxiao Chen, Wenhao Ding +4
1 version
Preprints & journals
16 papers in the corpus · 2019–2026Parametric Trajectory Distillation for Few-Step Video Generation2610.11498v1 · Lan Feng, Peter Karkus, Maximilian Igl et al.2026 · 0 citationsarXiv
Grounding What Shapes the Plan: Rethinking Groundedness for Physical Intelligence in Autonomous Driving2610.07521v1 · Minkyoung Cho, Zewei Zhou, Wenhao Ding et al.2026 · 0 citationsarXiv
Latent Chain-of-Thought World Modeling for End-to-End Driving2512.10226v3 · Shuhan Tan, Kashyap Chitta, Yuxiao Chen et al.2025 · 0 citationsarXiv
SceneDiffuser++: City-Scale Traffic Simulation via a Generative World Model2506.21976v1 · Shuhan Tan, John Lambert, Hong Jeon et al.2025 · 5 citationsarXiv
Long-term Traffic Simulation with Interleaved Autoregressive Motion and Scenario Generation2506.17213v2 · Xiuyu Yang, Shuhan Tan, Philipp Krahenbuhl2025 · 1 citationarXiv
Interactive Post-Training for Vision-Language-Action Models2505.17016v1 · Shuhan Tan, Kairan Dou, Yue Zhao et al.2025 · 0 citationsarXiv
Promptable Closed-loop Traffic Simulation2409.05863v1 · Shuhan Tan, Boris Ivanovic, Yuxiao Chen et al.2024 · 0 citationsarXiv
Wolf: Dense Video Captioning with a World Summarization Framework2407.18908v2 · Boyi Li, Ligeng Zhu, Ran Tian et al.2024 · 1 citationarXiv
Language Conditioned Traffic Generation2307.07947v1 · Shuhan Tan, Boris Ivanovic, Xinshuo Weng et al.2023 · 15 citationsarXiv
EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understanding2301.02217v1 · Shuhan Tan, Tushar Nagarajan, Kristen Grauman2023 · 8 citationsarXiv
TrafficGen: Learning to Generate Diverse and Realistic Traffic Scenarios2210.06609v2 · Lan Feng, Quanyi Li, Zhenghao Peng et al.2022 · 113 citationsarXiv
SceneGen: Learning to Generate Realistic Traffic Scenes2101.06541v1 · Shuhan Tan, Kelvin Wong, Shenlong Wang et al.2021 · 104 citationsarXiv
Improving the Fairness of Deep Generative Models without Retraining2012.04842v2 · Shuhan Tan, Yujun Shen, Bolei Zhou2020 · 25 citationsarXiv
LiDARsim: Realistic LiDAR Simulation by Leveraging the Real World2006.09348v1 · Sivabalan Manivasagam, Shenlong Wang, Kelvin Wong et al.2020 · 241 citationsarXiv
Class-imbalanced Domain Adaptation: An Empirical Odyssey1910.10320v2 · Shuhan Tan, Xingchao Peng, Kate Saenko2019 · 76 citationsarXiv
Weakly Supervised Open-set Domain Adaptation by Dual-domain Collaboration1904.13179v1 · Shuhan Tan, Jiening Jiao, Wei-Shi Zheng2019 · 27 citationsarXiv
Career total: 21 works. 16 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.