SY
Shoubin Yu
cs.CVcs.AIcs.CLcs.LGcs.RO
On Valency
published · living versionsW_hvdxbc96·v1 · currentpublished
Knowing When to Stop: The Evidence-Action Gap in Coding Agents
with Tianyu Chen, Xinran Zhao, Vijay Viswanathan, Mingyuan Zhou +1
1 version
W_p79tjmy3·v1published
Preprints & journals
26 papers in the corpus · 2021–2026Ego2Act: Evaluating Goal-Directed Manipulation in Egocentric Video Generation2610.01092v1 · Patrick Amadeus Irawan, Iskandar Muda Rizky Parlambang, Rava Maulana et al.2026 · 0 citationsarXiv
STORM: Internalized Modeling for Spatial-Temporal Reasoning in Video-Language Models2605.26014v1 · Yiming Liang, Yixiao Chen, Yiyang Zhou et al.2026 · 0 citationsarXiv
EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding2605.09874v2 · Ziyang Wang, Yue Zhang, Shoubin Yu et al.2026 · 0 citationsarXiv
Ego2Web: A Web Agent Benchmark Grounded in Egocentric Videos2603.22529v1 · Shoubin Yu, Lei Shu, Antoine Yang et al.2026 · 0 citationsarXiv
VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting2603.14659v2 · Daeun Lee, Shoubin Yu, Yue Zhang et al.2026 · 0 citationsarXiv
Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution2602.16154v1 · Nithin Sivakumaran, Shoubin Yu, Hyunji Lee et al.2026 · 0 citationsarXiv
When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning2602.08236v2 · Shoubin Yu, Yue Zhang, Zun Wang et al.2026 · 0 citationsarXiv
Prune-Then-Plan: Step-Level Calibration for Stable Frontier Exploration in Embodied Question Answering2511.19768v1 · Noah Frahm, Prakrut Patel, Yue Zhang et al.2025 · 0 citationsarXiv
SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models2510.08559v1 · Andong Deng, Taojiannan Yang, Shoubin Yu et al.2025 · 0 citationsarXiv
Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning2507.06485v2 · Ziyang Wang, Jaehong Yoon, Shoubin Yu et al.2025 · 7 citationsarXiv
4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time2506.18890v1 · Ziqiao Ma, Xuweiyi Chen, Shoubin Yu et al.2025 · 5 citationsarXiv
MEXA: Towards General Multimodal Reasoning with Dynamic Multi-Expert Aggregation2506.17113v2 · Shoubin Yu, Yue Zhang, Ziyang Wang et al.2025 · 1 citationarXiv
How Well Do Vision-Language Models Understand Movies?2506.06275v2 · Emmanouil Zaranis, Ant'onio Farinhas, Saul Santos et al.2025 · 0 citationsarXiv
Training-free Guidance in Text-to-Video Generation via Multimodal Planning and Structured Noise Initialization2504.08641v1 · Jialu Li, Shoubin Yu, Han Lin et al.2025 · 0 citationsarXiv
VEGGIE: Instructional Editing and Reasoning Video Concepts with Grounded Generation2503.14350v3 · Shoubin Yu, Difan Liu, Ziqiao Ma et al.2025 · 3 citationsarXiv
Humanity's Last Exam2501.14249v12 · Long Phan, Alice Gatti, Ziwen Han et al.2025 · 61 citationsarXiv
Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel2412.08467v2 · Zun Wang, Jialu Li, Yicong Hong et al.2024 · 0 citationsarXiv
Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level2411.09921v2 · Andong Deng, Tongjia Chen, Shoubin Yu et al.2024 · 11 citationsarXiv
SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation2410.12761v2 · Jaehong Yoon, Shoubin Yu, Vaidehi Patil et al.2024 · 2 citationsarXiv
VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos2405.19209v3 · Ziyang Wang, Shoubin Yu, Elias Stengel-Eskin et al.2024 · 54 citationsarXiv
RACCooN: A Versatile Instructional Video Editing Framework with Auto-Generated Narratives2405.18406v4 · Jaehong Yoon, Shoubin Yu, Mohit Bansal2024 · 0 citationsarXiv
STAR: A Benchmark for Situated Reasoning in Real-World Videos2405.09711v1 · Bo Wu, Shoubin Yu, Zhenfang Chen et al.2024 · 22 citationsarXiv
CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion2402.05889v4 · Shoubin Yu, Jaehong Yoon, Mohit Bansal2024 · 3 citationsarXiv
A Simple LLM Framework for Long-Range Video Question-Answering2312.17235v3 · Ce Zhang, Taixi Lu, Md Mohaiminul Islam et al.2023 · 60 citationsarXiv
Self-Chained Image-Language Model for Video Localization and Question Answering2305.06988v2 · Shoubin Yu, Jaemin Cho, Prateek Yadav et al.2023 · 74 citationsarXiv
Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection2112.03649v2 · Shoubin Yu, Zhongyin Zhao, Haoshu Fang et al.2021 · 23 citationsarXiv
Career total: 32 works. 26 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.