papers

Publications (25)

cs.CV2026

Ego2Web: A Web Agent Benchmark Grounded in Egocentric Videos

Shoubin Yu, Lei Shu, Antoine Yang +6

Multimodal AI agents are increasingly automating complex real-world workflows that involve online web execution. However, current web-agent benchmarks suffer from a critical limita…

cs.CV2025

4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time

Ziqiao Ma, Xuweiyi Chen, Shoubin Yu +10

Can we scale 4D pretraining to learn general space-time representations that reconstruct an object from a few views at some times to any view at any time? We provide an affirmative…

cs.CV2024

A Simple LLM Framework for Long-Range Video Question-Answering

Ce Zhang, Taixi Lu, Md Mohaiminul Islam +4

We present LLoVi, a language-based framework for long-range video question-answering (LVQA). Unlike prior long-range video understanding methods, which are often costly and require…

cs.CV2025

VEGGIE: Instructional Editing and Reasoning Video Concepts with Grounded Generation

Shoubin Yu, Difan Liu, Ziqiao Ma +5

Recent video diffusion models have enhanced video editing, but it remains challenging to handle instructional editing and diverse tasks (e.g., adding, removing, changing) within a…

cs.CV2021

Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection

Shoubin Yu, Zhongyin Zhao, Haoshu Fang +6

Anomaly detection in surveillance videos is challenging and important for ensuring public security. Different from pixel-based anomaly detection methods, pose-based methods utilize…

cs.CV2026

EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding

Ziyang Wang, Yue Zhang, Shoubin Yu +6

Next-generation visual assistants, such as smart glasses, embodied agents, and always-on life-logging systems, must reason over an entire day or more of continuous visual experienc…

cs.CV2025

Training-free Guidance in Text-to-Video Generation via Multimodal Planning and Structured Noise Initialization

Jialu Li, Shoubin Yu, Han Lin +3

Recent advancements in text-to-video (T2V) diffusion models have significantly enhanced the visual quality of the generated videos. However, even recent T2V models find it challeng…

cs.CV2025

Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning

Ziyang Wang, Jaehong Yoon, Shoubin Yu +3

Despite advances in reinforcement learning (RL)-based video reasoning with large language models (LLMs), data collection and fine-tuning remain significant challenges. These method…

cs.CV2025

SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models

Andong Deng, Taojiannan Yang, Shoubin Yu +5

Large Multimodal Models (LMMs) have achieved remarkable progress across various capabilities; however, complex video reasoning in the scientific domain remains a significant and ch…

cs.CV2025

Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel

Zun Wang, Jialu Li, Yicong Hong +8

Creating high-quality data for training robust language-instructed agents is a long-lasting challenge in embodied AI. In this paper, we introduce a Self-Refining Data Flywheel (SRD…

cs.CV2023

Self-Chained Image-Language Model for Video Localization and Question Answering

Shoubin Yu, Jaemin Cho, Prateek Yadav +1

Recent studies have shown promising results on utilizing large pre-trained image-language models for video question answering. While these image-language models can efficiently boo…

cs.CV2025

Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level

Andong Deng, Tongjia Chen, Shoubin Yu +6

In this paper, we introduce Motion-Grounded Video Reasoning, a new motion understanding task that requires generating visual answers (video segmentation masks) according to the inp…

cs.AI2024

STAR: A Benchmark for Situated Reasoning in Real-World Videos

Bo Wu, Shoubin Yu, Zhenfang Chen +2

Reasoning in the real world is not divorced from situations. How to capture the present knowledge from surrounding situations and perform reasoning accordingly is crucial and chall…

cs.CV2025

Movie Facts and Fibs (MF): A Benchmark for Long Movie Understanding

Emmanouil Zaranis, António Farinhas, Saul Santos +28

Despite recent progress in vision-language models (VLMs), holistic understanding of long-form video content remains a significant challenge, partly due to limitations in current be…

cs.CV2026

When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning

Shoubin Yu, Yue Zhang, Zun Wang +4

Despite rapid progress in MLLMs, visual spatial reasoning remains unreliable when correct answers depend on how a scene would appear under unseen or alternative viewpoints. Recent…

cs.CV2025

RACCooN: A Versatile Instructional Video Editing Framework with Auto-Generated Narratives

Jaehong Yoon, Shoubin Yu, Mohit Bansal

Recent video generative models primarily rely on carefully written text prompts for specific tasks, like inpainting or style editing. They require labor-intensive textual descripti…

cs.CV2025

SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation

Jaehong Yoon, Shoubin Yu, Vaidehi Patil +2

Recent advances in diffusion models have significantly enhanced their ability to generate high-quality images and videos, but they have also increased the risk of producing unsafe…

cs.CV2026

STORM: Internalized Modeling for Spatial-Temporal Reasoning in Video-Language Models

Yiming Liang, Yixiao Chen, Yiyang Zhou +8

Many video reasoning tasks require tracking motion, temporal order, and evolving visual states across frames. Existing methods built on large vision-language models (LVLMs) often a…

cs.CL2026

Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution

Nithin Sivakumaran, Shoubin Yu, Hyunji Lee +4

Chain-of-thought (CoT) reasoning sometimes fails to faithfully reflect the true computation of a large language model (LLM), hampering its utility in explaining how LLMs arrive at…

cs.CV2025

VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos

Ziyang Wang, Shoubin Yu, Elias Stengel-Eskin +4

Long-form video understanding is complicated by the high redundancy of video data and the abundance of query-irrelevant information. To tackle these challenges, we propose VideoTre…

cs.LG2026

Humanity's Last Exam

Long Phan, Alice Gatti, Ziwen Han +1144

Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…

cs.CV2026

VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting

Daeun Lee, Shoubin Yu, Yue Zhang +1

Video reasoning requires models to locate and track question-relevant evidence across frames. While reinforcement learning (RL) with verifiable rewards improves accuracy, it still…

cs.CV2025

MEXA: Towards General Multimodal Reasoning with Dynamic Multi-Expert Aggregation

Shoubin Yu, Yue Zhang, Ziyang Wang +2

Combining pre-trained expert models offers substantial potential for scalable multimodal reasoning, but building a unified framework remains challenging due to the increasing diver…

cs.CV2025

Prune-Then-Plan: Step-Level Calibration for Stable Frontier Exploration in Embodied Question Answering

Noah Frahm, Prakrut Patel, Yue Zhang +3

Large vision-language models (VLMs) have improved embodied question answering (EQA) agents by providing strong semantic priors for open-vocabulary reasoning. However, when used dir…

cs.CV2025

CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion

Shoubin Yu, Jaehong Yoon, Mohit Bansal

Despite impressive advancements in recent multimodal reasoning approaches, they are still limited in flexibility and efficiency, as these models typically process only a few fixed…