RA
Ruichuan An
cs.CVcs.AIcs.CLcs.LGcs.ROcs.IRcs.MMcs.SIeess.IVq-fin.CP
On Valency
published · living versionsW_9bfw4gjt·v1 · currentpublished
Dual Exam: Controlled Evaluation of Multimodal Agents and World Models
with Zhefan Rao, Meng Chu, Xuan Zhang, Jingfan Chen +78
1 version
Preprints & journals
42 papers in the corpus · 2023–2026VIEWCRAFT: Evolving What Multimodal Agents See and How They Read It2610.15915v1 · Binxiao Xu, Ruichuan An, Bocheng Zou et al.2026 · 0 citationsarXiv
From Scores to Samples: Elastic Forcing for Autoregressive Video Generation2609.35491v3 · Chi Zhang, Yueyi Liu, Shi Haoyang et al.2026 · 0 citationsarXiv
Unifying Distributional Training for One-Step Visual Generation2609.35763v4 · Chi Zhang, Shi Haoyang, Yueyi Liu et al.2026 · 0 citationsarXiv
VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System2607.27380v2 · Haodong Li, Tianfei Ren, Xiaoxiao Ma et al.2026 · 0 citationsarXiv
SteerVTE: Seamless Video Text Editing with Style and Glyph Control2606.23254v2 · Kai Zeng, Moran Li, Zhengwei Wang et al.2026 · 0 citationsNeurIPS 2026
Agent Skills Should Go Beyond Text: The Case for Visual Skills2606.01414v1 · Binxiao Xu, Ruichuan An, Bocheng Zou et al.2026 · 0 citationsarXiv
Rethinking VLM Representation for VLA Initialization2605.25802v1 · Weifeng Lin, Siyuan Huang, Hao Li et al.2026 · 0 citationsarXiv
DataPrep-Bench: Benchmarking LLMs as Training Data Preparators2607.20465v1 · Hao Liang, Qifeng Cai, Yibo Lin et al.2026 · 0 citationsarXiv
TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning2605.18109v1 · ZhiYuan Feng, Yu Deng, Ruichuan An et al.2026 · 0 citationsarXiv
VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction2605.15186v2 · Kaixin Zhu, Yiwen Tang, Yifan Yang et al.2026 · 0 citationsarXiv
Uni-Synergy: Bridging Understanding and Generation for Personalized Reasoning via Co-operative Reinforcement Learning2605.10445v1 · Zijun Shen, Sihan Yang, Ruichuan An et al.2026 · 0 citationsarXiv
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models2604.04707v2 · DataFlow Team, Bohan Zeng, Daili Hua et al.2026 · 0 citationsarXiv
DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models2603.26164v2 · Hao Liang, Zhengyang Zhao, Mingrui Chen et al.2026 · 0 citationsarXiv
MME-CoF-Pro: Evaluating Reasoning Coherence in Video Generative Models with Text and Visual Hints2603.20194v1 · Yu Qi, Xinyi Xu, Ziyu Guo et al.2026 · 0 citationsarXiv
PEARL: Personalized Streaming Video Understanding Model2603.20422v1 · Yuanhong Zheng, Ruichuan An, Xiaopeng Lin et al.2026 · 0 citationsarXiv
GENIUS: Generative Fluid Intelligence Evaluation Suite2602.11144v1 · Ruichuan An, Sihan Yang, Ziyu Guo et al.2026 · 0 citationsarXiv
GUI-GenBench: Evaluating Image Generation Models as Interactive GUI Environments2602.09007v3 · Haodong Li, Jingwei Wu, Quan Sun et al.2026 · 0 citationsarXiv
QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining2602.07085v3 · Jun Han, Shuo Zhang, Wei Li et al.2026 · 0 citationsarXiv
Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks2602.01630v1 · Bohan Zeng, Kaixin Zhu, Daili Hua et al.2026 · 0 citationsarXiv
How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editing2602.01851v2 · Huanyu Zhang, Xuehai Bai, Chengzu Li et al.2026 · 0 citationsarXiv
Thinking in Frames: How Visual Context and Test-Time Scaling Empower Video Reasoning2601.21037v1 · Chengzu Li, Zanyi Wang, Jiaang Li et al.2026 · 0 citationsarXiv
CoF-T2I: Video Models as Pure Visual Reasoners for Text-to-Image Generation2601.10061v1 · Chengzhuo Tong, Mingkun Chang, Shenglong Zhang et al.2026 · 0 citationsarXiv
Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark2510.26802v1 · Ziyu Guo, Xinyan Chen, Renrui Zhang et al.2025 · 1 citationarXiv
Robobench: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models as Embodied Brain2510.17801v2 · Yulin Luo, Chun-Kai Fan, Menghang Dong et al.2025 · 2 citationsarXiv
MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoning2510.14265v1 · Xukai Wang, Xuanbo Liu, Mingrui Chen et al.2025 · 0 citationsarXiv
CapGeo-Bench: Decoupling Visual Perception from Reasoning and Evaluating Geometric Understanding2510.09302v2 · Yuying Li, Siyi Qian, Hao Liang et al.2025 · 0 citationsarXiv
WoW: Towards a World omniscient World model Through Embodied Interaction2509.22642v2 · Xiaowei Chi, Peidong Jia, Chun-Kai Fan et al.2025 · 0 citationsarXiv
Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos2506.05302v1 · Weifeng Lin, Xinyu Wei, Ruichuan An et al.2025 · 8 citationsarXiv
Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking2505.20199v1 · Pengxiang Li, Shilin Yan, Joey Tsai et al.2025 · 1 citationarXiv
SpikeGen: Decoupled "Rods and Cones" Visual Representation Processing with Latent Generative Framework2505.18049v2 · Gaole Dai, Menghang Dong, Rongyu Zhang et al.2025 · 0 citationsarXiv
LoVR: A Benchmark for Long Video Retrieval in Multimodal Contexts2505.13928v4 · Qifeng Cai, Hao Liang, Zhaoyang Han et al.2025 · 1 citationarXiv
UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens2505.14671v3 · Ruichuan An, Sihan Yang, Renrui Zhang et al.2025 · 5 citationsNeurIPS 2025
MC-LLaVA: Multi-Concept Personalized Vision-Language Model2503.18854v2 · Ruichuan An, Sihan Yang, Ming Lu et al.2025 · 0 citationsarXiv
Concept-as-Tree: A Controllable Synthetic Data Framework Makes Stronger Personalized VLMs2503.12999v4 · Ruichuan An, Kai Zeng, Ming Lu et al.2025 · 0 citationsarXiv
MathDebugger: Detecting and Diagnosing Errors in Synthetic Mathematical Data2502.19058v2 · Hao Liang, Meiyi Qiang, Yuying Li et al.2025 · 0 citationsarXiv
MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders2501.01709v3 · Jiajun Cao, Yuan Zhang, Tao Huang et al.2025 · 13 citationsarXiv
MC-LLaVA: Multi-Concept Personalized Vision-Language Model2411.11706v4 · Ruichuan An, Sihan Yang, Renrui Zhang et al.2024 · 3 citationsarXiv
Can Modifying Data Address Graph Domain Adaptation?2407.19311v1 · Renhong Huang, Jiarong Xu, Xin Jiang et al.2024 · 4 citationsarXiv
LLM as Dataset Analyst: Subpopulation Structure Discovery with Large Language Model2405.02363v2 · Yulin Luo, Ruichuan An, Bocheng Zou et al.2024 · 13 citationsarXiv
Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want2403.20271v3 · Weifeng Lin, Xinyu Wei, Ruichuan An et al.2024 · 3 citationsarXiv
MoSA: Mixture of Sparse Adapters for Visual Efficient Tuning2312.02923v2 · Qizhe Zhang, Bocheng Zou, Ruichuan An et al.2023 · 0 citationsarXiv
MoEC: Mixture of Experts Implicit Neural Compression2312.01361v1 · Jianchen Zhao, Cheng-Ching Tseng, Ming Lu et al.2023 · 0 citationsarXiv
Career total: 48 works. 42 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.