Author

Shaofei Cai

Observed name: Cai, Shaofei

Observed institutions: Chinese Academy of Sciences, Peking University, Institute of Computing Technology, University of Chinese Academy of Sciences, ByteDance (China)

ORCID: 0000-0002-1195-7276

Observed ORCID: 0000-0002-1195-7276

OpenAlex ID: A5074233262

Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents

2023 · Wang, Zihao, Cai, Shaofei, et al. · arXiv (Cornell University) · 55

PDF

Rethinking Graph Neural Architecture Search from Message-passing

2021 · Shaofei Cai, Liang Li, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 54

PDF

JARVIS -1: Open-World Multi-Task Agents With Memory-Augmented Multimodal Language Models

2024 · Zihao Wang, Shaofei Cai, et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 35

Inductive State-Relabeling Adversarial Active Learning With Heuristic Clique Rescaling

2024 · Beichen Zhang, Liang Li, et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 26

Describe, Explain, Plan and Select: Interactive Planning with LLMs Enables Open-World Multi-Task Agents

2023 · Zihao Wang, Shaofei Cai, et al. · neural information processing systems · 20

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

2025 · DeepSeek-AI, Liu, Aixin, et al. · arXiv (Cornell University) · 19

PDF

IR-GAN: Image Manipulation with Linguistic Instruction by Increment Reasoning

2020 · Zhenhuan Liu, Jincan Deng, et al. · ACM International Conference on Multimedia (ACM MM) · 19

PDF

Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction

2023 · Shaofei Cai, Zihao Wang, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 11

PDF

DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editings

2023 · Bingchuan Li, Shaofei Cai, et al. · IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · 10

Automatic Relation-aware Graph Network Proliferation

2022 · Shaofei Cai, Liang Li, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 8

PDF

Semantic and Correlation Disentangled Graph Convolutions for Multilabel Image Recognition

2023 · Shaofei Cai, Liang Li, et al. · IEEE Transactions on Neural Networks and Learning Systems · 6

JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models

2023 · Wang, Zihao, Cai, Shaofei, et al. · arXiv (Cornell University) · 6

PDF

Rethinking Graph Neural Network Search from Message-passing.

2021 · Shaofei Cai, Liang Li, et al. · arXiv (Cornell University) · 6

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

2026 · DeepSeek-AI, Xu, Anyi, et al. · arXiv (Cornell University) · 4

PDF

ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting

2025 · Shaofei Cai, Zihao Wang, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2

PDF

GROOT: Learning to Follow Instructions by Watching Gameplay Videos

2023 · Cai, Shaofei, Zhang, Bowei, et al. · arXiv (Cornell University) · 2

PDF

DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editing

2021 · Li, Bingchuan, Cai, Shaofei, et al. · arXiv (Cornell University) · 2

PDF

CREATE: C ross-Layer Resilience Characterization and Optimization for Efficient yet R eliable E mbodied A I Sys te ms

2026 · Tong Xie, Yijiahao Qi, et al. · ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) · 1

Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning

2025 · Qin, Yulei, Tan, Xiaoyu, et al. · arXiv (Cornell University) · 1

PDF

A Survey on Vision-Language-Action Models: An Action Tokenization Perspective

2025 · Zhong, Yifan, Bai, Fengshuo, et al. · arXiv (Cornell University) · 1

PDF

Edge-featured Graph Neural Architecture Search

2021 · Cai, Shaofei, Li, Liang, et al. · arXiv (Cornell University) · 1

PDF

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

2026 · DeepSeek-AI, :, et al. · arXiv (Cornell University)

PDF