Skip to content
conftrace_

Shaofei Cai

11 papers · 2021–2026 · 6 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
+5 more ↓ πŸ—ΊοΈ Taxonomy Completionist (27) 🌍 Conference Polyglot Β· Silver 🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge Β· Silver πŸƒ Academic Marathon Β· Sprint
🧬 Topic Evolution πŸ“ˆ Trend Setter πŸ”₯ Unstoppable Β· Bronze πŸ’Ž Century Club Β· Bronze πŸ—ƒοΈ Keyword Collector (56)

Venues

CVPR (4) ICLR (2) NeurIPS (2) AAAI (1) ICCV (1) WACV (1)

Top co-authors

Yitao Liang (8) Anji Liu (8) Zihao Wang (7) Xiaojian Ma (5) Zhancun Mu (3) Qingming Huang (2) Bowei Zhang (2) Haowei Lin (2) Zheng-Jun Zha (2) Liang Li (2)

Research topics

Artificial Intelligence (9) Core AI (9) Machine Learning (8) Deep Learning (5) Architectures (5) Learning Types (5) Core Methods (3) Computer Vision (2) Robotics (2) Capabilities (2) Learning Paradigms (2) Techniques (2) Natural Language Processing (1) Analysis (1) Application Areas (1)

Keywords

instruction following (3) video understanding (2) message passing (2) spatial reasoning (2) neural architecture search (2) zero-shot generalization (2) graph neural network (2) multi-task learning (2) imitation learning (1) model architecture (1) autoregressive transformer (1) zero-shot learning (1) multimodal learning (1) action prediction (1) weakly supervised learning (1) skill discovery (1) self-supervised learning (1) behavior cloning (1) robot learning (1) style transfer (1)

Papers

Steering Visuomotor Policy in Open Worlds via Cross-View Goal Alignment AAAI 2026 GROOT-2: Weakly Supervised Multimodal Instruction Following Agents ICLR 2025 Open-World Skill Discovery from Unsegmented Demonstration Videos ICCV 2025 ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting CVPR 2025 GROOT: Learning to Follow Instructions by Watching Gameplay Videos ICLR 2024 OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents NeurIPS 2024 Describe, Explain, Plan and Select: Interactive Planning with LLMs Enables Open-World Multi-Task Agents NeurIPS 2023 DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editings WACV 2023 Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction CVPR 2023 Automatic Relation-Aware Graph Network Proliferation CVPR 2022 Rethinking Graph Neural Architecture Search From Message-Passing CVPR 2021