Peng Jia

10 papers · 2024–2026 · 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 ↓

+1 more ↓

🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (21) 🐣 Hot Topic Early Bird 💎 Century Club · Bronze

⚡ Prolific Year · Productive

Venues

ICCV (3) AAAI (2) CVPR (2) CoRL (1) ECCV (1) ICML (1)

Top co-authors

Kun Zhan (7) XianPeng Lang (7) Haiyang Sun (3) Xiaodan Liang (3) Pengfei Li (2) Yupeng Zheng (2) Xueyang Zhang (2) Yang Wang (2) Yuhang Zheng (2) Yida Wang (2)

Research topics

Artificial Intelligence (7) Core AI (7) Computer Vision (6) Deep Learning (4) Domain-Specific (4) Generation (3) Machine Learning (2) Robotics (2) Analysis (2) Capabilities (2) Core Methods (2) Models (2) Mathematics & Optimization (1) Application Areas (1) Architectures (1)

Keywords

world model (3) autonomous driving (3) 3d gaussian splatting (3) vision-language model (2) large language model (2) trajectory prediction (2) chain-of-thought reasoning (1) self-supervised learning (1) scene understanding (1) bird's eye view (1) neural rendering (1) human behavior (1) robot manipulation (1) text retrieval (1) scene reconstruction (1) video generation (1) neural radiance field (1) knowledge graph embedding (1) hierarchical planning (1) robotic manipulation (1)

Papers

From Manuals to Actions: A Unified VLA Model for Chain-of-Thought Manual Generation and Robotic Manipulation CVPR 2026 Other Vehicle Trajectories Are Also Needed: A Driving World Model Unifies Ego-Other Vehicle Trajectories in Video Latent Space AAAI 2026 BEV-TSR: Text-Scene Retrieval in BEV Space for Autonomous Driving AAAI 2025 HiNeuS: High-fidelity Neural Surface Mitigating Low-texture and Reflective Ambiguity ICCV 2025 ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration CVPR 2025 RoboPearls: Editable Video Simulation for Robot Manipulation ICCV 2025 S2-Track: A Simple yet Strong Approach for End-to-End 3D Multi-Object Tracking ICML 2025 World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model ICCV 2025 DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models CoRL 2024 TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes ECCV 2024