Junyan Li

8 papers · 2023–2026 · 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 ↓

🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (15)

Venues

CVPR (2) ICCV (2) AAAI (1) ECCV (1) ICLR (1) ICML (1)

Top co-authors

Chuang Gan (7) Peihao Chen (4) Yining Hong (3) Yikang Shen (2) Tianle Cai (2) Delin Chen (2) Zhenfang Chen (2) Litao Liu (1) Pengfei Yi (1) Yifan Han (1)

Research topics

Artificial Intelligence (5) Core AI (4) Computer Vision (3) Analysis (3) Machine Learning (2) Application Areas (2) Reinforcement Learning (1) Robotics (1) Applications (1) Capabilities (1) Core Methods (1) Generation (1) Learning Paradigms (1) Processing (1)

Keywords

large language model (3) embodied ai (2) video generation (1) expectation maximization (1) 3d vision (1) 3d scene understanding (1) efficient computing (1) instruction tuning (1) image super-resolution (1) vector quantization (1) multisensory perception (1) inverse dynamics (1) entity relationship (1) vision-language model (1) novel view synthesis (1) goal-conditioned policy (1) dense prediction (1) object-centric representation (1) 3d scene reconstruction (1) compositional reasoning (1)

Papers

FoAM: Foresight-Augmented Multi-Task Imitation Policy for Robotic Manipulation AAAI 2026 CommVQ: Commutative Vector Quantization for KV Cache Compression ICML 2025 Learning 4D Embodied World Models ICCV 2025 LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences CVPR 2025 CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decoding ICLR 2024 FlexAttention for Efficient High-Resolution Vision-Language Models ECCV 2024 MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World CVPR 2024 EfficientViT: Lightweight Multi-Scale Attention for High-Resolution Dense Prediction ICCV 2023