Jun Peng

6 papers · 2022–2026 · 5 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

AAAI (2) ECCV (1) ICCV (1) ICML (1) IJCAI (1)

Top co-authors

Rongrong Ji (3) Yunhang Shen (2) Feidiao Yang (2) Yuxin Zhang (2) Yonghong Tian (2) Xiawu Zheng (2) Xiaoshuai Sun (2) Guangyao Chen (2) Yiyi Zhou (2) Zhilin Huang (1)

Research topics

Artificial Intelligence (4) Core AI (4) Computer Vision (2) Machine Learning (2) Core Methods (2) Computer Science (1) Deep Learning (1) Analysis (1) Application Areas (1) Applications (1) Generation (1) Learning Paradigms (1) Models (1) Processing (1)

Keywords

feature alignment (1) transfer learning (1) object detection (1) symbolic reasoning (1) event camera (1) video understanding (1) efficient inference (1) parameter-efficient fine-tuning (1) feature fusion (1) vision-language model (1) token pruning (1) video question answering (1) prompt tuning (1) visual understanding (1) object detector (1) recursive network (1) geometric regularization (1) multi-view consistency (1) event recognition (1) keyframe selection (1)

Papers

KTV: Keyframes and Key Tokens Selection for Efficient Training-Free Video LLMs AAAI 2026 From Objects to Events: Unlocking Complex Visual Understanding in Object Detectors via LLM-guided Symbolic Reasoning ICCV 2025 TextRefiner: Internal Visual Feature as Efficient Refiner for Vision-Language Models Prompt Tuning AAAI 2025 Efficient Event Stream Super-Resolution with Recursive Multi-Branch Fusion IJCAI 2024 Fast Text-to-3D-Aware Face Generation and Manipulation via Direct Cross-modal Mapping and Geometric Regularization ICML 2024 PixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generation ECCV 2022