Yanan Sun

34 papers · 2019–2026 · 9 conferences · across top CS/AI conferences

Achievements

🗺️ Taxonomy Completionist (61) 🌉 Interdisciplinary Bridge 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (8) 🏃 Academic Marathon (6) 🧭 Keyword Pioneer 🐝 Cross-Pollinator (10) 🏆 Grand Slam 🧬 Topic Evolution 🏆 Keyword Champion (2) 💎 Century Club (32) 🔥 Unstoppable (7) 🗃️ Keyword Collector (130) ⚡ Prolific Year (9)

Conferences

CVPR (9) ICCV (7) ECCV (5) ICML (4) IJCAI (3) AAAI (2) ICLR (2) ACML (1) NIPS (1)

Top co-authors

Zetong Yang (6) Chi-Keung Tang (5) Yu-Wing Tai (5) Yuqi Feng (5) Xiaotian Song (4) Jiahao Fan (4) Jiaya Jia (4) Han Ji (4) Hangjie Yuan (3) Kai Chen (3)

Keywords

neural architecture search (7) 3d object detection (4) alpha matte (4) representation learning (3) semantic segmentation (3) point cloud (3) 3d detection (3) neural network architecture (2) neural network (2) image matting (2) neural predictor (2) catastrophic forgetting (2) model compression (2) video matting (2) continual learning (2) autonomous driving (2) energy efficiency (2) graph neural network (2) neuromorphic computing (1) feature extraction (1)

Papers

LAS: Loss-less ANN-SNN Conversion for Fully Spike-Driven Large Language Models AAAI 2026

Adapt Before Continual Learning AAAI 2026

FaceShot: Bring Any Character into Life ICLR 2025

MotionShot: Adaptive Motion Transfer across Arbitrary Objects for Text-to-Video Generation ICCV 2025

Zero-cost Proxy for Adversarial Robustness Evaluation ICLR 2025

Prior Knowledge Guided Neural Architecture Generation ICML 2025

Runtime Analysis of Evolutionary NAS for Multiclass Classification ICML 2025

Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective ICML 2025

Detect Anything 3D in the Wild ICCV 2025

CARL: Causality-guided Architecture Representation Learning for an Interpretable Performance Predictor ICCV 2025

Loss Functions for Predictor-based Neural Architecture Search ICCV 2025

Visual Point Cloud Forecasting enables Scalable Autonomous Driving CVPR 2024

Revisiting Neural Networks for Continual Learning: An Architectural Perspective IJCAI 2024

Towards Accurate and Robust Architectures via Neural Architecture Search CVPR 2024

One-step Spiking Transformer with a Linear Complexity IJCAI 2024

Position: Exploring the Robustness of Pipeline-Parallelism-Based Decentralized Training ICML 2024

AnyControl: Create Your Artwork with Versatile Control on Text-to-Image Generation ECCV 2024

Generalizable Symbolic Optimizer Learning ECCV 2024

CAP: A Context-Aware Neural Predictor for NAS IJCAI 2024

Communication-efficient Federated Learning with Single-Step Synthetic Features Compressor for Faster Convergence ICCV 2023

Evolutionary Neural Architecture Search for Multivariate Time Series Forecasting ACML 2023

Ultrahigh Resolution Image/Video Matting With Spatio-Temporal Sparsity CVPR 2023

Bridge the Gap Between Architecture Spaces via A Cross-Domain Predictor NIPS 2022

A Unified Query-Based Paradigm for Point Cloud Understanding CVPR 2022

Human Instance Matting via Mutual Guidance and Multi-Instance Refinement CVPR 2022

Audio-Driven Stylized Gesture Generation with Flow-Based Model ECCV 2022

Homogeneous Architecture Augmentation for Neural Predictor ICCV 2021

Autoregressive Stylized Motion Synthesis With Generative Flow CVPR 2021

Deep Video Matting via Spatio-Temporal Alignment and Aggregation CVPR 2021

Semantic Image Matting CVPR 2021

3DSSD: Point-Based 3D Single Stage Object Detector CVPR 2020

GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision ECCV 2020

CN: Channel Normalization For Point Cloud Recognition ECCV 2020

STD: Sparse-to-Dense 3D Object Detector for Point Cloud ICCV 2019