Shaohui Li

6 papers · 2024–2026 · 4 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 · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (17) 🐣 Hot Topic Early Bird 📈 Trend Setter

Venues

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

Top co-authors

Chenglin Li (3) Wenrui Dai (3) Zhi Li (3) Hongkai Xiong (3) Han Li (3) Yu Liu (3) Junni Zou (3) You He (3) Maida Cao (2) Nuowen Kan (1)

Research topics

Deep Learning (5) Artificial Intelligence (3) Computer Vision (3) Core AI (3) Learning Types (3) Processing (2) Machine Learning (1) Reinforcement Learning (1) Analysis (1) Application Areas (1) Architectures (1) Domain-Specific (1) Methods (1) Models (1) Techniques (1)

Keywords

rate-distortion performance (2) learned image compression (2) motion estimation (1) autonomous driving (1) sensor fusion (1) robust learning (1) 3d object detection (1) diffusion model (1) vision-language model (1) autonomous vehicle (1) multimodal alignment (1) window attention (1) collaborative perception (1) confidence estimation (1) feature decorrelation (1) zero-shot anomaly detection (1) multi-agent perception (1) multi-agent system (1) anomaly localization (1) random network distillation (1)

Papers

From Attraction to Equilibrium: Physics-Inspired Semantic Gravitons for Zero-Shot Anomaly Detection CVPR 2026 On Disentangled Training for Nonlinear Transform in Learned Image Compression ICLR 2025 Frequency-Aware Transformer for Learned Image Compression ICLR 2024 Image Compression for Machine and Human Vision With Spatial-Frequency Adaptation ECCV 2024 Multi-agent Collaborative Perception via Motion-aware Robust Communication Network CVPR 2024 ReDiffuser: Reliable Decision-Making Using a Diffuser with Confidence Estimation ICML 2024