Profiles2021-2026ORCID 0000-0003-0284-9940
Shaohui Lin
East China Normal University
15Papers
4Last author
33Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers15
- Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought CompressionAuthor 11 of 11ICML 2026 · 5 citations
- Omni-Supervised Motion Editing: Balancing Change and Invariance through Positive-Negative LearningAuthor 10 of 10CVPR 2026 · 4 citations
- CSD: Content-aware Speculative Decoding for Efficient Image GenerationAuthor 11 of 11ICML 2026
- Dynamic Contrastive Knowledge Distillation for Efficient Image RestorationAuthor 9 of 9AAAI 2025 · 7 citations
- TimeSoccer: An End-to-End Multimodal Large Language Model for Soccer Commentary GenerationAuthor 6 of 8ACM MM 2025 · 2 citations
- Aligning and Prompting Everything All at Once for Universal Visual PerceptionAuthor 8 of 9CVPR 2024 · 19 citations
- Kumaraswamy Wavelet for Heterophilic Scene Graph GenerationAuthor 3 of 5AAAI 2024 · 2 citations
- CLIP-Driven Open-Vocabulary 3D Scene Graph Generation via Cross-Modality Contrastive LearningAuthor 4 of 6CVPR 2024
- Adaptive Hierarchy-Branch Fusion for Online Knowledge DistillationAuthor 2 of 10AAAI 2023 · 16 citations
- Explicit Invariant Feature Induced Cross-Domain Crowd CountingAuthor 4 of 7AAAI 2023 · 7 citations
- HybridCR: Weakly-Supervised 3D Point Cloud Semantic Segmentation via Hybrid Contrastive RegularizationAuthor 7 of 8CVPR 2022 · 92 citations
- Comprehensive Regularization in a Bi-directional Predictive Network for Video Anomaly DetectionAuthor 3 of 10AAAI 2022 · 68 citations
- Self-supervised Models are Good Teaching Assistants for Vision TransformersAuthor 4 of 7ICML 2022 · 26 citations
- Contrastive Learning for Compact Single Image DehazingAuthor 3 of 8CVPR 2021
- Towards Compact CNNs via Collaborative CompressionAuthor 2 of 10CVPR 2021
