Shuicheng Yan
13 papers · 0 citations
Most-cited papers
- Tokens-to-token Vit: Training Vision Transformers From Scratch On Imagenet2021 · 1881 citations
- Highly Efficient Salient Object Detection With 100K Parameters2020 · 164 citations
- VOLO: Vision Outlooker For Visual Recognition2021 · 157 citations
- Omg-llava: Bridging Image-level, Object-level, Pixel-level Reasoning And Understanding2024 · 150 citations
- Skywork: A More Open Bilingual Foundation Model2023 · 128 citations
- Enhancing Video-language Representations With Structural Spatio-temporal Alignment2024 · 75 citations
- Towards Semantic Equivalence Of Tokenization In Multimodal LLM2024 · 62 citations
- Multi-prototype Networks For Unconstrained Set-based Face Recognition2019 · 37 citations
- Stprivacy: Spatio-temporal Privacy-preserving Action Recognition2023 · 28 citations
- Demystifying Reinforcement Learning In Agentic Reasoning2025
- Patch-as-decodable-token: Towards Unified Multi-modal Vision Tasks In Mllms2025
- Reinforcement Learning Tuning For Videollms: Reward Design And Data Efficiency2025
- Visual Multi-agent System: Mitigating Hallucination Snowballing Via Visual Flow2025
- Tokenar: Multiple Subject Generation Via Autoregressive Token-level Enhancement2025
- Ivebench: Modern Benchmark Suite For Instruction-guided Video Editing Assessment2025
Topics