Yu Cheng
18 papers · 3 citations
Most-cited papers
- Llama-moe: Building Mixture-of-experts From Llama With Continual Pre-training2024 · 146 citations
- MAGIS: Llm-based Multi-agent Framework For Github Issue Resolution2024 · 143 citations
- Context-aware Biaffine Localizing Network For Temporal Sentence Grounding2021 · 106 citations
- Grounded-videollm: Sharpening Fine-grained Temporal Grounding In Video Large Language Models2024 · 70 citations
- UC2: Universal Cross-lingual Cross-modal Vision-and-language Pre-training2021 · 54 citations
- Monocular 3D Multi-person Pose Estimation By Integrating Top-down And Bottom-up Networks2021 · 45 citations
- Moe-i\(^2\): Compressing Mixture Of Experts Models Through Inter-expert Pruning And Intra-expert Low-rank Decomposition2024 · 42 citations
- Living In The Moment: Can Large Language Models Grasp Co-temporal Reasoning?2024 · 32 citations
- The Principle Of Diversity: Training Stronger Vision Transformers Calls For Reducing All Levels Of Redundancy2022 · 30 citations
- Unsupervised Temporal Video Grounding With Deep Semantic Clustering2022 · 27 citations
- Grounded-videollm: Sharpening Fine-grained Temporal Grounding In Video Large Language Models2024 · 9 citations
- Smfusion: Semantic-preserving Fusion Of Multimodal Medical Images For Enhanced Clinical Diagnosis2025 · 2 citations
- Visually Interpretable Subtask Reasoning For Visual Question Answering2025 · 1 citations
- Clip-moe: Towards Building Mixture Of Experts For CLIP With Diversified Multiplet Upcycling2024 · 1 citations
- Interleaving Reasoning For Better Text-to-image Generation2025
Topics