Li Yuan
19 papers · 5 citations
Most-cited papers
- Tokens-to-token Vit: Training Vision Transformers From Scratch On Imagenet2021 · 2247 citations
- LLM Lies: Hallucinations Are Not Bugs, But Features As Adversarial Examples2023 · 296 citations
- VOLO: Vision Outlooker For Visual Recognition2021 · 269 citations
- LOOK-M: Look-once Optimization In KV Cache For Efficient Multimodal Long-context Inference2024 · 84 citations
- Viewcrafter: Taming Video Diffusion Models For High-fidelity Novel View Synthesis2024 · 50 citations
- Collaborative Multi-lora Experts With Achievement-based Multi-tasks Loss For Unified Multimodal Information Extraction2025 · 3 citations
- Does Understanding Inform Generation In Unified Multimodal Models? From Analysis To Path Forward2025
Topics