An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models
Liang Chen, Haozhe Zhao, Tianyu Liu, Shuai Bai, Junyang Lin, Chang Zhou, Baobao Chang
Who it is from
Alibaba Groupaffiliation declared by the authors, according to OpenAlex- Peking Universityaffiliation declared by the authors, according to OpenAlex
Other papers from the same organizations
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language ModelsPeking University · 12,684 citations
- DETRs Beat YOLOs on Real-time Object DetectionBaidu · 8,096 citations
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any ResolutionAlibaba Group · 6,193 citations
- DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code IntelligencePeking University · 2,491 citations
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation ModelsAlibaba Group · 2,422 citations
- T2I-Adapter: Learning Adapters to Dig Out More Controllable Ability for Text-to-Image Diffusion ModelsChinese Academy of Sciences · 2,217 citations