Jianfeng Gao
- Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation
- Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillation
- GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents
- Interpretable Next-token Prediction via the Generalized Induction Head
- Mixture of Inputs: Text Generation Beyond Discrete Token Sampling
- Reinforcement Learning for Reasoning in Large Language Models with One Training Example
- SAS: Simulated Attention Score
- Training Language Models to Generate Quality Code with Program Analysis Feedback