Xuelong Li
- Adversarial Locomotion and Motion Imitation for Humanoid Policy Learning
- CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs
- KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills
- Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learning
- NFIG: Multi-Scale Autoregressive Image Generation via Frequency Ordering
- PUO-Bench: A Panel Understanding and Operation Benchmark with A Privacy-Preserving Framework
- Towards Reliable LLM-based Robots Planning via Combined Uncertainty Estimation