4 papers
X-Cache: Cross-Chunk Block Caching for Few-Step Autoregressive World Models Inference
Yixiao Zeng, Jianlei Zheng, Chaoda Zheng +10
Real-time world simulation is becoming a key infrastructure for scalable evaluation and online reinforcement learning of autonomous driving systems. Recent driving world models bui…
Prompt-MII: Meta-Learning Instruction Induction for LLMs
Emily Xiao, Yixiao Zeng, Ada Chen +3
A popular method to adapt large language models (LLMs) to new tasks is in-context learning (ICL), which is effective but incurs high inference costs as context length grows. In thi…
RARE: Retrieval-Aware Robustness Evaluation for Retrieval-Augmented Generation Systems
Yixiao Zeng, Tianyu Cao, Danqing Wang +5
Retrieval-Augmented Generation (RAG) enhances recency and factuality in answers. However, existing evaluations rarely test how well these systems cope with real-world noise, confli…
Improving Multi-candidate Speculative Decoding
Xiaofan Lu, Yixiao Zeng, Feiyang Ma +2
Speculative Decoding (SD) is a technique to accelerate the inference of Large Language Models (LLMs) by using a lower complexity draft model to propose candidate tokens verified by…