collaborators

5 papers

cs.AI2026

RedKnot-MLA: Multi-Head Offline-Online Reuse for DeepSeek-V4 Long-Context Serving

Yang Liu, Zhaokai Luo, Huayi Jin +10

Multi-head latent attention (MLA) exposes many logical query heads through one packed latent KV stream. This representation is memory efficient, but it removes the physical per-hea…

cs.AI2026

RedKnot: Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention

Yang Liu, Zhaokai Luo, Huayi Jin +6

As the input length of large language model (LLM) serving continues to grow, the KV cache has become a dominant bottleneck in AI infrastructure. It limits GPU memory capacity, serv…

cs.AI2026

EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments

Zhilin Wang, Han Song, Runzhe Zhan +13

Autonomous agents are increasingly expected to improve executable policies through feedback, yet existing evaluations often collapse this process into a final score or confound it…

cs.CV2026

Exploring the AI Obedience: Why is Generating a Pure Color Image Harder than CyberPunk?

Hongyu Li, Kuan Liu, Yuan Chen +6

Recent advances in generative AI have shown human-level performance in complex content creation. However, we identify a "Paradox of Simplicity": models that can render complex scen…

cs.LG2024

: Towards Building Reliable Language Models with Sparse Mixture-of-Experts

Guanjie Chen, Xinyu Zhao, Tianlong Chen +1

Mixture-of-Experts (MoE) has gained increasing popularity as a promising framework for scaling up large language models (LLMs). However, the reliability assessment of MoE lags behi…