collaborators

8 papers

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.AI2026

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

Yang Liu, ZhaoKai Luo, Zhaokai Luo +11

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.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.DC2026

Huawei Cloud Model-as-a-Service on the CloudMatrix384 SuperPod

Ao Xiao, Bangzheng He, Baoquan Zhang +125

Scaled-out MoE LLMs and scaled-up SuperPods create new systems challenges for production Model-as-a-Service (MaaS), requiring disaggregation, low-latency communication, and decentr…

cs.CV2026

Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints

Guanjie Chen, Xinyu Zhao, Yucheng Zhou +3

Diffusion Transformers (DiT) have emerged as a powerful architecture for image and video generation, offering superior quality and scalability. However, their practical application…

cs.CV2025

Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learning

Guanjie Chen, Shirui Huang, Kai Liu +5

Diffusion Models have emerged as a leading class of generative models, yet their iterative sampling process remains computationally expensive. Timestep distillation is a promising…