8 papers
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…
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…
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…
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…
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…
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…