Papers

• Accelerating Disaggregated RL for Visual Generative LLMs with Diffusion-Based Parallelism and Trainer-Assisted Generation (2026)
  Sijie Wang et al.
  4.33
• Single-Connection Mixed-Criticality Transport with CATS: Bounded Guarantees, Three Structural Limits, and a QUIC Escape (2026)
  Syed Muhammad Aqdas Rizvi
  1.94
• The Serialized Bridge: Understanding and Recovering LLM Serving Performance under Blackwell GPU Confidential Computing (2026)
  Hang Yin et al.
  1.94