← authors · overview

• Scaling Generative Recommendations with Context Parallelism on Hierarchical Sequential Transducers
  2025 · 1 citations
• RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources
  2026
• AttenMIA: LLM Membership Inference Attack through Attention Signals
  2026
• MACE: A Hybrid LLM Serving System with Colocated SLO-aware Continuous Retraining Alignment
  2025
• What Do They Fix? LLM-Aided Categorization of Security Patches for Critical Memory Bugs
  2025
• MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details
  2025
• Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment
  2025
• MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask
  2020
• PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
  2024