← authors · overview

• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
  2025 · 5456 citations
• Prompt Stealing Attacks Against Large Language Models
  2024 · 50 citations
• When Large Language Models Meet Citation: A Survey
  2023 · 15 citations
• SOS! Soft Prompt Attack Against Open-source Large Language Models
  2024 · 10 citations
• Mondrian: Prompt Abstraction Attack Against Large Language Models For Cheaper API Pricing
  2023 · 7 citations
• Steering LLM Thinking with Budget Guidance
  2025 · 1 citations
• SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation
  2025 · 1 citations
• Iclguard: Controlling In-context Learning Behavior For Applicability Authorization
  2024 · 1 citations
• Real-Time Personalization for LLM-based Recommendation with Customized In-Context Learning
  2024 · 1 citations
• Learning from the Future: Privileged Self-Distillation for Sequential Recommendation
  2026
• Metis: Memory Foundation Model
  2026
• IGD: Token Decisiveness Modeling via Information Gain in LLMs for Personalized Recommendation
  2025
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
  2025
• CommVQ: Commutative Vector Quantization for KV Cache Compression
  2025
• Large Language Models are Learnable Planners for Long-Term Recommendation
  2024