← authors · overview

• Don't Waste It: Guiding Generative Recommenders with Structured Human Priors via Multi-Head Decoding
  2025 · 4 citations
• Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
  2026 · 3 citations
• Story-Iter: A Training-free Iterative Paradigm for Long Story Visualization
  2024 · 3 citations
• Variance-Aware Baselines and Adaptive Learning Rates for Reinforcement Learning with Verifiable Rewards
  2025
• EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents
  2026
• SimpleMem: Efficient Lifelong Memory for LLM Agents
  2026
• OBLR-PO: A Theoretical Framework for Stable Reinforcement Learning
  2025
• Insight Miner: A Time Series Analysis Dataset for Cross-Domain Alignment with Natural Language
  2025
• A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Models
  2025
• IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis
  2025
• Grasp: Gradient-based Affordance Selection For Planning
  2022
• Understanding the performance gap between online and offline alignment algorithms
  2024