← authors · overview

• Pruning Foundation Models For High Accuracy Without Retraining
  2024 · 22 citations
• LettinGo: Explore User Profile Generation for Recommendation System
  2025 · 11 citations
• Effective MoE-based LLM Compression by Exploiting Heterogeneous Inter-Group Experts Routing Frequency and Information Density
  2026
• TSLA: A Task-Specific Learning Adaptation for Semantic Segmentation on Autonomous Vehicles Platform
  2025
• Lean and Mean: Decoupled Value Policy Optimization with Global Value Guidance
  2025
• Reprompt: Reasoning-augmented Reprompting For Text-to-image Generation Via Reinforcement Learning
  2025
• Defensive Dropout for Hardening Deep Neural Networks under Adversarial Attacks
  2018
• Toward Adaptive Large Language Models Structured Pruning via Hybrid-grained Weight Importance Assessment
  2024
• Arena Learning: Build Data Flywheel for LLMs Post-training via Simulated Chatbot Arena
  2024
• Fully Open Source Moxin-7B Technical Report
  2024
• Fully Open Source Moxin-7B Technical Report
  2024