← authors · overview

• Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning
  2026
• When and Why Does Multi-Agent Debate Fail and Does It Really Underperform?
  2025
• Towards Scalable Oversight with Collaborative Multi-Agent Debate in Error Detection
  2025
• Direction Matters: On Influence-Preserving Graph Summarization and Max-cut Principle for Directed Graphs
  2019
• Scalable Evaluation and Improvement of Document Set Expansion via Neural Positive-Unlabeled Learning
  2019
• Learning Diverse-Structured Networks for Adversarial Robustness
  2021
• Towards Effective Visual Representations for Partial-Label Learning
  2023
• Distribution Shift Matters for Knowledge Distillation with Webly Collected Images
  2023
• Atom-Motif Contrastive Transformer for Molecular Property Prediction
  2023
• Direct Distillation between Different Domains
  2024