PPaperPicks

Ermo Hua

11 papers at tracked venues · 10 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism
  2. Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization
    ICML 2025 · Ermo Hua
  3. How to Synthesize Text Data without Model Collapse?
  4. Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process
    ACL 2025 · Ermo Hua
  5. MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding
  6. OpenPRM: Building Open-domain Process-based Reward Models with Preference Trees
  7. Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines
  8. TTRL: Test-Time Reinforcement Learning
  9. CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following
  10. Scalable Efficient Training of Large Language Models with Low-dimensional Projected Attention
  11. UltraMedical: Building Specialized Generalists in Biomedicine