PPaperPicks

Huanxuan Liao

9 papers at tracked venues · 9 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Harmonizing the Past, Present, and Future: A Null-Space Constrained Region-Specific Method for Continual Learning in LLMs
  2. Pushing the Limits of LLM Tool Calling via Experiential Knowledge Integration and Activation
  3. Shuttle Between Symbolic Instructions and Neural Parameters of Large Language Models
  4. SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning
    AAAI 2026 · Huanxuan Liao
  5. Spectral Disentanglement: Rank-Aware Task Adaptation for Rehearsal-free Continual Learning in LLMs
    ACL 2026 · Huanxuan Liao
  6. CITI: Enhancing Tool Utilizing Ability in Large Language Models Without Sacrificing General Performance
  7. Evaluating Personalized Tool-Augmented LLMs from the Perspectives of Personalization and Proactivity
  8. Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning Tasks
    AAAI 2025 · Huanxuan Liao
  9. From Instance Training to Instruction Learning: Task Adapters Generation from Instructions
    NeurIPS 2024 · Huanxuan Liao