PPaperPicks

Shizhu He

25 papers at tracked venues · 16 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. GATE: Graph-based Adaptive Tool Evolution Across Diverse Tasks
  2. Harmonizing the Past, Present, and Future: A Null-Space Constrained Region-Specific Method for Continual Learning in LLMs
  3. Progressive Re-ranking for Multimodal Retrieval-Augmented Generation via Curriculum Learning
  4. Seeing Is Believing: Grounding Long-Video Understanding in Spatio-Temporal Visual Evidence
  5. Shuttle Between Symbolic Instructions and Neural Parameters of Large Language Models
  6. SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning
  7. Spectral Disentanglement: Rank-Aware Task Adaptation for Rehearsal-free Continual Learning in LLMs
  8. TaREx: Reinforcement Learning for Code-Driven Table Reasoning
  9. HFF-Tracker: A Hierarchical Fine-grained Fusion Tracker for Referring Multi-Object Tracking
  10. KMatrix-2: A Comprehensive Heterogeneous Knowledge Collaborative Enhancement Toolkit for Large Language Model
  11. LLaSA: Large Language and Structured Data Assistant
  12. Multilingual Knowledge Graph Completion via Efficient Multilingual Knowledge Sharing
  13. Neural Incompatibility: The Unbridgeable Gap of Cross-Scale Parametric Knowledge Transfer in Large Language Models
  14. Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning Tasks
  15. Search-in-Context: Efficient Multi-Hop QA over Long Contexts via Monte Carlo Tree Search with Dynamic KV Retrieval
  16. Why and How LLMs Benefit from Knowledge Introspection in Commonsense Reasoning
  17. DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models
  18. Does Large Language Model Contain Task-Specific Neurons?
  19. From Instance Training to Instruction Learning: Task Adapters Generation from Instructions
  20. Generate-on-Graph: Treat LLM as both Agent and KG for Incomplete Knowledge Graph Question Answering
  21. Instance-Level Dynamic LoRAs Composition for Cross-Task Generalization
  22. ItD: Large Language Models Can Teach Themselves Induction through Deduction
  23. Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks
  24. S3Eval: A Synthetic, Scalable, Systematic Evaluation Suite for Large Language Model
  25. Teaching Small Language Models to Reason for Knowledge-Intensive Multi-Hop Question Answering