PPaperPicks

Jing Li

Harbin Institute of Technology Shenzhen (HITSZ), Shenzhen, China

22 papers at tracked venues · 21 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation
  2. LLM Inductive Reasoning Through Multi-Agent Enhanced Monte Carlo Tree Search
  3. Skill Weaving: Efficient LLM Improvement via Modular Skillpacks
  4. Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queries
  5. Adaptive Detoxification: Safeguarding General Capabilities of LLMs through Toxicity-Aware Knowledge Editing
  6. Function-to-Style Guidance of LLMs for Code Translation
  7. Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question Answering
  8. LLMs Can Also Do Well! Breaking Barriers in Semantic Role Labeling via Large Language Models
  9. Learning to Watermark: A Selective Watermarking Framework for Large Language Models via Multi-Objective Optimization
  10. MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming
  11. Multi-Modality Expansion and Retention for LLMs through Parameter Merging and Decoupling
  12. NeurIPT: Foundation Model for Neural Interfaces
  13. Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer
  14. ProjectEval: A Benchmark for Programming Agents Automated Evaluation on Project-Level Code Generation
  15. Reflection on Knowledge Graph for Large Language Models Reasoning
  16. Safety Alignment via Constrained Knowledge Unlearning
  17. Speed Up Your Code: Progressive Code Acceleration Through Bidirectional Tree Editing
  18. To See a World in a Spark of Neuron: Disentangling Multi-Task Interference for Training-Free Model Merging
  19. Knowledge Fusion By Evolving Weights of Language Models
  20. Masked Structural Growth for 2x Faster Language Model Pre-training
  21. Multimodal Reasoning with Multimodal Knowledge Graph
  22. Parameter Competition Balancing for Model Merging