PPaperPicks

Li Du

28 papers at tracked venues · 24 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration
  2. Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation
  3. LLMs Know More About Numbers than They Can Say
  4. Large Language Models Are Still Misled by Simple Bias Ensembles
  5. MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization
  6. MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation
  7. Scaling Towards the Information Boundary of Instructions through Data Synthesizing
    AAAI 2026 · Li Du
  8. Analyzing the Rapid Generalization of SFT via the Perspective of Attention Head Activation Patterns
  9. Beyond IID: Optimizing Instruction Finetuning from the Perspective of Instruction Interaction and Dependency
  10. Beyond Similarity: A Gradient-based Graph Method for Instruction Tuning Data Selection
  11. Com² : A Causal-Guided Benchmark for Exploring Complex Commonsense Reasoning in Large Language Models
  12. FBQuant: FeedBack Quantization for Large Language Models
  13. PAT: Pruning-Aware Tuning for Large Language Models
  14. SliceOcc: Indoor 3D Semantic Occupancy Prediction with Vertical Slice Representation
  15. SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking
  16. Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMs
  17. Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo
  18. Tool Zero: Training Tool-Augmented LLMs via Pure RL from Scratch
  19. UFO-RL: Uncertainty-Focused Optimization for Efficient Reinforcement Learning Data Selection
  20. BiPFT: Binary Pre-trained Foundation Transformer with Low-Rank Estimation of Binarization Residual Polynomials
  21. Causal-Guided Active Learning for Debiasing Large Language Models
  22. Deciphering the Impact of Pretraining Data on Large Language Models through Machine Unlearning
  23. Medical Dialogue System: A Survey of Categories, Methods, Evaluation and Challenges
  24. Principled Gradient-Based MCMC for Conditional Sampling of Text
    ICML 2024 · Li Du
  25. PromptCoT: Align Prompt Distribution via Adapted Chain-of-Thought
  26. SFC: Achieve Accurate Fast Convolution under Low-precision Arithmetic
  27. VeCAF: Vision-language Collaborative Active Finetuning with Training Objective Awareness
  28. When is a Language Process a Language Model?
    ACL 2024 · Li Du