PPaperPicks

Min Zhang

East China Normal University, Shanghai Institute of Al for Education, Shanghai, China

20 papers at tracked venues · 17 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Step-GRPO: Internalizing Dynamic Early Exit for Efficient Reasoning
  2. Tailoring Diagnostic Modeling to Individual Learners: Personalized Distractor Generation via MCTS-Guided Reasoning Reconstruction
  3. A Two-Stage Pretraining-Finetuning Framework for Treatment Effect Estimation with Unmeasured Confounding
  4. Advancing Personalized Learning with Neural Collapse for Long-Tail Challenge
  5. CALM: Consensus-Aware Localized Merging for Multi-Task Learning
  6. Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference
  7. ERICT: Enhancing Robustness by Identifying Concept Tokens in Zero-Shot Vision Language Models
  8. REMEDY: Recipe Merging Dynamics in Large Vision-Language Models
  9. Strong and Weak Identifiability of Optimization-based Causal Discovery in Non-linear Additive Noise Models
  10. VLAS: Vision-Language-Action Model with Speech Instructions for Customized Robot Manipulation
  11. Learning to Reweight for Generalizable Graph Neural Network
  12. MetaCoCo: A New Few-Shot Classification Benchmark with Spurious Correlation
    ICLR 2024 · Min Zhang
  13. Neural Collapse Anchored Prompt Tuning for Generalizable Vision-Language Models
  14. Neural Collapse Inspired Feature Alignment for Out-of-Distribution Generalization
  15. PiTe: Pixel-Temporal Alignment for Large Video-Language Model
  16. ProFD: Prompt-Guided Feature Disentangling for Occluded Person Re-Identification
  17. Prompt-Based Distribution Alignment for Unsupervised Domain Adaptation
  18. QUAR-VLA: Vision-Language-Action Model for Quadruped Robots
  19. Scaling Laws Across Model Architectures: A Comparative Analysis of Dense and MoE Models in Large Language Models
  20. Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning