Publications

4 results for Meng Wang

Visual Prompting Reimagined: The Power of Activation Prompts
- - Yihua Zhang
  - Hongkang Li
  - et al.
- 2026
- AISTATS 2026
Conference paper
Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis
- - Hongkang Li
  - Songtao Lu
  - et al.
- 2025
- ICLR 2025
Conference paper
When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers
- - Hongkang Li
  - Yihua Zhang
  - et al.
- 2025
- ICLR 2025
Conference paper
A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts
- - Mohammed Nowaz Rabbani Chowdhury
  - Meng Wang
  - et al.
- 2024
- ICML 2024
Conference paper