Zhenmei Shi
~Zhenmei_Shi1
15
论文总数
7.5
年均投稿
平均评分
接收情况7/15
会议分布
ICLR
10
NeurIPS
2
ICML
2
COLM
1
发表论文 (15 篇)
202512 篇
4
Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction
ICLR 2025Rejected
4
Tensor Attention Training: Provably Efficient Learning of Higher-order Transformers
ICLR 2025Rejected
4
Towards Infinite-Long Prefix in Transformer
ICLR 2025Rejected
4
Differential Privacy of Cross-Attention with Provable Guarantee
ICLR 2025Rejected
4
Kernel Regression in Structured Non-IID Settings: Theory and Implications for Denoising Score Learning
NeurIPS 2025Poster
3
Fine-grained Attention I/O Complexity: Comprehensive Analysis for Backward Passes
ICLR 2025Rejected
4
Beyond Linear Approximations: A Novel Pruning Approach for Attention Matrix
ICLR 2025Poster
4
Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time
ICLR 2025Rejected
3
Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers
ICLR 2025Rejected
4
HSR-Enhanced Sparse Attention Acceleration
ICLR 2025withdrawn
3
Fundamental Limits of Visual Autoregressive Transformers: Universal Approximation Abilities
ICML 2025Poster
3
Dissecting Submission Limit in Desk-Rejections: A Mathematical Analysis of Fairness in AI Conference Policies
ICML 2025Poster
20243 篇
4
Do Large Language Models Have Compositional Ability? An Investigation into Limitations and Scalability
COLM 2024Poster
4
Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning
ICLR 2024Poster
4
Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models
NeurIPS 2024Poster