Zhouchen Lin
~Zhouchen_Lin1
35
论文总数
17.5
年均投稿
平均评分
接收情况22/35
会议分布
ICLR
19
NeurIPS
11
ICML
5
发表论文 (35 篇)
202528 篇
4
Low-Dimension-to-High-Dimension Generalization and Its Implications for Length Generalization
ICLR 2025Rejected
4
EKAN: Equivariant Kolmogorov-Arnold Networks
ICLR 2025withdrawn
4
Explicit Discovery of Nonlinear Symmetries from Dynamic Data
ICML 2025Poster
4
On the $O(\frac{\sqrt{d}}{K^{1/4}})$ Convergence Rate of AdamW Measured by $\ell_1$ Norm
NeurIPS 2025Poster
4
Incorporating Arbitrary Matrix Group Equivariance into KANs
ICML 2025Poster
4
Low-Dimension-to-High-Dimension Generalization and Its Implications for Length Generalization
ICML 2025Poster
4
PseuZO: Pseudo-Zeroth-Order Algorithm for Training Deep Neural Networks
NeurIPS 2025Poster
4
Active Treatment Effect Estimation via Limited Samples
ICML 2025Poster
4
Affine Steerable Equivariant Layer for Canonicalization of Neural Networks
ICLR 2025Poster
4
PaZO: Preconditioned Accelerated Zeroth-Order Optimization for Fine-Tuning LLMs
NeurIPS 2025Poster
4
Number Cookbook: Number Understanding of Language Models and How to Improve It
ICLR 2025Poster
4
SEPARATE: A Simple Low-rank Projection for Gradient Compression in Modern Large-scale Model Training Process
ICLR 2025Poster
3
Finding Second-order Stationary Points for Generalized-Smooth Nonconvex Minimax Optimization via Gradient-based Algorithm
ICLR 2025Rejected
4
TC-MoE: Augmenting Mixture of Experts with Ternary Expert Choice
ICLR 2025Poster
4
Stepsize anything: A unified learning rate schedule for budgeted-iteration training
NeurIPS 2025Poster
4
Provable Faster Zeroth-order Method for Bilevel Optimization with Optimal Dependency on Error and Dimension
ICLR 2025Rejected
4
Variance-Reduced Normalized Zeroth Order Method for Generalized-Smooth Non-Convex Optimization
ICLR 2025Rejected
4
GL-Fusion: Rethinking the Combination of Graph Neural Network and Large Language model
ICLR 2025Rejected
4
Tool Decoding: A Plug-and-Play Approach to Enhancing Language Models for Tool Usage
ICLR 2025withdrawn
4
AdaMSS: Adaptive Multi-Subspace Approach for Parameter-Efficient Fine-Tuning
NeurIPS 2025Poster
4
Projective Equivariant Networks via Second-order Fundamental Differential Invariants
NeurIPS 2025Spotlight
3
MLAE: Masked LoRA Experts for Visual Parameter-Efficient Fine-Tuning
ICLR 2025Rejected
4
Improving Model Representation and Reducing KV Cache via Skip Connections with First Value Heads
NeurIPS 2025Poster
4
Language Ranker: A Lightweight Ranking framework for LLM Decoding
NeurIPS 2025Poster
4
Inverse Methods for Missing Data Imputation
NeurIPS 2025Poster
4
Time-o1: Time-Series Forecasting Needs Transformed Label Alignment
NeurIPS 2025Poster
4
Unbiased Recommender Learning from Implicit Feedback via Weakly Supervised Learning
ICML 2025Poster
5
Pyramidal Flow Matching for Efficient Video Generative Modeling
ICLR 2025Poster
20247 篇
3
Explaining the Complex Task Reasoning of Large Language Models with Template-Content Structure
ICLR 2024Rejected
5
Transformer-Based Large Language Models Are Not General Learners: A Universal Circuit Perspective
ICLR 2024Rejected
4
EigenGuard: Backdoor Defense in Eigenspace
ICLR 2024Rejected
4
Separation and Bias of Deep Equilibrium Models on Expressivity and Learning Dynamics
NeurIPS 2024Poster
4
Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks
ICLR 2024Poster
3
Forward Gradient Training of Spiking Neural Networks
ICLR 2024Rejected
3
CORE: Common Random Reconstruction for Distributed Optimization with Provable Low Communication Complexity
ICLR 2024Rejected