Yong Liu
~Yong_Liu7
30
论文总数
15.0
年均投稿
平均评分
接收情况12/30
会议分布
ICLR
22
NeurIPS
6
ICML
2
发表论文 (30 篇)
202523 篇
4
Mastering Syntax, Unlocking Semantics: A Mathematically Provable Two-stage Learning Process in Transformers
ICLR 2025withdrawn
3
Efficient Newton-type Federated Learning with Non-IID Data
ICLR 2025withdrawn
4
Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck Perspective
ICLR 2025Poster
5
Can Mamba Always Enjoy the "Free Lunch"?
ICLR 2025Rejected
4
Stability and Sharper Risk Bounds with Convergence Rate $O(1/n^2)$
ICLR 2025Rejected
4
ADePT: Adaptive Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning
ICLR 2025Poster
6
Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct Reasoning
ICML 2025Poster
5
Sharper Bounds of Non-Convex Stochastic Gradient Descent with Momentum
ICLR 2025Rejected
3
How Much Can RAG Help the Reasoning of LLM?
ICLR 2025Rejected
4
Improved Risk Bounds with Unbounded Losses for Transductive Learning
ICLR 2025Rejected
5
Clip Body and Tail Separately: High Probability Guarantees for DP-SGD with Heavy Tails
ICLR 2025withdrawn
4
DEAN: Deactivating the Coupled Neurons to Mitigate Fairness-Privacy Conflicts in Large Language Models
ICLR 2025withdrawn
4
Stability and Sharper Risk Bounds with Convergence Rate $\tilde{O}(1/n^2)$
NeurIPS 2025Poster
4
Understanding Model Ensemble in Transferable Adversarial Attack
ICLR 2025Rejected
4
Understanding Model Ensemble in Transferable Adversarial Attack
ICML 2025Poster
5
Towards Auto-Regressive Next-Token Prediction: In-context Learning Emerges from Generalization
ICLR 2025Poster
4
REEF: Representation Encoding Fingerprints for Large Language Models
ICLR 2025Oral
4
Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
NeurIPS 2025Poster
4
SSTAG: Structure-Aware Self-Supervised Learning Method for Text-Attributed Graphs
NeurIPS 2025Poster
4
Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization
ICLR 2025Rejected
4
Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization
ICLR 2025Poster
4
DMQR-RAG: Diverse Multi-Query Rewriting in Retrieval-Augmented Generation
ICLR 2025withdrawn
4
Recipes for Unbiased Reward Modeling Learning: An Empirically Study
ICLR 2025withdrawn
20247 篇
5
Perfect Alignment May be Poisonous to Graph Contrastive Learning
ICLR 2024Rejected
4
Towards Understanding How Transformers Learn In-context Through a Representation Learning Lens
NeurIPS 2024Poster
4
Algorithmic Stability Unleashed: Generalization Bounds with Unbounded Losses
ICLR 2024Rejected
4
Uniform Localized Convergence and Sharper Generalization Bounds for Minimax Problems
ICLR 2024Rejected
4
Stability and Sharper Risk Bounds with Convergence Rate $O(1/n^2)$
NeurIPS 2024Rejected
4
Enhancing In-Context Learning Performance with just SVD-Based Weight Pruning: A Theoretical Perspective
NeurIPS 2024Poster
4
AdaO2B: Adaptive Online to Batch Conversion for Out-of-Distribution Generalization
ICLR 2024withdrawn