Yingbin Liang
~Yingbin_Liang1
29
论文总数
14.5
年均投稿
平均评分
接收情况19/29
会议分布
ICLR
21
NeurIPS
6
ICML
2
发表论文 (29 篇)
202516 篇
4
RLHF with Inconsistent Multi-Agent Feedback Under General Function Approximation: A Theoretical Perspective
ICLR 2025Rejected
5
Discrete Diffusion Models: Novel Analysis and New Sampler Guarantees
NeurIPS 2025Poster
4
How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit Bias
ICML 2025Poster
5
Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent
NeurIPS 2025Poster
3
Broadening Target Distributions for Accelerated Diffusion Models via a Novel Analysis Approach
ICLR 2025Poster
5
Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers
ICLR 2025Poster
4
DUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity
ICLR 2025Poster
4
A Theoretical Analysis of Self-Supervised Learning for Vision Transformers
ICLR 2025Poster
4
Transformers Provably Learn Two-Mixture of Linear Classification via Gradient Flow
ICLR 2025Poster
3
Theory on Mixture-of-Experts in Continual Learning
ICLR 2025Spotlight
4
Meta ControlNet: Enhancing Task Adaptation via Meta Learning
ICLR 2025withdrawn
4
Replay concurrently or sequentially? A theoretical perspective on replay in continual learning
ICLR 2025withdrawn
4
Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective
ICML 2025Poster
4
Model Developmental Safety: A Safety-Centric Method and Applications in Vision-Language Models
ICLR 2025Rejected
4
Absorb and Converge: Provable Convergence Guarantee for Absorbing Discrete Diffusion Models
NeurIPS 2025Poster
3
Dynamic Loss-Based Sample Reweighting for Improved Large Language Model Pretraining
ICLR 2025Poster
202413 篇
4
Theoretical Hardness and Tractability of POMDPs in RL with Partial Online State Information
ICLR 2024Rejected
4
Provably Efficient UCB-type Algorithms For Learning Predictive State Representations
ICLR 2024Poster
4
Non-asymptotic Convergence of Training Transformers for Next-token Prediction
NeurIPS 2024Poster
4
In-Context Learning with Representations: Contextual Generalization of Trained Transformers
NeurIPS 2024Poster
4
In-context Convergence of Transformers
ICLR 2024Rejected
4
On the Hardness of Online Nonconvex Optimization with Single Oracle Feedback
ICLR 2024Poster
4
Theoretical Analysis on the Generalization Power of Overfitted Transfer Learning
ICLR 2024Rejected
4
Understanding the Theoretical Generalization Performance of Federated Learning
ICLR 2024Rejected
3
Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis
NeurIPS 2024Poster
3
Doubly Robust Instance-Reweighted Adversarial Training
ICLR 2024Poster
4
Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games
ICLR 2024Rejected
5
Provable Benefits of Multi-task RL under Non-Markovian Decision Making Processes
ICLR 2024Poster
-
A UCB-type of Approach for Nonstationary MDPs with General Function Approximation
ICLR 2024withdrawn