PaperHub

Yingbin Liang

~Yingbin_Liang1

29
论文总数
14.5
年均投稿
5.9
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

4.5
4

RLHF with Inconsistent Multi-Agent Feedback Under General Function Approximation: A Theoretical Perspective

ICLR 2025Rejected
7.8
5

Discrete Diffusion Models: Novel Analysis and New Sampler Guarantees

NeurIPS 2025Poster
5.5
4

How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit Bias

ICML 2025Poster
6.8
5

Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent

NeurIPS 2025Poster
6.0
3

Broadening Target Distributions for Accelerated Diffusion Models via a Novel Analysis Approach

ICLR 2025Poster
6.4
5

Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers

ICLR 2025Poster
5.3
4

DUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity

ICLR 2025Poster
6.3
4

A Theoretical Analysis of Self-Supervised Learning for Vision Transformers

ICLR 2025Poster
6.5
4

Transformers Provably Learn Two-Mixture of Linear Classification via Gradient Flow

ICLR 2025Poster
7.3
3

Theory on Mixture-of-Experts in Continual Learning

ICLR 2025Spotlight
5.0
4

Meta ControlNet: Enhancing Task Adaptation via Meta Learning

ICLR 2025withdrawn
4.0
4

Replay concurrently or sequentially? A theoretical perspective on replay in continual learning

ICLR 2025withdrawn
5.5
4

Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective

ICML 2025Poster
5.5
4

Model Developmental Safety: A Safety-Centric Method and Applications in Vision-Language Models

ICLR 2025Rejected
7.3
4

Absorb and Converge: Provable Convergence Guarantee for Absorbing Discrete Diffusion Models

NeurIPS 2025Poster
6.0
3

Dynamic Loss-Based Sample Reweighting for Improved Large Language Model Pretraining

ICLR 2025Poster

202413