PaperHub
影响力指数
92.33/100
前 0.4%
全站排名 #268
发表论文30 篇
平均评分5.8
年均产出10.0 篇/年

Ying Wei

Assistant Professor@Zhejiang University·中国·OpenReview
研究方向

Transfer Learning · Domain Adaptation · Meta-learning · Multitask Learning · Automatic Machine Learning · Sentiment Classification

6.0
14

EchoBench: Benchmarking Sycophancy in Medical Large Vision-Language Models

ICLR 2026Rejected
5.5
32

Scaling Reasoning Hop Exposes Weaknesses: Demystifying and Improving Hop Generalization in Large Language Models

ICLR 2026Poster
通讯
5.3
25

Plug-and-Play Compositionality for Boosting Continual Learning with Foundation Models

ICLR 2026Oral
通讯
4.5
6

Concept-Guided Tokenization: Closing the Gap Between Reconstruction and Generation

ICLR 2026Rejected
通讯
3.5
16

One-Token Verification for Reasoning LLMs, Anytime, Anywhere

ICLR 2026Rejected
3.2
6

Useless, or Untapped? Unlocking the Full Value of Zero-Advantage Samples for Better Policy Optimization

ICLR 2026Withdrawn
通讯
3.0
6

Stability Matters: Combating Parameter Shifts in Low-Rank Adaptation for Continual Learning

ICLR 2026Rejected
三作
9.0
28

Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning

ICLR 2025Oral
通讯
7.5
18

SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning

ICLR 2025Oral
通讯
6.5
34

CREAM: Consistency Regularized Self-Rewarding Language Models

ICLR 2025Poster
6.5
33

Anyprefer: An Agentic Framework for Preference Data Synthesis

ICLR 2025Poster
6.4
22

Data Selection Matters: Towards Robust Instruction Tuning of Large Multimodal Models

NeurIPS 2025Poster
三作
6.4
23

Curriculum Model Merging: Harmonizing Chemical LLMs for Enhanced Cross-Task Generalization

NeurIPS 2025Poster
三作
6.4
25

A$^3$E: Towards Compositional Model Editing

NeurIPS 2025Poster
通讯
6.0
84

Reaction Graph: Toward Modeling Chemical Reactions with 3D Molecular Structures

ICLR 2025Rejected
三作
5.7
51

CLDyB: Towards Dynamic Benchmarking for Continual Learning with Pre-trained Models

ICLR 2025Poster
通讯
5.5
15

Reaction Graph: Towards Reaction-Level Modeling for Chemical Reactions with 3D Structures

ICML 2025Poster
三作
5.5
13

Come Together, But Not Right Now: A Progressive Strategy to Boost Low-Rank Adaptation

ICML 2025Poster
通讯
4.6
6

Fading Focus: Mitigating Visual Attention Degradation in Large Vision-Language Models

ICLR 2025Withdrawn
3.7
10

How Well Can LLMs Synthesize Molecules? An LLM-Powered Framework for Multi-Step Retrosynthesis

ICLR 2025Withdrawn
通讯
合作者 (20)