PaperHub
影响力指数
89.88/100
前 0.6%
全站排名 #381
发表论文44 篇
平均评分4.9
年均产出14.7 篇/年

Muhan Zhang

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

large language models · graph neural network · link prediction · graph representation learning · relational machine learning

4.5
23

Meta Pruning via Graph Metanetworks : A Universal Meta Learning Framework for Network Pruning

ICLR 2026Rejected
三作
4.5
22

ProofRM: A Scalable Pipeline to Train a Generalized Math Proof Reward Model

ICLR 2026Rejected
通讯
4.0
15

Round-trip Reinforcement Learning: Self-Consistent Training for Better Chemical LLMs

ICLR 2026Rejected
通讯
4.0
20

Coevolutionary Continuous Discrete Diffusion: Make Your Diffusion Language Model a Latent Reasoner

ICLR 2026Rejected
4.0
14

VACT: A Video Automatic Causal Testing System and a Benchmark

ICLR 2026Rejected
通讯
3.5
7

Continual Learning via Continual Weighted Sparsity and Meta-Plasticity Scheduling

ICLR 2026Rejected
3.0
6

Expressive Graph Neural Networks via Equivariant Use of Noise

ICLR 2026Rejected
二作
3.0
18

The Road Less Traveled: Enhancing Exploration in LLMs via Sequential Sampling

ICLR 2026Rejected
二作
3.0
14

GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning

ICLR 2026Rejected
通讯
3.0
6

GL-Fusion: Rethinking the Combination of Graph Neural Network and Large Language model

ICLR 2026Rejected
通讯
3.0
21

GET: Rethinking Dynamic Graph Learning as Global Event Sequence Generation

ICLR 2026Rejected
通讯
2.5
15

Multi-Agent Evolve: LLM Self-Improve through Multi-Agent Co-evolution

ICLR 2026Rejected
2.5
12

LIFT: Enhancing Long-Context Reasoning in Large Language Models via Long Input Fine-Tuning

ICLR 2026Rejected
通讯
2.0
6

GREPO: A Benchmark for Graph Neural Networks on Repository-Level Bug Localization

ICLR 2026Withdrawn
通讯
7.2
14

Geometric Representation Condition Improves Equivariant Molecule Generation

ICML 2025Spotlight
通讯
7.1
32

Beyond Single-Task: Robust Multi-Task Length Generalization for LLMs

NeurIPS 2025Poster
通讯
6.8
28

LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades

NeurIPS 2025Poster
三作
6.8
31

TransMLA: Migrating GQA Models to MLA with Full DeepSeek Compatibility and Speedup

NeurIPS 2025Spotlight
通讯
6.5
27

Number Cookbook: Number Understanding of Language Models and How to Improve It

ICLR 2025Poster
通讯
6.5
31

GOFA: A Generative One-For-All Model for Joint Graph Language Modeling

ICLR 2025Poster
通讯
6.0
22

On the Completeness of Invariant Geometric Deep Learning Models

ICLR 2025Poster
通讯
6.0
25

OCN: Effectively Utilizing Higher-Order Common Neighbors for Better Link Prediction

NeurIPS 2025Poster
三作
5.5
17

Towards Stable, Globally Expressive Graph Representations with Laplacian Eigenvectors

ICLR 2025Rejected
通讯
5.5
15

Griffin: Towards a Graph-Centric Relational Database Foundation Model

ICML 2025Poster
通讯
5.4
18

Geometric Representation Condition Improves Equivariant Molecule Generation

ICLR 2025Rejected
通讯
5.3
28

GL-Fusion: Rethinking the Combination of Graph Neural Network and Large Language model

ICLR 2025Rejected
通讯
5.0
25

Efficient Neural Common Neighbor for Temporal Graph Link Prediction

ICLR 2025Rejected
通讯
4.4
11

CLOVER: Cross-Layer Orthogonal Vectors Pruning

ICML 2025Poster
通讯
4.3
6

Continual Learning via Continual Weighted Sparsity and Meta-Plasticity Scheduling

ICLR 2025Rejected
三作
合作者 (20)