影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
72.6/100
前 2.2%
全站排名 #1,437
发表论文16 篇
平均评分
年均产出5.3 篇/年
Zengfeng Huang
研究方向
Differential Privacy · Online Learning · Representation Learning · Matrix computation · Graph algorithms · Streaming and Sketching
16
Sublinear Spectral Clustering Oracle with Little Memory
ICLR 2026Poster
通讯24
Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs
ICLR 2026Poster
32
Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache
ICLR 2026Rejected
23
EvolProver: Advancing Automated theorem proving by Evolving Formalized Problems via Symmetry and Difficulty
ICLR 2026Poster
10
Poivre: Self-Refining Visual Pointing with Reinforcement Learning
ICLR 2026Withdrawn
二作10
Overcoming Redundant Context in Auto-Regressive LLMs with Dynamic Draft Refinement
ICLR 2026Rejected
三作13
$S^3$-Bench: A Comprehensive Study of Multimodal LLMs for Scientific Discovery with Benchmarking
ICLR 2026Rejected
50
Geometric Imbalance in Semi-Supervised Node Classification
NeurIPS 2025Poster
通讯29
TGB-Seq Benchmark: Challenging Temporal GNNs with Complex Sequential Dynamics
ICLR 2025Poster
通讯22
MuseGNN: Forming Scalable, Convergent GNN Layers that Minimize a Sampling-Based Energy
ICLR 2025Poster
三作19
High Probability Bounds for Cross-Learning Contextual Bandits with Unknown Context Distributions
ICLR 2025Rejected
二作11
High Probability Bound for Cross-Learning Contextual Bandits with Unknown Context Distributions
ICML 2025Poster
二作15
Lipschitz Bandits in Optimal Space
ICLR 2025Poster
二作32
Know Your Neighbors: Subgraph Importance Sampling for Heterophilic Graph Active Learning
ICLR 2025Rejected
通讯