Shengjie Luo
14 papers · 2021–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
🌍 Conference Polyglot (5) 🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🐝 Cross-Pollinator (13)
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(13)
🏆
Keyword Champion
(3)
👑
Triple Crown
🤝
Dynamic Duo
(12)
💎
Century Club
(14)
⚡
Prolific Year
(6)
❓
The Questioner
🔥
Unstoppable
(5)
Conferences
NIPS (5)
ICLR (4)
ICML (3)
ACL (1)
AISTATS (1)
Top co-authors
Keywords
transformer architecture
(4)
relative positional encoding
(3)
attention mechanism
(2)
representation learning
(2)
graph neural network
(2)
graph classification
(1)
fourier transform
(1)
function approximation
(1)
universal approximation
(1)
language modeling
(1)
self-attention mechanism
(1)
state evolution
(1)
diffusion model
(1)
deep neural network
(1)
physical consistency
(1)
molecular property
(1)
data heterogeneity
(1)
heterogeneous datum
(1)
structure prediction
(1)
batch normalization
(1)
Papers
How Numerical Precision Affects Arithmetical Reasoning Capabilities of LLMs
ACL 2025
Let the Code LLM Edit Itself When You Edit the Code
ICLR 2025
GeoMFormer: A General Architecture for Geometric Molecular Representation Learning
ICML 2024
Physical Consistency Bridges Heterogeneous Data in Molecular Multi-Task Learning
NIPS 2024
Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation
ICML 2024
Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers
AISTATS 2024
Bridging Geometric States via Geometric Diffusion Bridge
NIPS 2024
Enabling Efficient Equivariant Operations in the Fourier Basis via Gaunt Tensor Products
ICLR 2024
One Transformer Can Understand Both 2D & 3D Molecular Data
ICLR 2023
Rethinking the Expressive Power of GNNs via Graph Biconnectivity
ICLR 2023
Your Transformer May Not be as Powerful as You Expect
NIPS 2022
Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding
NIPS 2021
GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training
ICML 2021
Do Transformers Really Perform Badly for Graph Representation?
NIPS 2021