Shengjie Luo
14 papers · 2021–2025 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
π£ Hot Topic Early Bird π Interdisciplinary Bridge Β· Bronze π Conference Polyglot Β· Silver πΊοΈ Taxonomy Completionist (25) π€ Dynamic Duo (12)
π€
Dynamic Duo
(12)
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
β
The Questioner
ποΈ
Keyword Collector
(70)
π₯
Unstoppable Β· Bronze
Top co-authors
Research topics
Deep Learning
(12)
Machine Learning
(12)
Architectures
(10)
Core Methods
(8)
Optimization & Theory
(6)
Artificial Intelligence
(4)
Techniques
(3)
Natural Language Processing
(2)
Application Areas
(2)
Core AI
(2)
Learning Paradigms
(2)
Healthcare & Medicine
(1)
Generation
(1)
Learning Types Β· Machine Learning
(1)
Learning Types Β· Deep Learning
(1)
Keywords
transformer architecture
(5)
relative positional encoding
(3)
graph neural network
(3)
positional encoding
(3)
representation learning
(3)
attention mechanism
(2)
large language model
(2)
fourier transform
(2)
graph classification
(1)
code generation
(1)
function approximation
(1)
universal approximation
(1)
transformer
(1)
irreducible representations
(1)
multimodal learning
(1)
language modeling
(1)
self-attention mechanism
(1)
semantic information
(1)
diffusion model
(1)
state evolution
(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
Bridging Geometric States via Geometric Diffusion Bridge
NeurIPS 2024
Enabling Efficient Equivariant Operations in the Fourier Basis via Gaunt Tensor Products
ICLR 2024
GeoMFormer: A General Architecture for Geometric Molecular Representation Learning
ICML 2024
Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers
AISTATS 2024
Physical Consistency Bridges Heterogeneous Data in Molecular Multi-Task Learning
NeurIPS 2024
Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation
ICML 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
NeurIPS 2022
Do Transformers Really Perform Badly for Graph Representation?
NeurIPS 2021
GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training
ICML 2021
Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding
NeurIPS 2021