Shengchao Liu
22 papers · 2018–2026 · 6 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 ↓+11 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (40) π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π
Grand Slam
π
Keyword Champion
(2)
π§
Keyword Pioneer
π
Triple Crown
π
Conference Pioneer
π₯
Unstoppable Β· Bronze
β
The Questioner
(2)
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
π
Renaissance Researcher
(6)
ποΈ
Keyword Collector
(96)
Top co-authors
Research topics
Machine Learning
(18)
Deep Learning
(10)
Learning Types Β· Machine Learning
(10)
Core Methods
(9)
Artificial Intelligence
(8)
Architectures
(6)
Core AI
(6)
Optimization & Theory
(4)
Techniques
(4)
Natural Language Processing
(3)
Application Areas
(3)
Learning Paradigms
(3)
Mathematics & Optimization
(2)
Applications
(2)
Learning Types Β· Deep Learning
(2)
Keywords
graph neural network
(6)
self-supervised learning
(5)
drug discovery
(3)
molecule representation
(3)
contrastive learning
(3)
geometric representation
(2)
negative transfer
(2)
out-of-distribution generalization
(2)
domain adaptation
(2)
transfer learning
(2)
representation learning
(2)
molecular geometry
(2)
graph representation
(2)
molecular graph
(2)
3d geometry
(2)
machine-generated text detection
(2)
domain generalization
(2)
chain-of-thought reasoning
(1)
multi-task learning
(1)
policy gradient
(1)
Papers
Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression
ACL 2026
MGT-Prism: Enhancing Domain Generalization for Machine-Generated Text Detection via Spectral Alignment
AAAI 2026
AssembleFlow: Rigid Flow Matching with Inertial Frames for Molecular Assembly
ICLR 2025
CARE: a Benchmark Suite for the Classification and Retrieval of Enzymes
NeurIPS 2024
Conversational Drug Editing Using Retrieval and Domain Feedback
ICLR 2024
Does DetectGPT Fully Utilize Perturbation? Bridging Selective Perturbation to Fine-tuned Contrastive Learning Detector would be Better
ACL 2024
Improving Domain Generalization with Domain Relations
ICLR 2024
A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretraining
ICML 2023
Evaluating Self-Supervised Learning for Molecular Graph Embeddings
NeurIPS 2023
Flaky Performances When Pretraining on Relational Databases (Student Abstract)
AAAI 2023
GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning
NeurIPS 2023
Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matching
ICLR 2023
Molecule Joint Auto-Encoding: Trajectory Pretraining with 2D and 3D Diffusion
NeurIPS 2023
Symmetry-Informed Geometric Representation for Molecules, Proteins, and Crystalline Materials
NeurIPS 2023
Pre-training Molecular Graph Representation with 3D Geometry
ICLR 2022
Structured Multi-task Learning for Molecular Property Prediction
AISTATS 2022
Neural Sentence Ordering Based on Constraint Graphs
AAAI 2021
Bad Global Minima Exist and SGD Can Reach Them
NeurIPS 2020
Learning to Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning
ICML 2020
Loss-Balanced Task Weighting to Reduce Negative Transfer in Multi-Task Learning
AAAI 2019
N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules
NeurIPS 2019
ATOMO: Communication-efficient Learning via Atomic Sparsification
NeurIPS 2018