Xujie Si
17 papers · 2018–2026 · 8 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 ↓+8 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (40) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π§¬
Topic Evolution
π
Keyword Champion
π
Trend Setter
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
π
Renaissance Researcher
(5)
β
The Questioner
ποΈ
Keyword Collector
(97)
Top co-authors
Research topics
Artificial Intelligence
(13)
Machine Learning
(12)
Core AI
(10)
Optimization & Theory
(7)
Deep Learning
(5)
Core Methods
(5)
Learning Types Β· Machine Learning
(5)
Natural Language Processing
(4)
Resources & Methods
(4)
Mathematics & Optimization
(3)
Architectures
(3)
Optimization
(3)
Knowledge & Reasoning
(2)
Learning Paradigms
(2)
Learning Types Β· Deep Learning
(2)
Keywords
graph neural network
(3)
large language model
(3)
program synthesis
(3)
logical reasoning
(2)
reinforcement learning
(2)
neuro-symbolic ai
(2)
neural network verification
(2)
visual reasoning
(2)
differentiable maxsat solver
(2)
logical rule learning
(2)
belief propagation
(1)
mathematical reasoning
(1)
self-supervised learning
(1)
in-context learning
(1)
sequential decision making
(1)
decision making
(1)
adversarial robustness
(1)
visual question answering
(1)
evaluation methodology
(1)
transfer learning
(1)
Papers
Is This LLM Library Learning? Evaluation Must Account For Compute and Behaviour
EACL 2026
APPL: A Prompt Programming Language for Harmonious Integration of Programs and Large Language Model Prompts
ACL 2025
Decoupling Training-Free Guided Diffusion by ADMM
CVPR 2025
Proving Olympiad Inequalities by Synergizing LLMs and Symbolic Reasoning
ICLR 2025
TypyBench: Evaluating LLM Type Inference for Untyped Python Repositories
ICML 2025
Autoformalizing Euclidean Geometry
ICML 2024
Code Repair with LLMs gives an Exploration-Exploitation Tradeoff
NeurIPS 2024
LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulation
NeurIPS 2024
Towards Robust Saliency Maps
ACML 2024
Learning Reliable Logical Rules with SATNet
NeurIPS 2023
Towards Reliable Neural Specifications
ICML 2023
NSNet: A General Neural Probabilistic Framework for Satisfiability Problems
NeurIPS 2022
Scallop: From Probabilistic Deductive Databases to Scalable Differentiable Reasoning
NeurIPS 2021
Techniques for Symbol Grounding with SATNet
NeurIPS 2021
Learning a Meta-Solver for Syntax-Guided Program Synthesis
ICLR 2019
Synthesizing Datalog Programs using Numerical Relaxation
IJCAI 2019
Learning Loop Invariants for Program Verification
NeurIPS 2018