Xinyu Xing
13 papers · 2018–2025 · 4 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 ↓+5 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (34) π Conference Polyglot Β· Bronze π Academic Marathon Β· Sprint π£ Hot Topic Early Bird π Interdisciplinary Bridge Β· Bronze
π§¬
Topic Evolution
π§
Keyword Pioneer
β‘
Prolific Year Β· Productive
ποΈ
Keyword Collector
(70)
π
Century Club Β· Bronze
Venues
Top co-authors
Research topics
Artificial Intelligence
(9)
Core AI
(9)
Machine Learning
(7)
Deep Learning
(5)
Learning Types
(5)
Reinforcement Learning
(4)
Natural Language Processing
(3)
Applications Β· Natural Language Processing
(3)
Methods
(3)
Optimization & Theory
(3)
Application Areas
(2)
Generation
(2)
Models
(2)
Applications Β· Reinforcement Learning
(1)
Architectures
(1)
Keywords
deep reinforcement learning
(5)
reinforcement learning
(3)
adversarial learning
(2)
text generation
(2)
competitive game
(2)
adversarial attack
(2)
policy explanation
(2)
variational inference
(1)
conditional generation
(1)
policy optimization
(1)
natural language generation
(1)
saliency map
(1)
adversarial training
(1)
question generation
(1)
policy gradient
(1)
gaussian process
(1)
empirical risk minimization
(1)
text classification
(1)
model interpretability
(1)
feature attribution
(1)
Papers
UTF: Under-trained Tokens as Fingerprints ββ a Novel Approach to LLM Identification
ACL 2025
RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation
ICML 2024
Soft-Label Integration for Robust Toxicity Classification
NeurIPS 2024
StateMask: Explaining Deep Reinforcement Learning through State Mask
NeurIPS 2023
Adversarial Policy Learning in Two-player Competitive Games
ICML 2021
BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning
IJCAI 2021
DANCE: Enhancing saliency maps using decoys
ICML 2021
EDGE: Explaining Deep Reinforcement Learning Policies
NeurIPS 2021
RNNRepair: Automatic RNN Repair via Model-based Analysis
ICML 2021
Structure-Aware Pre-Training for Table-to-Text Generation
ACL 2021
Automatic Generation of Citation Texts in Scholarly Papers: A Pilot Study
ACL 2020
Asking the Crowd: Question Analysis, Evaluation and Generation for Open Discussion on Online Forums
ACL 2019
Explaining Deep Learning Models -- A Bayesian Non-parametric Approach
NeurIPS 2018