Jiaxin Ding
8 papers · 2020–2026 · 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 ↓+2 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (19) π£ Hot Topic Early Bird π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver
π
Renaissance Researcher
(7)
β
The Questioner
Top co-authors
Research topics
Artificial Intelligence
(5)
Core AI
(5)
Deep Learning
(4)
Reinforcement Learning
(4)
Methods
(4)
Machine Learning
(3)
Learning Types
(2)
Optimization & Theory
(2)
Interdisciplinary
(1)
Knowledge & Reasoning
(1)
Mathematics & Optimization
(1)
Natural Language Processing
(1)
Robotics
(1)
Architectures
(1)
Capabilities
(1)
Keywords
constraint satisfaction
(2)
policy optimization
(2)
constrained reinforcement learning
(2)
natural language generation
(1)
human judgment
(1)
persistent homology
(1)
interpretability
(1)
continuous control
(1)
policy update
(1)
bias correction
(1)
language model
(1)
reward maximization
(1)
constrained optimization
(1)
quantile optimization
(1)
budget-aware learning
(1)
evaluation metric
(1)
constrained policy optimization
(1)
constraint violation
(1)
reinforcement learning
(1)
representation learning
(1)
Papers
VisPCO: Visual Token Pruning Configuration Optimization via Budget-Aware Pareto-Frontier Learning for Vision-Language Models
ACL 2026
Controlling Underestimation Bias in Constrained Reinforcement Learning for Safe Exploration
ICML 2025
Extreme Value Policy Optimization for Safe Reinforcement Learning
ICML 2025
TopInG: Topologically Interpretable Graph Learning via Persistent Rationale Filtration
ICML 2025
Exterior Penalty Policy Optimization with Penalty Metric Network under Constraints
IJCAI 2024
Is Reference Necessary in the Evaluation of NLG Systems? When and Where?
NAACL 2024
RepEval: Effective Text Evaluation with LLM Representation
EMNLP 2024
IPO: Interior-Point Policy Optimization under Constraints
AAAI 2020