Du Su
10 papers · 2024–2026 · 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 ↓+3 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (24) 🗃️ Keyword Collector (52)
💎
Century Club · Bronze
⚡
Prolific Year · Productive
🌈
Renaissance Researcher
(5)
Top co-authors
Research topics
Artificial Intelligence
(9)
Core AI
(8)
Deep Learning
(5)
Machine Learning
(5)
Learning Types · Machine Learning
(4)
Natural Language Processing
(2)
Applications · Natural Language Processing
(2)
Learning Types · Deep Learning
(2)
Models
(2)
Computer Science
(1)
Data Science & Analytics
(1)
Reinforcement Learning
(1)
Application Areas
(1)
Applications · Data Science & Analytics
(1)
Applications · Computer Science
(1)
Keywords
large language model
(5)
autoregressive transformer
(1)
multi-objective optimization
(1)
bayesian inference
(1)
text classification
(1)
mathematical reasoning
(1)
preference learning
(1)
chain-of-thought reasoning
(1)
confidence calibration
(1)
adversarial training
(1)
model editing
(1)
safety alignment
(1)
error detection
(1)
posterior probability
(1)
policy optimization
(1)
entropy regularization
(1)
text watermarking
(1)
perturbation robustness
(1)
parameter update
(1)
algorithmic fairness
(1)
Papers
AuditAgent: LLM Agent for Risks Auditing in Recommender Systems
AAAI 2026
BaseCal: Unsupervised Confidence Calibration via Base Model Signals
ACL 2026
Safety-Utility Conflicts Are Not Global: Surgical Alignment via Head-Level Diagnosis
ACL 2026
Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via sequence-level likelihood
ACL 2026
Indirect Online Preference Optimization via Reinforcement Learning
IJCAI 2025
Jailbreak LLMs through Internal Stance Manipulation
EMNLP 2025
Low-Entropy Watermark Detection via Bayes’ Rule Derived Detector
ACL 2025
PRDetect: Perturbation-Robust LLM-generated Text Detection Based on Syntax Tree
NAACL 2025
Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs
EMNLP 2025
The Fall of ROME: Understanding the Collapse of LLMs in Model Editing
EMNLP 2024