Junkang Wu
12 papers · 2023–2026 · 7 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 ↓+4 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (25) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🏆 Grand Slam
⚡
Prolific Year · Productive
❓
The Questioner
💎
Century Club · Bronze
🗃️
Keyword Collector
(58)
Top co-authors
Research topics
Machine Learning
(10)
Artificial Intelligence
(9)
Core AI
(9)
Optimization & Theory
(8)
Learning Types · Machine Learning
(5)
Natural Language Processing
(4)
Resources & Methods
(4)
Deep Learning
(3)
Learning Types · Deep Learning
(3)
Application Areas
(2)
Reinforcement Learning
(1)
Core Methods
(1)
Methods
(1)
Keywords
direct preference optimization
(5)
reward margin
(3)
large language model
(3)
contrastive learning
(2)
preference learning
(2)
distributionally robust optimization
(2)
human preference
(2)
preference optimization
(1)
preference alignment
(1)
policy optimization
(1)
parameter optimization
(1)
label shift
(1)
preference modeling
(1)
noise robustness
(1)
structural causal model
(1)
mutual information
(1)
multimodal large language model
(1)
auction mechanism
(1)
spurious correlation
(1)
language model
(1)
Papers
Causal-HalBench: Uncovering LVLMs Object Hallucinations Through Causal Intervention
AAAI 2026
AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization
ICML 2025
DAMA: Data- and Model-aware Alignment of Multi-modal LLMs
ICML 2025
LaMP-Val: Large Language Models Empower Personalized Valuation in Auction
EMNLP 2025
Larger or Smaller Reward Margins to Select Preferences for LLM Alignment?
ICML 2025
MM-RLHF: The Next Step Forward in Multimodal LLM Alignment
ICML 2025
Robust Preference Optimization via Dynamic Target Margins
ACL 2025
Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization
ICLR 2025
β-DPO: Direct Preference Optimization with Dynamic β
NeurIPS 2024
Direct Multi-Turn Preference Optimization for Language Agents
EMNLP 2024
Discriminative-Invariant Representation Learning for Unbiased Recommendation
IJCAI 2023
Understanding Contrastive Learning via Distributionally Robust Optimization
NeurIPS 2023