Junkang Wu
12 papers · 2023–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot (6) π Cross-Pollinator (11) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (21)
π§
Keyword Pioneer
π
Grand Slam
β‘
Prolific Year
(7)
β
The Questioner
π
Century Club
(11)
Conferences
ICML (4)
EMNLP (2)
NIPS (2)
AAAI (1)
ACL (1)
ICLR (1)
IJCAI (1)
Top co-authors
Keywords
large language model
(3)
direct preference optimization
(3)
contrastive learning
(2)
language model training
(1)
model alignment
(1)
mutual information
(1)
label shift
(1)
parameter optimization
(1)
distributionally robust optimization
(1)
preference modeling
(1)
noise robustness
(1)
language model
(1)
spurious correlation
(1)
auction mechanism
(1)
structural causal model
(1)
multi-turn dialogue
(1)
hallucination detection
(1)
selection bia
(1)
object hallucination
(1)
causal intervention
(1)
Papers
Causal-HalBench: Uncovering LVLMs Object Hallucinations Through Causal Intervention
AAAI 2026
Robust Preference Optimization via Dynamic Target Margins
ACL 2025
Larger or Smaller Reward Margins to Select Preferences for LLM Alignment?
ICML 2025
Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization
ICLR 2025
DAMA: Data- and Model-aware Alignment of Multi-modal LLMs
ICML 2025
AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization
ICML 2025
MM-RLHF: The Next Step Forward in Multimodal LLM Alignment
ICML 2025
LaMP-Val: Large Language Models Empower Personalized Valuation in Auction
EMNLP 2025
Direct Multi-Turn Preference Optimization for Language Agents
EMNLP 2024
$\beta$-DPO: Direct Preference Optimization with Dynamic $\beta$
NIPS 2024
Discriminative-Invariant Representation Learning for Unbiased Recommendation
IJCAI 2023
Understanding Contrastive Learning via Distributionally Robust Optimization
NIPS 2023