Haodong Zhao
11 papers · 2022–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Renaissance Researcher (6) πΊοΈ Taxonomy Completionist (29) π§ Keyword Pioneer π Interdisciplinary Bridge π Conference Polyglot (6)
π
Cross-Pollinator
(9)
ποΈ
Keyword Collector
(65)
π
Century Club
(10)
β
The Questioner
Conferences
ACL (5)
AAAI (2)
EMNLP (1)
ICCV (1)
ICML (1)
INTERSPEECH (1)
Top co-authors
Research topics
Keywords
pre-trained language model
(3)
trigger word
(2)
backdoor attack
(2)
contrastive learning
(2)
ownership verification
(2)
adversarial robustness
(1)
preference alignment
(1)
vision transformer
(1)
gradient-based optimization
(1)
transfer learning
(1)
adversarial learning
(1)
prompt engineering
(1)
semantic analysis
(1)
neural architecture search
(1)
speaker verification
(1)
policy optimization
(1)
speaker embedding
(1)
computational efficiency
(1)
weight sharing
(1)
supervised contrastive learning
(1)
Papers
Turning Failures into Value: Negative Experience Replay for RLVR via Confidence Gating and Boundary Failure Sampling
ACL 2026
AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models
ACL 2025
When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning
EMNLP 2025
Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models
ICML 2025
Revisiting the Information Capacity of Neural Network Watermarks: Upper Bound Estimation and Beyond
AAAI 2024
UOR: Universal Backdoor Attacks on Pre-trained Language Models
ACL 2024
ShiftNAS: Improving One-shot NAS via Probability Shift
ICCV 2023
PLMmark: A Secure and Robust Black-Box Watermarking Framework for Pre-trained Language Models
AAAI 2023
Is Continuous Prompt a Combination of Discrete Prompts? Towards a Novel View for Interpreting Continuous Prompts
ACL 2023
Infusing Hierarchical Guidance into Prompt Tuning: A Parameter-Efficient Framework for Multi-level Implicit Discourse Relation Recognition
ACL 2023
A Universal Identity Backdoor Attack against Speaker Verification based on Siamese Network
INTERSPEECH 2022