Bochuan Cao
13 papers · 2022–2025 · 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 ↓+4 more ↓ Show less ↑
๐ Interdisciplinary Bridge ยท Bronze ๐บ๏ธ Taxonomy Completionist (29) ๐ Conference Polyglot ยท Silver ๐ฃ Hot Topic Early Bird ๐ค Dynamic Duo (10)
๐
Renaissance Researcher
(5)
โก
Prolific Year ยท Productive
๐
Century Club ยท Bronze
๐๏ธ
Keyword Collector
(66)
Top co-authors
Research topics
Artificial Intelligence
(11)
Core AI
(11)
Machine Learning
(7)
Deep Learning
(5)
Learning Types
(5)
Natural Language Processing
(4)
Application Areas
(3)
Models
(3)
Core Methods
(2)
Generation
(2)
Optimization & Theory
(2)
Resources & Methods
(2)
Computer Science
(1)
Computer Vision
(1)
Security & Privacy
(1)
Keywords
large language model
(7)
model alignment
(3)
ai safety
(3)
jailbreak attack
(2)
adversarial attack
(2)
hallucination mitigation
(2)
model security
(1)
image generation
(1)
continual learning
(1)
factual accuracy
(1)
text generation
(1)
preference optimization
(1)
convergence analysis
(1)
language model alignment
(1)
self-supervised learning
(1)
adversarial robustness
(1)
safety alignment
(1)
harmful content
(1)
ensemble learning
(1)
flow matching
(1)
Papers
AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion Models
ICML 2025
JoPA: Explaining Large Language Modelโs Generation via Joint Prompt Attribution
ACL 2025
Monitoring Decoding: Mitigating Hallucination via Evaluating the Factuality of Partial Response during Generation
ACL 2025
On the Convergence of Moral Self-Correction in Large Language Models
IJCNLP 2025
TruthFlow: Truthful LLM Generation via Representation Flow Correction
ICML 2025
WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response
NAACL 2025
Data Free Backdoor Attacks
NeurIPS 2024
Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM
ACL 2024
Jailbreak Open-Sourced Large Language Models via Enforced Decoding
ACL 2024
Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
NeurIPS 2024
Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections
NAACL 2024
IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI
NeurIPS 2023
Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time
NeurIPS 2022