Han Qiu
33 papers · 2020–2026 · 11 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+12 more ↓ Show less ↑
๐ Conference Polyglot (10) ๐ Academic Marathon (5) ๐ Interdisciplinary Bridge ๐งญ Keyword Pioneer ๐ Cross-Pollinator (10)
๐บ๏ธ
Taxonomy Completionist
(43)
๐
Conference Polyglot
(10)
๐
Academic Marathon
(5)
๐ค
Dynamic Duo
(20)
๐
Triple Crown
๐
Grand Slam
๐งฌ
Topic Evolution
๐
Trend Setter
โก
Prolific Year
(8)
๐
Century Club
(28)
๐๏ธ
Keyword Collector
(105)
๐ฅ
Unstoppable
(6)
Conferences
ACL (7)
EMNLP (5)
ICCV (5)
ICLR (5)
ECCV (3)
CVPR (2)
ICML (2)
AAAI (1)
COLING (1)
IJCAI (1)
NIPS (1)
Top co-authors
Research topics
Keywords
large language model
(7)
safety alignment
(2)
adversarial attack
(2)
multimodal large language model
(2)
remote sensing
(2)
prompt engineering
(2)
satellite imagery
(2)
jailbreak attack
(2)
attack success rate
(2)
supervised fine-tuning
(2)
data augmentation
(2)
data poisoning
(1)
in-context learning
(1)
preference optimization
(1)
neural network security
(1)
vision transformer
(1)
preference learning
(1)
depth estimation
(1)
model robustness
(1)
model security
(1)
Papers
When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMsโ Toxicity
AAAI 2026
New Terms, New Toxicity: Consensus-based Chinese Neologism Toxicity Detection via Search-Augmented LLMs
ACL 2026
Revisiting the Reliability of Language Models in Instruction-Following
ACL 2026
LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
ACL 2026
The Side Effects of Being Smart: Safety Risks in MLLMsโ Multi-Image Reasoning
ACL 2026
Understanding the Dark Side of LLMsโ Intrinsic Self-Correction
ACL 2025
An Engorgio Prompt Makes Large Language Model Babble on
ICLR 2025
When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models
EMNLP 2025
โIโve Decided to Leakโ: Probing Internals Behind Prompt Leakage Intents
EMNLP 2025
Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings
ACL 2025
Speculating LLMsโ Chinese Training Data Pollution from Their Tokens
EMNLP 2025
Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems
ICML 2025
VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking
ICLR 2025
Spatial Preference Rewarding for MLLMs Spatial Understanding
ICCV 2025
VISO: Accelerating In-orbit Object Detection with Language-Guided Mask Learning and Sparse Inference
ICCV 2025
A Benchmark for Semantic Sensitive Information in LLMs Outputs
ICLR 2025
COSMIC: Compress Satellite Image Efficiently via Diffusion Compensation
NIPS 2024
The Earth is Flat because...: Investigating LLMsโ Belief towards Misinformation via Persuasive Conversation
ACL 2024
Masked AutoDecoder is Effective Multi-Task Vision Generalist
CVPR 2024
"SPHINX: A Mixer of Weights, Visual Embeddings and Image Scales for Multi-modal Large Language Models"
ECCV 2024
Walking in Othersโ Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias
EMNLP 2024
Course-Correction: Safety Alignment Using Synthetic Preferences
EMNLP 2024
You Only Query Once: An Efficient Label-Only Membership Inference Attack
ICLR 2024
Purifying Quantization-conditioned Backdoors via Layer-wise Activation Correction with Distribution Approximation
ICML 2024
Extracting Robust Models with Uncertain Examples
ICLR 2023
MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection
ICCV 2023
Computation and Data Efficient Backdoor Attacks
ICCV 2023
One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training
ICCV 2023
Improving Adversarial Robustness of 3D Point Cloud Classification Models
ECCV 2022
An MRC Framework for Semantic Role Labeling
COLING 2022
Privacy-Preserving Collaborative Learning With Automatic Transformation Search
CVPR 2021
Fine-tuning Is Not Enough: A Simple yet Effective Watermark Removal Attack for DNN Models
IJCAI 2021
BorderDet: Border Feature for Dense Object Detection
ECCV 2020