Qin Liu
28 papers · 2021–2026 · 9 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 ↓+10 more ↓ Show less ↑
🗺️ Taxonomy Completionist (52) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird
👥
Mega-Team · Squad
🧬
Topic Evolution
🤝
Dynamic Duo
(12)
🔬
Deep Specialist
(10)
⚡
Prolific Year · Productive
🔥
Unstoppable · Bronze
❓
The Questioner
💎
Century Club · Bronze
🌈
Renaissance Researcher
(5)
🗃️
Keyword Collector
(119)
Top co-authors
Research topics
Artificial Intelligence
(19)
Core AI
(18)
Deep Learning
(15)
Machine Learning
(15)
Learning Types · Machine Learning
(11)
Optimization & Theory · Machine Learning
(7)
Computer Vision
(6)
Learning Types · Deep Learning
(6)
Natural Language Processing
(5)
Models
(5)
Processing
(5)
Analysis
(4)
Applications
(4)
Generation
(3)
Optimization & Theory · Deep Learning
(3)
Keywords
large language model
(9)
adversarial attack
(4)
text classification
(3)
interactive segmentation
(3)
semantic segmentation
(3)
vision transformer
(3)
backdoor attack
(3)
model robustness
(2)
natural language processing
(2)
data poisoning
(2)
multi-turn conversation
(2)
product of expert
(2)
adversarial defense
(2)
adversarial training
(2)
reinforcement learning
(2)
language model
(2)
ensemble learning
(1)
adversarial robustness
(1)
domain adaptation
(1)
question answering
(1)
Papers
Boosting Adversarial Transferability via Ensemble Non-Attention
AAAI 2026
ESAM++: Efficient Online 3D Perception on the Edge
CVPR 2026
Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination
AAAI 2026
RedCoder: Automated Multi-Turn Red Teaming for Code LLMs
ACL 2026
Taming Extreme Tokens: Covariance-Aware GRPO with Gaussian-Kernel Advantage Reweighting
ACL 2026
Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation
EMNLP 2025
LiVOS: Light Video Object Segmentation with Gated Linear Matching
CVPR 2025
MetaScientist: A Human-AI Synergistic Framework for Automated Mechanical Metamaterial Design
NAACL 2025
MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding
ICLR 2025
Order-aware Interactive Segmentation
ICLR 2025
QA‐LIGN: Aligning LLMs through Constitutionally Decomposed QA
EMNLP 2025
SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment
ACL 2025
Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations
NAACL 2025
Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models
ACL 2025
ChatMusician: Understanding and Generating Music Intrinsically with LLM
ACL 2024
From Shortcuts to Triggers: Backdoor Defense with Denoised PoE
NAACL 2024
LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing
EMNLP 2024
Monotonic Paraphrasing Improves Generalization of Language Model Prompting
EMNLP 2024
Rethinking Interactive Image Segmentation with Low Latency High Quality and Diverse Prompts
CVPR 2024
Securing Multi-turn Conversational Language Models From Distributed Backdoor Attacks
EMNLP 2024
Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-Backdoors
NAACL 2024
Characterizing the Impacts of Instances on Robustness
ACL 2023
Detecting Adversarial Samples through Sharpness of Loss Landscape
ACL 2023
SimpleClick: Interactive Image Segmentation with Simple Vision Transformers
ICCV 2023
Flooding-X: Improving BERT’s Resistance to Adversarial Attacks via Loss-Restricted Fine-Tuning
ACL 2022
PlugAT: A Plug and Play Module to Defend against Textual Adversarial Attack
COLING 2022
PseudoClick: Interactive Image Segmentation with Click Imitation
ECCV 2022
TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing
ACL 2021