Jiakai Wang
25 papers · 2020–2026 · 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 ↓+6 more ↓ Show less ↑
🗺️ Taxonomy Completionist (54) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird
🧬
Topic Evolution
🤝
Dynamic Duo
(18)
⚡
Prolific Year · Productive
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
🗃️
Keyword Collector
(133)
Top co-authors
Research topics
Artificial Intelligence
(17)
Machine Learning
(17)
Core AI
(17)
Deep Learning
(12)
Application Areas
(11)
Learning Types · Machine Learning
(9)
Learning Types · Deep Learning
(6)
Computer Vision
(5)
Natural Language Processing
(5)
Analysis
(5)
Models
(5)
Core Methods
(3)
Optimization & Theory · Deep Learning
(3)
Optimization & Theory · Machine Learning
(3)
Resources & Methods
(3)
Keywords
large language model
(6)
object detection
(3)
model compression
(3)
adversarial attack
(3)
model quantization
(3)
image generation
(2)
knowledge distillation
(2)
domain adaptation
(2)
continual pre-training
(2)
activation editing
(2)
efficient computing
(2)
weight binarization
(2)
diffusion model
(2)
gradient-based optimization
(1)
object recognition
(1)
adversarial robustness
(1)
computer vision
(1)
deepfake detection
(1)
adversarial learning
(1)
trajectory prediction
(1)
Papers
Activation Manipulation Attack: Penetrating and Harmful Jailbreak Attack Against Large Vision-Language Models
AAAI 2026
Adversarial Generation and Collaborative Evolution of Safety-Critical Scenarios for Autonomous Vehicles
AAAI 2026
AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions
CVPR 2026
Dormant Backdoor: Weaponizing Model Finetuning for Feasible Backdoor Attacks Against Pretrained Models
AAAI 2026
First-Order Error Matters: Accurate Compensation for Quantized Large Language Models
AAAI 2026
Query-Routed Activation Editing with Truth-hierarchical Preference Optimization
AAAI 2026
BinaryDM: Accurate Weight Binarization for Efficient Diffusion Models
ICLR 2025
Harnessing Global-Local Collaborative Adversarial Perturbation for Anti-Customization
CVPR 2025
Lexical Diversity-aware Relevance Assessment for Retrieval-Augmented Generation
ACL 2025
Token-Aware Editing of Internal Activations for Large Language Model Alignment
EMNLP 2025
Unlocking the Potential of Lightweight Quantized Models for Deepfake Detection
IJCAI 2025
BiDM: Pushing the Limit of Quantization for Diffusion Models
NeurIPS 2024
Byzantine Robust Cooperative Multi-Agent Reinforcement Learning as a Bayesian Game
ICLR 2024
D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models
NeurIPS 2024
DDK: Distilling Domain Knowledge for Efficient Large Language Models
NeurIPS 2024
E2-LLM: Efficient and Extreme Length Extension of Large Language Models
ACL 2024
NAPGuard: Towards Detecting Naturalistic Adversarial Patches
CVPR 2024
RoleAgent: Building, Interacting, and Benchmarking High-quality Role-Playing Agents from Scripts
NeurIPS 2024
Vision-fused Attack: Advancing Aggressive and Stealthy Adversarial Text against Neural Machine Translation
IJCAI 2024
Towards Benchmarking and Assessing Visual Naturalness of Physical World Adversarial Attacks
CVPR 2023
Defensive Patches for Robust Recognition in the Physical World
CVPR 2022
Adversarial Examples in Physical World
IJCAI 2021
Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical World
CVPR 2021
Towards Real-World X-Ray Security Inspection: A High-Quality Benchmark and Lateral Inhibition Module for Prohibited Items Detection
ICCV 2021
Bias-based Universal Adversarial Patch Attack for Automatic Check-out
ECCV 2020