Kai Hu
22 papers · 2020–2026 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+11 more ↓ Show less ↑
π Conference Polyglot (8) π Academic Marathon (5) π Interdisciplinary Bridge π§ Keyword Pioneer π Cross-Pollinator (11)
π
Cross-Pollinator
(11)
π
Renaissance Researcher
(8)
πΊοΈ
Taxonomy Completionist
(63)
π
Triple Crown
π
Grand Slam
π§¬
Topic Evolution
β
The Questioner
π
Century Club
(20)
ποΈ
Keyword Collector
(116)
β‘
Prolific Year
(7)
π₯
Unstoppable
(6)
Conferences
NIPS (6)
AAAI (4)
CVPR (4)
ACL (2)
ICLR (2)
ICML (2)
EMNLP (1)
ICCV (1)
Top co-authors
Keywords
semantic segmentation
(4)
contrastive learning
(3)
self-supervised learning
(3)
image generation
(2)
question answering
(2)
object detection
(2)
large language model
(2)
diffusion model
(2)
jailbreak attack
(2)
video understanding
(2)
knowledge distillation
(2)
style transfer
(1)
transformer architecture
(1)
action recognition
(1)
adversarial robustness
(1)
image classification
(1)
text-to-image synthesis
(1)
semi-supervised learning
(1)
data augmentation
(1)
attention mechanism
(1)
Papers
Jailbreak-Zero: A Path to Pareto Optimal Red Teaming for Large Language Models
ACL 2026
SSR-SAM: Retrieval-Style Segment Anything Model for Semi-Supervised Ultra-High-Resolution Image Segmentation
AAAI 2026
Self-supervised ControlNet with Spatio-Temporal Mamba for Real-world Video Super-resolution
CVPR 2025
M-LLM Based Video Frame Selection for Efficient Video Understanding
CVPR 2025
Learning Graph Invariance by Harnessing Spuriosity
ICLR 2025
Explicit Relational Reasoning Network for Scene Text Detection
AAAI 2025
Distilling Knowledge from Heterogeneous Architectures for Semantic Segmentation
AAAI 2025
MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space
ACL 2025
Empowering Graph Invariance Learning with Deep Spurious Infomax
ICML 2024
A Recipe for Improved Certifiable Robustness
ICLR 2024
One-to-Multiple: A Progressive Style Transfer Unsupervised Domain-Adaptive Framework for Kidney Tumor Segmentation
NIPS 2024
Multi-view Masked Contrastive Representation Learning for Endoscopic Video Analysis
NIPS 2024
Slight Corruption in Pre-training Data Makes Better Diffusion Models
NIPS 2024
Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization
NIPS 2024
Completing Visual Objects via Bridging Generation and Segmentation
ICML 2024
Enhanced Training of Query-Based Object Detection via Selective Query Recollection
CVPR 2023
Unlocking Deterministic Robustness Certification on ImageNet
NIPS 2023
A Question-Answering Approach to Key Value Pair Extraction from Form-Like Document Images
AAAI 2023
The VolcTrans System for WMT22 Multilingual Machine Translation Task
EMNLP 2022
Text to Image Generation With Semantic-Spatial Aware GAN
CVPR 2022
Contrast and Order Representations for Video Self-Supervised Learning
ICCV 2021
Is normalization indispensable for training deep neural network?
NIPS 2020