← Authors

Hai Li

43 papers · 2016–2026 · 12 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (11) πŸƒ Academic Marathon (9) 🐝 Cross-Pollinator (13) 🌈 Renaissance Researcher (10) πŸ—ΊοΈ Taxonomy Completionist (73) 🀝 Dynamic Duo (24) πŸ‘‘ Triple Crown πŸ† Keyword Champion 🧬 Topic Evolution πŸ† Grand Slam ❓ The Questioner πŸ—ƒοΈ Keyword Collector (179) πŸ’Ž Century Club (41) πŸ“ˆ Trend Setter πŸ”₯ Unstoppable (10) ⚑ Prolific Year (5) πŸš€ Conference Pioneer

Conferences

ICLR (6) NIPS (6) WACV (6) AAAI (5) CVPR (5) ICML (4) ICCV (3) INTERSPEECH (3) ECCV (2) ACL (1) AUTOML (1) EACL (1)

Top co-authors

Yiran Chen (24) Jingwei Sun (8) Wei Wen (7) Jingyang Zhang (6) Jianyi Zhang (6) Ang Li (5) Huanrui Yang (5) Feng Yan (5) Nathan Inkawhich (4) Minxue Tang (3)

Research topics

Privacy (1)

Keywords

federated learning (6) model compression (5) object detection (4) adversarial training (4) neural architecture search (4) adversarial defense (3) representation learning (3) model efficiency (2) vision transformer (2) adversarial learning (2) semantic segmentation (2) convolutional neural network (2) data heterogeneity (2) parameter reduction (2) self-supervised learning (2) neural network optimization (2) edge device (2) image generation (1) adversarial robustness (1) generative modeling (1)

Papers

FLAT-LLM: Fine-grained Low-rank Activation Space Transformation for Large Language Model Compression EACL 2026
Brains vs. Algorithms? How Experts and Students See AI-Generated Distractors AAAI 2026
PanoGS: Gaussian-based Panoptic Segmentation for 3D Open Vocabulary Scene Understanding CVPR 2025
Min-K%++: Improved Baseline for Pre-Training Data Detection from Large Language Models ICLR 2025
Proactive Privacy Amnesia for Large Language Models: Safeguarding PII with Negligible Impact on Model Utility ICLR 2025
Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing ICCV 2025
MLLM-LLaVA-FL: Multimodal Large Language Model Assisted Federated Learning WACV 2025
SADA: Stability-guided Adaptive Diffusion Acceleration ICML 2025
Tunable Hybrid Proposal Networks for the Open World WACV 2024
MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-Labeling CVPR 2024
FreeV: Free Lunch For Vocoders Through Pseudo Inversed Mel Filter INTERSPEECH 2024
PIDS: Joint Point Interaction-Dimension Search for 3D Point Cloud WACV 2023
FLSL: Feature-level Self-supervised Learning NIPS 2023
REMIT: Reinforced Multi-Interest Transfer for Cross-Domain Recommendation AAAI 2023
Enhanced Training Methods for Multiple Languages ACL 2023
Global Vision Transformer Pruning With Hessian-Aware Saliency CVPR 2023
Stable and Causal Inference for Discriminative Self-supervised Deep Visual Representations ICCV 2023
Disentangling Learning Representations with Density Estimation ICLR 2023
Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction ICML 2023
Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-Grained Environments WACV 2023
NashAE: Disentangling Representations through Adversarial Covariance Minimization ECCV 2022
The Untapped Potential of Off-the-Shelf Convolutional Neural Networks WACV 2022
FedCor: Correlation-Based Active Client Selection Strategy for Heterogeneous Federated Learning CVPR 2022
ScaleNAS: Multi-Path One-Shot NAS for Scale-Aware High-Resolution Representation AUTOML 2022
Automated Detection of Wilson’s Disease Based on Improved Mel-frequency Cepstral Coefficients with Signal Decomposition INTERSPEECH 2022
Soteria: Provable Defense Against Privacy Leakage in Federated Learning From Representation Perspective CVPR 2021
Improving Gradient Regularization using Complex-Valued Neural Networks ICML 2021
FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspective NIPS 2021
Enriching Source Style Transfer in Recognition-Synthesis Based Non-Parallel Voice Conversion INTERSPEECH 2021
Line Art Correlation Matching Feature Transfer Network for Automatic Animation Colorization WACV 2021
BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization ICLR 2021
NASGEM: Neural Architecture Search via Graph Embedding Method AAAI 2021
KGDet: Keypoint-Guided Fashion Detection AAAI 2021
AutoShrink: A Topology-Aware NAS for Discovering Efficient Neural Architecture AAAI 2020
DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures ICLR 2020
DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles NIPS 2020
PENNI: Pruned Kernel Sharing for Efficient CNN Inference ICML 2020
Neural Predictor for Neural Architecture Search ECCV 2020
Defending Neural Backdoors via Generative Distribution Modeling NIPS 2019
Learning Intrinsic Sparse Structures within Long Short-Term Memory ICLR 2018
TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning NIPS 2017
Coordinating Filters for Faster Deep Neural Networks ICCV 2017
Learning Structured Sparsity in Deep Neural Networks NIPS 2016