Hai Li

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