Li Shen

CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning ACL 2026 Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach ICML 2025 Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models AAAI 2025 Image-to-video Adaptation with Outlier Modeling and Robust Self-learning AAAI 2025 Edit Once, Update Everywhere: A Simple Framework for Cross-Lingual Knowledge Synchronization in LLMs ACL 2025 Investigating the Role of Weight Decay in Enhancing Nonconvex SGD CVPR 2025 LoRA Recycle: Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs CVPR 2025 DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs EMNLP 2025 Robust Knowledge Editing via Explicit Reasoning Chains for Distractor-Resilient Multi-Hop QA EMNLP 2025 PEARL: Towards Permutation-Resilient LLMs ICLR 2025 Enhancing Learning with Label Differential Privacy by Vector Approximation ICLR 2025 Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace ICLR 2025 Near-Optimal Online Learning for Multi-Agent Submodular Coordination: Tight Approximation and Communication Efficiency ICLR 2025 Combatting Dimensional Collapse in LLM Pre-Training Data via Submodular File Selection ICLR 2025 Dynamic Neural Fortresses: An Adaptive Shield for Model Extraction Defense ICLR 2025 Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic ICLR 2025 Understanding the Stability-based Generalization of Personalized Federated Learning ICLR 2025 Open-Vocabulary Customization from CLIP via Data-Free Knowledge Distillation ICLR 2025 Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning ICML 2025 Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer ICML 2025 Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning ICML 2025 Targeted Low-rank Refinement: Enhancing Sparse Language Models with Precision ICML 2025 Retrieval-Augmented Perception: High-resolution Image Perception Meets Visual RAG ICML 2025 Safety Reasoning with Guidelines ICML 2025 GraphCL: Graph-based Clustering for Semi-Supervised Medical Image Segmentation ICML 2025 Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent ICML 2025 Multinoulli Extension: A Lossless Yet Effective Probabilistic Framework for Subset Selection over Partition Constraints ICML 2025 Contextual Bandits for Unbounded Context Distributions ICML 2025 Decision Mixer: Integrating Long-term and Local Dependencies via Dynamic Token Selection for Decision-Making ICML 2025 Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More ICML 2025 Hypernetwork Aggregation for Decentralized Personalized Federated Learning IJCAI 2025 FusionBench: A Unified Library and Comprehensive Benchmark for Deep Model Fusion JMLR 2025 DALK: Dynamic Co-Augmentation of LLMs and KG to answer Alzheimer’s Disease Questions with Scientific Literature EMNLP 2024 AdaMerging: Adaptive Model Merging for Multi-Task Learning ICLR 2024 Parameter-Efficient Multi-Task Model Fusion with Partial Linearization ICLR 2024 Revisiting Knowledge Distillation for Autoregressive Language Models ACL 2024 A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacy NIPS 2024 Decomposed Prompt Decision Transformer for Efficient Unseen Task Generalization NIPS 2024 A-FedPD: Aligning Dual-Drift is All Federated Primal-Dual Learning Needs NIPS 2024 A Unified and General Framework for Continual Learning ICLR 2024 Learning Multi-Agent Communication from Graph Modeling Perspective ICLR 2024 Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense NIPS 2024 Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning? NIPS 2024 Fairness-Aware Estimation of Graphical Models NIPS 2024 DREAM: Dual Structured Exploration with Mixup for Open-set Graph Domain Adaption ICLR 2024 Improving Non-Transferable Representation Learning by Harnessing Content and Style ICLR 2024 Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages ICLR 2024 Merging Multi-Task Models via Weight-Ensembling Mixture of Experts ICML 2024 Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications ICML 2024 OOP: Object-Oriented Programming Evaluation Benchmark for Large Language Models ACL 2024 Representation Surgery for Multi-Task Model Merging ICML 2024 Dude: Dual Distribution-Aware Context Prompt Learning For Large Vision-Language Model ACML 2024 Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models ICML 2024 Online Bilevel Optimization: Regret Analysis of Online Alternating Gradient Methods AISTATS 2024 FREE: Faster and Better Data-Free Meta-Learning CVPR 2024 POCE: Primal Policy Optimization with Conservative Estimation for Multi-constraint Offline Reinforcement Learning CVPR 2024 Your Transferability Barrier is Fragile: Free-Lunch for Transferring the Non-Transferable Learning CVPR 2024 Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld CVPR 2024 Sheared Backpropagation for Fine-tuning Foundation Models CVPR 2024 Decentralized Directed Collaboration for Personalized Federated Learning CVPR 2024 HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning ICML 2024 Q-value Regularized Transformer for Offline Reinforcement Learning ICML 2024 Volume-optimal persistence homological scaffolds of hemodynamic networks covary with MEG theta-alpha aperiodic dynamics MICCAI 2024 Subject-Adaptive Transfer Learning Using Resting State EEG Signals for Cross-Subject EEG Motor Imagery Classification MICCAI 2024 Unmasking Bias in Diffusion Model Training ECCV 2024 Training A Secure Model against Data-Free Model Extraction ECCV 2024 MuEP: A Multimodal Benchmark for Embodied Planning with Foundation Models IJCAI 2024 Generalization Analysis of Stochastic Weight Averaging with General Sampling ICML 2024 Neural Network Approximation for Pessimistic Offline Reinforcement Learning AAAI 2024 Evaluate Geometry of Radiance Fields with Low-Frequency Color Prior AAAI 2024 Is C4 Dataset Optimal for Pruning? An Investigation of Calibration Data for LLM Pruning EMNLP 2024 Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization ICCV 2023 MetaMix: Towards Corruption-Robust Continual Learning With Temporally Self-Adaptive Data Transformation CVPR 2023 Robust Generalization Against Photon-Limited Corruptions via Worst-Case Sharpness Minimization CVPR 2023 Architecture, Dataset and Model-Scale Agnostic Data-Free Meta-Learning CVPR 2023 Make Landscape Flatter in Differentially Private Federated Learning CVPR 2023 Compressing Volumetric Radiance Fields to 1 MB CVPR 2023 Zero-shot Sharpness-Aware Quantization for Pre-trained Language Models EMNLP 2023 Merging Experts into One: Improving Computational Efficiency of Mixture of Experts EMNLP 2023 Towards Making the Most of ChatGPT for Machine Translation EMNLP 2023 Data Augmented Flatness-aware Gradient Projection for Continual Learning ICCV 2023 Global Balanced Experts for Federated Long-Tailed Learning ICCV 2023 Rethinking the Role of Pre-Trained Networks in Source-Free Domain Adaptation ICCV 2023 FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy ICLR 2023 Towards One-shot Neural Combinatorial Solvers: Theoretical and Empirical Notes on the Cardinality-Constrained Case ICLR 2023 Harnessing Out-Of-Distribution Examples via Augmenting Content and Style ICLR 2023 Fairness-aware class imbalanced learning on multiple subgroups UAI 2023 Learning to Learn from APIs: Black-Box Data-Free Meta-Learning ICML 2023 Are Large Kernels Better Teachers than Transformers for ConvNets? ICML 2023 Improving the Model Consistency of Decentralized Federated Learning ICML 2023 Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape ICML 2023 CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classification ICML 2023 Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training NIPS 2023 Fair Canonical Correlation Analysis NIPS 2023 FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learning NIPS 2023 Stability and Generalization of the Decentralized Stochastic Gradient Descent Ascent Algorithm NIPS 2023 Federated Learning with Manifold Regularization and Normalized Update Reaggregation NIPS 2023 Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learning NIPS 2023 An Efficient Dataset Condensation Plugin and Its Application to Continual Learning NIPS 2023 Dynamic Sparsity Is Channel-Level Sparsity Learner NIPS 2023 Towards Stable Backdoor Purification through Feature Shift Tuning NIPS 2023 Understanding How Consistency Works in Federated Learning via Stage-wise Relaxed Initialization NIPS 2023 Offline Quantum Reinforcement Learning in a Conservative Manner AAAI 2023 FedABC: Targeting Fair Competition in Personalized Federated Learning AAAI 2023 AdaTask: A Task-Aware Adaptive Learning Rate Approach to Multi-Task Learning AAAI 2023 Evaluating Model-Free Reinforcement Learning toward Safety-Critical Tasks AAAI 2023 Understanding Robust Overfitting of Adversarial Training and Beyond ICML 2022 Fine-Tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning CVPR 2022 Learning To Learn and Remember Super Long Multi-Domain Task Sequence CVPR 2022 MissDAG: Causal Discovery in the Presence of Missing Data with Continuous Additive Noise Models NIPS 2022 Streaming Radiance Fields for 3D Video Synthesis NIPS 2022 Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation NIPS 2022 Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach NIPS 2022 Robust Unlearnable Examples: Protecting Data Privacy Against Adversarial Learning ICLR 2022 The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training ICLR 2022 Robust Weight Perturbation for Adversarial Training IJCAI 2022 Few-Shot Adaptation of Pre-Trained Networks for Domain Shift IJCAI 2022 Penalized Proximal Policy Optimization for Safe Reinforcement Learning IJCAI 2022 Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models EMNLP 2022 Towards Practical Adam: Non-Convexity, Convergence Theory, and Mini-Batch Acceleration JMLR 2022 Meta-Learning with Less Forgetting on Large-Scale Non-stationary Task Distributions ECCV 2022 Meta-learning without data via Wasserstein distributionally-robust model fusion UAI 2022 DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training ICML 2022 Deep Neural Network Fusion via Graph Matching with Applications to Model Ensemble and Federated Learning ICML 2022 Improving Task-free Continual Learning by Distributionally Robust Memory Evolution ICML 2022 On the Complementarity between Pre-Training and Random-Initialization for Resource-Rich Machine Translation COLING 2022 Depth-Aware Generative Adversarial Network for Talking Head Video Generation CVPR 2022 Sparse Training via Boosting Pruning Plasticity with Neuroregeneration NIPS 2021 Communication Efficient Primal-Dual Algorithm for Nonconvex Nonsmooth Distributed Optimization AISTATS 2021 Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networks ICML 2020 Adaptive Activation Network and Functional Regularization for Efficient and Flexible Deep Multi-Task Learning AAAI 2020 MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation CVPR 2020 A Decomposition Algorithm for the Sparse Generalized Eigenvalue Problem CVPR 2019 Discrete Trust-aware Matrix Factorization for Fast Recommendation IJCAI 2019 A Sufficient Condition for Convergences of Adam and RMSProp CVPR 2019 Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks NIPS 2018 Squeeze-and-Excitation Networks CVPR 2018 An Algorithmic Framework of Variable Metric Over-Relaxed Hybrid Proximal Extra-Gradient Method ICML 2018 Comparator Networks ECCV 2018 GSOS: Gauss-Seidel Operator Splitting Algorithm for Multi-Term Nonsmooth Convex Composite Optimization ICML 2017 Shadow Optimization From Structured Deep Edge Detection CVPR 2015 Adaptive Sharing for Image Classification IJCAI 2015 A New Perspective on Material Classification and Ink Identification CVPR 2014 Multi-level Discriminative Dictionary Learning towards Hierarchical Visual Categorization CVPR 2013 High-Order Multi-Task Feature Learning to Identify Longitudinal Phenotypic Markers for Alzheimer's Disease Progression Prediction NIPS 2012