Li Shen

66

Papers

212

Total Citations

Papers (66)

Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models

A Unified and General Framework for Continual Learning

DREAM: Dual Structured Exploration with Mixup for Open-set Graph Domain Adaption

Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages

Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach

RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness

Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning

Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning

POCE: Primal Policy Optimization with Conservative Estimation for Multi-constraint Offline Reinforcement Learning

Evaluate Geometry of Radiance Fields with Low-Frequency Color Prior

Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer

Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler

Neural Network Approximation for Pessimistic Offline Reinforcement Learning

Merging Multi-Task Models via Weight-Ensembling Mixture of Experts

Generalization Analysis of Stochastic Weight Averaging with General Sampling

Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models

Representation Surgery for Multi-Task Model Merging

Shadow Optimization From Structured Deep Edge Detection

Squeeze-and-Excitation Networks

A Decomposition Algorithm for the Sparse Generalized Eigenvalue Problem

A Sufficient Condition for Convergences of Adam and RMSProp

MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation

Depth-Aware Generative Adversarial Network for Talking Head Video Generation

Learning To Learn and Remember Super Long Multi-Domain Task Sequence

Fine-Tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning

MetaMix: Towards Corruption-Robust Continual Learning With Temporally Self-Adaptive Data Transformation

Robust Generalization Against Photon-Limited Corruptions via Worst-Case Sharpness Minimization

Architecture, Dataset and Model-Scale Agnostic Data-Free Meta-Learning

LoRA Recycle: Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs

Compressing Volumetric Radiance Fields to 1 MB

Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization

Data Augmented Flatness-aware Gradient Projection for Continual Learning

Global Balanced Experts for Federated Long-Tailed Learning

Rethinking the Role of Pre-Trained Networks in Source-Free Domain Adaptation

Meta-Learning with Less Forgetting on Large-Scale Non-stationary Task Distributions

Make Landscape Flatter in Differentially Private Federated Learning

Investigating the Role of Weight Decay in Enhancing Nonconvex SGD

Analytic Energy-Guided Policy Optimization for Offline Reinforcement Learning

Image-to-video Adaptation with Outlier Modeling and Robust Self-learning

Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld

Sheared Backpropagation for Fine-tuning Foundation Models

Your Transferability Barrier is Fragile: Free-Lunch for Transferring the Non-Transferable Learning

FREE: Faster and Better Data-Free Meta-Learning

Decentralized Directed Collaboration for Personalized Federated Learning

Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More

HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning

Q-value Regularized Transformer for Offline Reinforcement Learning

Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications

Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks

Sparse Training via Boosting Pruning Plasticity with Neuroregeneration

MissDAG: Causal Discovery in the Presence of Missing Data with Continuous Additive Noise Models

Streaming Radiance Fields for 3D Video Synthesis

Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation

Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach

Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training

Fair Canonical Correlation Analysis

FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learning

Stability and Generalization of the Decentralized Stochastic Gradient Descent Ascent Algorithm

Federated Learning with Manifold Regularization and Normalized Update Reaggregation

Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learning

An Efficient Dataset Condensation Plugin and Its Application to Continual Learning

Dynamic Sparsity Is Channel-Level Sparsity Learner

Towards Stable Backdoor Purification through Feature Shift Tuning

Understanding How Consistency Works in Federated Learning via Stage-wise Relaxed Initialization

GSOS: Gauss-Seidel Operator Splitting Algorithm for Multi-Term Nonsmooth Convex Composite Optimization

An Algorithmic Framework of Variable Metric Over-Relaxed Hybrid Proximal Extra-Gradient Method