Li Shen

30

Papers

212

Total Citations

Papers (30)

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

NeurIPS 2025arXiv

Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning

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

Evaluate Geometry of Radiance Fields with Low-Frequency Color Prior

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

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

NeurIPS 2025arXiv

Neural Network Approximation for Pessimistic Offline Reinforcement Learning

Investigating the Role of Weight Decay in Enhancing Nonconvex SGD

Decentralized Directed Collaboration for Personalized Federated Learning

Analytic Energy-Guided Policy Optimization for Offline Reinforcement Learning

NeurIPS 2025arXiv

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

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

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

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

Representation Surgery for Multi-Task Model Merging

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

Sheared Backpropagation for Fine-tuning Foundation Models

FREE: Faster and Better Data-Free Meta-Learning

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

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