PPaperPicks

Li Shen

Sun Yat-sen University Shenzhen Campus, School of Cyber Science and Technology, Shenzhen, China

91 papers at tracked venues · 83 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0001-5659-3464 ↗Google Scholar ↗Homepage ↗

Venues

NeurIPS ×27ICML ×19ICLR ×15ACL ×8CVPR ×8ACM MM ×3EMNLP ×3AAAI ×2IJCAI ×2AAMAS ×1ECAI ×1ECCV ×1ICCV ×1

Frequent coauthors

Yongxian Wei
DBLP profile ↗ORCID search ↗
×4
Shengchao Hu
DBLP profile ↗ORCID search ↗
×4
Yuchen Wu
DBLP profile ↗ORCID search ↗
×3
Zixuan Hu
DBLP profile ↗ORCID search ↗
×3
Puning Zhao
DBLP profile ↗ORCID search ↗
×3
Enneng Yang
DBLP profile ↗ORCID search ↗
×3
Hongling Zheng
DBLP profile ↗ORCID search ↗
×3
Wenbin Wang
DBLP profile ↗ORCID search ↗
×3
Qixin Zhang
DBLP profile ↗ORCID search ↗
×3
Anke Tang
DBLP profile ↗ORCID search ↗
×3
Haotian Luo
DBLP profile ↗ORCID search ↗
×2
Fei Wang
DBLP profile ↗ORCID search ↗
×2

Papers

  1. CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning
    ACL 2026 ·
    Biao Yi
    DBLP profile ↗ORCID search ↗
  2. Efficient Transformer Parameter Reuse via Zero-Token Mechanism
    ACL 2026 ·
    Guanghao Li
    DBLP profile ↗ORCID search ↗
  3. O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning
    ACL 2026 ·
    Haotian Luo
    DBLP profile ↗ORCID search ↗
  4. Reason-KE++: Aligning the Process, Not Just the Outcome, for Faithful LLM Knowledge Editing
    ACL 2026 ·
    Yuchen Wu
    DBLP profile ↗ORCID search ↗
  5. Universally Empowering Zeroth-Order Optimization via Adaptive Layer-wise Sampling
    ACL 2026 ·
    Fei Wang
    DBLP profile ↗ORCID search ↗
  6. Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization
    NeurIPS 2025 ·
    Haotian Luo
    DBLP profile ↗ORCID search ↗
  7. Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler
    NeurIPS 2025 ·
    Zixuan Hu
    DBLP profile ↗ORCID search ↗
  8. AlphaDecay: Module-wise Weight Decay for Heavy-Tailed Balancing in LLMs
    NeurIPS 2025 ·
    Di He
    DBLP profile ↗ORCID search ↗
  9. Analytic Energy-Guided Policy Optimization for Offline Reinforcement Learning
    NeurIPS 2025 ·
    Jifeng Hu
    DBLP profile ↗ORCID search ↗
  10. CHPO: Constrained Hybrid-action Policy Optimization for Reinforcement Learning
    NeurIPS 2025 ·
    Ao Zhou
    DBLP profile ↗ORCID search ↗
  11. Combatting Dimensional Collapse in LLM Pre-Training Data via Submodular File Selection
    ICLR 2025 ·
    Ziqing Fan
    DBLP profile ↗ORCID search ↗
  12. Contextual Bandits for Unbounded Context Distributions
    ICML 2025 ·
    Puning Zhao
    DBLP profile ↗ORCID search ↗
  13. Continual Model Merging without Data: Dual Projections for Balancing Stability and Plasticity
    NeurIPS 2025 ·
    Enneng Yang
    DBLP profile ↗ORCID search ↗
  14. Decision Mixer: Integrating Long-term and Local Dependencies via Dynamic Token Selection for Decision-Making
    ICML 2025 ·
    Hongling Zheng
    DBLP profile ↗ORCID search ↗
  15. Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models
    AAAI 2025 ·
    Wenbin Wang
    DBLP profile ↗ORCID search ↗
  16. Dynamic Analysis and Adaptive Discriminator for Fake News Detection
    ACM MM 2025 ·
    Xinqi Su
    DBLP profile ↗ORCID search ↗
  17. Dynamic Neural Fortresses: An Adaptive Shield for Model Extraction Defense
    ICLR 2025 ·
    Siyu Luan
    DBLP profile ↗ORCID search ↗
  18. DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs
    EMNLP 2025 ·
    Xiabin Zhou
    DBLP profile ↗ORCID search ↗
  19. Edit Once, Update Everywhere: A Simple Framework for Cross-Lingual Knowledge Synchronization in LLMs
    ACL 2025 ·
    Yuchen Wu
    DBLP profile ↗ORCID search ↗
  20. Effective Policy Learning for Multi-Agent Online Coordination Beyond Submodular Objectives
    NeurIPS 2025 ·
    Qixin Zhang
    DBLP profile ↗ORCID search ↗
  21. Efficient Federated Learning against Byzantine Attacks and Data Heterogeneity via Aggregating Normalized Gradients
    NeurIPS 2025 ·
    Shiyuan Zuo
    DBLP profile ↗ORCID search ↗
  22. Enhancing Learning with Label Differential Privacy by Vector Approximation
    ICLR 2025 ·
    Puning Zhao
    DBLP profile ↗ORCID search ↗
  23. GraphCL: Graph-based Clustering for Semi-Supervised Medical Image Segmentation
    ICML 2025 ·
    Mengzhu Wang
    DBLP profile ↗ORCID search ↗
  24. Hypernetwork Aggregation for Decentralized Personalized Federated Learning
    IJCAI 2025 ·
    Weishi Li
    DBLP profile ↗ORCID search ↗
  25. Investigating the Role of Weight Decay in Enhancing Nonconvex SGD
    CVPR 2025 ·
    Tao Sun
    DBLP profile ↗ORCID search ↗
  26. Layer as Puzzle Pieces: Compressing Large Language Models through Layer Concatenation
    NeurIPS 2025 ·
    Fei Wang
    DBLP profile ↗ORCID search ↗
  27. LoRA Recycle: Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs
    CVPR 2025 ·
    Zixuan Hu
    DBLP profile ↗ORCID search ↗
  28. Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More
    ICML 2025 ·
    Xialie Zhuang
    DBLP profile ↗ORCID search ↗
  29. Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer
    ICML 2025 ·
    Yilun Kong
    DBLP profile ↗ORCID search ↗
  30. Merging on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging
    NeurIPS 2025 ·
    Anke Tang
    DBLP profile ↗ORCID search ↗
  31. Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace
    ICLR 2025 ·
    Jinluan Yang
    DBLP profile ↗ORCID search ↗
  32. Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging
    NeurIPS 2025 ·
    Jinluan Yang
    DBLP profile ↗ORCID search ↗
  33. MixPrompt: Efficient Mixed Prompting for Multimodal Semantic Segmentation
    NeurIPS 2025 ·
    Zhiwei Hao
    DBLP profile ↗ORCID search ↗
  34. Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent
    ICML 2025 ·
    Yongxian Wei
    DBLP profile ↗ORCID search ↗
  35. MuGS: Multi-Baseline Generalizable Gaussian Splatting Reconstruction
    ICCV 2025 ·
    Yaopeng Lou
    DBLP profile ↗ORCID search ↗
  36. Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search
    NeurIPS 2025 ·
    Huanjin Yao
    DBLP profile ↗ORCID search ↗
  37. Multinoulli Extension: A Lossless Yet Effective Probabilistic Framework for Subset Selection over Partition Constraints
    ICML 2025 ·
    Qixin Zhang
    DBLP profile ↗ORCID search ↗
  38. Near-Optimal Online Learning for Multi-Agent Submodular Coordination: Tight Approximation and Communication Efficiency
    ICLR 2025 ·
    Qixin Zhang
    DBLP profile ↗ORCID search ↗
  39. Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning
    ICML 2025 ·
    Guozheng Ma
    DBLP profile ↗ORCID search ↗
  40. Open-Vocabulary Customization from CLIP via Data-Free Knowledge Distillation
    ICLR 2025 ·
    Yongxian Wei
    DBLP profile ↗ORCID search ↗
  41. PEARL: Towards Permutation-Resilient LLMs
    ICLR 2025 ·
    Liang Chen
    DBLP profile ↗ORCID search ↗
  42. Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation
    NeurIPS 2025 ·
    Yibo Wang
    DBLP profile ↗ORCID search ↗
  43. Prompt Tuning with Diffusion for Few-Shot Pre-trained Policy Generalization
    AAMAS 2025 ·
    Shengchao Hu
    DBLP profile ↗ORCID search ↗
  44. R1-ShareVL: Incentivizing Reasoning Capabilities of Multimodal Large Language Models via Share-GRPO
    NeurIPS 2025 ·
    Huanjin Yao
    DBLP profile ↗ORCID search ↗
  45. Retrieval-Augmented Perception: High-resolution Image Perception Meets Visual RAG
    ICML 2025 ·
    Wenbin Wang
    DBLP profile ↗ORCID search ↗
  46. RoMa: A Robust Model Watermarking Scheme for Protecting IP in Diffusion Models
    NeurIPS 2025 ·
    Yingsha Xie
    DBLP profile ↗ORCID search ↗
  47. Robust Knowledge Editing via Explicit Reasoning Chains for Distractor-Resilient Multi-Hop QA
    EMNLP 2025 ·
    Yuchen Wu
    DBLP profile ↗ORCID search ↗
  48. Robust Policy Expansion for Offline-to-Online RL under Diverse Data Corruption
    NeurIPS 2025 ·
    Longxiang He
    DBLP profile ↗ORCID search ↗
  49. Safety Reasoning with Guidelines
    ICML 2025 ·
    Haoyu Wang
    DBLP profile ↗ORCID search ↗
  50. Self-Verification Provably Prevents Model Collapse in Recursive Synthetic Training
    NeurIPS 2025 ·
    Shi Fu
    DBLP profile ↗ORCID search ↗
  51. Tackling Continual Offline RL through Selective Weights Activation on Aligned Spaces
    NeurIPS 2025 ·
    Jifeng Hu
    DBLP profile ↗ORCID search ↗
  52. Targeted Low-rank Refinement: Enhancing Sparse Language Models with Precision
    ICML 2025 · Li Shen
  53. Understanding the Stability-based Generalization of Personalized Federated Learning
    ICLR 2025 ·
    Yingqi Liu
    DBLP profile ↗ORCID search ↗
  54. Unveiling the Power of Multiple Gossip Steps: A Stability-Based Generalization Analysis in Decentralized Training
    NeurIPS 2025 ·
    Qinglun Li
    DBLP profile ↗ORCID search ↗
  55. Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought
    NeurIPS 2025 ·
    Chao Huang
    DBLP profile ↗ORCID search ↗
  56. Value-Guided Decision Transformer: A Unified Reinforcement Learning Framework for Online and Offline Settings
    NeurIPS 2025 ·
    Hongling Zheng
    DBLP profile ↗ORCID search ↗
  57. Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning
    ICML 2025 ·
    Liang Chen
    DBLP profile ↗ORCID search ↗
  58. A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacy
    NeurIPS 2024 ·
    Puning Zhao
    DBLP profile ↗ORCID search ↗
  59. A Unified and General Framework for Continual Learning
    ICLR 2024 ·
    Zhenyi Wang
    DBLP profile ↗ORCID search ↗
  60. A-FedPD: Aligning Dual-Drift is All Federated Primal-Dual Learning Needs
    NeurIPS 2024 ·
    Yan Sun
    DBLP profile ↗ORCID search ↗
  61. AdaMerging: Adaptive Model Merging for Multi-Task Learning
    ICLR 2024 ·
    Enneng Yang
    DBLP profile ↗ORCID search ↗
  62. DREAM: Dual Structured Exploration with Mixup for Open-set Graph Domain Adaption
    ICLR 2024 ·
    Nan Yin
    DBLP profile ↗ORCID search ↗
  63. Decentralized Directed Collaboration for Personalized Federated Learning
    CVPR 2024 ·
    Yingqi Liu
    DBLP profile ↗ORCID search ↗
  64. Decomposed Prompt Decision Transformer for Efficient Unseen Task Generalization
    NeurIPS 2024 ·
    Hongling Zheng
    DBLP profile ↗ORCID search ↗
  65. Diversifying the Mixture-of-Experts Representation for Language Models with Orthogonal Optimizer
    ECAI 2024 ·
    Boan Liu
    DBLP profile ↗ORCID search ↗
  66. Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld
    CVPR 2024 ·
    Yijun Yang
    DBLP profile ↗ORCID search ↗
  67. Free: Faster and Better Data-Free Meta-Learning
    CVPR 2024 ·
    Yongxian Wei
    DBLP profile ↗ORCID search ↗
  68. Generalization Analysis of Stochastic Weight Averaging with General Sampling
    ICML 2024 ·
    Peng Wang
    DBLP profile ↗ORCID search ↗
  69. HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning
    ICML 2024 ·
    Shengchao Hu
    DBLP profile ↗ORCID search ↗
  70. Improving Non-Transferable Representation Learning by Harnessing Content and Style
    ICLR 2024 ·
    Ziming Hong
    DBLP profile ↗ORCID search ↗
  71. Is C4 Dataset Optimal for Pruning? An Investigation of Calibration Data for LLM Pruning
    EMNLP 2024 ·
    Abhinav Bandari
    DBLP profile ↗ORCID search ↗
  72. Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?
    NeurIPS 2024 ·
    Yang Dai
    DBLP profile ↗ORCID search ↗
  73. Learning Multi-Agent Communication from Graph Modeling Perspective
    ICLR 2024 ·
    Shengchao Hu
    DBLP profile ↗ORCID search ↗
  74. Merging Multi-Task Models via Weight-Ensembling Mixture of Experts
    ICML 2024 ·
    Anke Tang
    DBLP profile ↗ORCID search ↗
  75. MuEP: A Multimodal Benchmark for Embodied Planning with Foundation Models
    IJCAI 2024 ·
    Kanxue Li
    DBLP profile ↗ORCID search ↗
  76. Neural Network Approximation for Pessimistic Offline Reinforcement Learning
    AAAI 2024 ·
    Di Wu
    DBLP profile ↗ORCID search ↗
  77. OOP: Object-Oriented Programming Evaluation Benchmark for Large Language Models
    ACL 2024 ·
    Shuai Wang
    DBLP profile ↗ORCID search ↗
  78. POCE: Primal Policy Optimization with Conservative Estimation for Multi-constraint Offline Reinforcement Learning
    CVPR 2024 ·
    Jiayi Guan
    DBLP profile ↗ORCID search ↗
  79. Parameter-Efficient Multi-Task Model Fusion with Partial Linearization
    ICLR 2024 ·
    Anke Tang
    DBLP profile ↗ORCID search ↗
  80. PrimKD: Primary Modality Guided Multimodal Fusion for RGB-D Semantic Segmentation
    ACM MM 2024 ·
    Zhiwei Hao
    DBLP profile ↗ORCID search ↗
  81. Q-value Regularized Transformer for Offline Reinforcement Learning
    ICML 2024 ·
    Shengchao Hu
    DBLP profile ↗ORCID search ↗
  82. Representation Surgery for Multi-Task Model Merging
    ICML 2024 ·
    Enneng Yang
    DBLP profile ↗ORCID search ↗
  83. Revisiting Knowledge Distillation for Autoregressive Language Models
    ACL 2024 ·
    Qihuang Zhong
    DBLP profile ↗ORCID search ↗
  84. Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages
    ICLR 2024 ·
    Guozheng Ma
    DBLP profile ↗ORCID search ↗
  85. Sheared Backpropagation for Fine-Tuning Foundation Models
    CVPR 2024 ·
    Zhiyuan Yu
    DBLP profile ↗ORCID search ↗
  86. Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications
    ICML 2024 ·
    Zixuan Hu
    DBLP profile ↗ORCID search ↗
  87. Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models
    ICML 2024 ·
    Yongxian Wei
    DBLP profile ↗ORCID search ↗
  88. Training A Secure Model Against Data-Free Model Extraction
    ECCV 2024 ·
    Zhenyi Wang
    DBLP profile ↗ORCID search ↗
  89. Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense
    NeurIPS 2024 ·
    Rui Min
    DBLP profile ↗ORCID search ↗
  90. WisdoM: Improving Multimodal Sentiment Analysis by Fusing Contextual World Knowledge
    ACM MM 2024 ·
    Wenbin Wang
    DBLP profile ↗ORCID search ↗
  91. Your Transferability Barrier is Fragile: Free-Lunch for Transferring the Non-Transferable Learning
    CVPR 2024 ·
    Ziming Hong
    DBLP profile ↗ORCID search ↗