PaperHub

Li Shen

~Li_Shen1

93
论文总数
46.5
年均投稿
5.8
平均评分
接收情况55/93
会议分布
ICLR
49
NeurIPS
31
ICML
13

发表论文 (93 篇)

202566

6.1
4

Targeted Low-rank Refinement: Enhancing Sparse Language Models with Precision

ICML 2025Poster
4.5
4

Targeted Low-rank Refinement: Enhancing Sparse Neural Networks with Precision

ICLR 2025withdrawn
4.5
4

Continuous Spiking Graph ODE Networks

ICLR 2025withdrawn
8.2
5

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

NeurIPS 2025Spotlight
7.3
4

Value-Guided Decision Transformer: A Unified Reinforcement Learning Framework for Online and Offline Settings

NeurIPS 2025Poster
6.4
4

Layer as Puzzle Pieces: Compressing Large Language Models through Layer Concatenation

NeurIPS 2025Poster
5.3
3

AlignIQL: Policy Alignment in Implicit Q-Learning through Constrained Optimization

ICLR 2025Rejected
4.7
3

Learning with User-Level Local Differential Privacy

ICLR 2025Rejected
4.0
4

Simultaneous Computation and Memory Efficient Zeroth-Order Optimizer for Fine-Tuning Large Language Models

ICLR 2025withdrawn
6.3
4

PEARL: Towards Permutation-Resilient LLMs

ICLR 2025Poster
5.0
4

LightSAM: Parameter-Agnostic Sharpness-Aware Minimization

ICLR 2025withdrawn
4.7
3

Exploring One-Shot Federated Learning by Model Inversion and Token Relabel with Vision Transformers

ICLR 2025Rejected
5.0
4

FusionBench: A Comprehensive Benchmark of Deep Model Fusion

ICLR 2025Rejected
7.2
4

Decision Mixer: Integrating Long-term and Local Dependencies via Dynamic Token Selection for Decision-Making

ICML 2025Poster
6.8
5

Dynamic Neural Fortresses: An Adaptive Shield for Model Extraction Defense

ICLR 2025Poster
6.8
4

Convergent Differential Privacy Analysis for General Federated Learning

NeurIPS 2025Rejected
6.8
5

Beyond Two-Stage Training: Integrating SFT and RL for Improved Reasoning in LLMs

NeurIPS 2025Rejected
6.8
4

Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation

NeurIPS 2025Poster
3.8
4

Towards Understanding Memory buffer based Continual Learning

ICLR 2025withdrawn
5.5
4

Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent

ICML 2025Poster
4.9
4

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

ICML 2025Poster
6.8
5

Safety Reasoning with Guidelines

ICML 2025Poster
6.4
4

Merging on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging

NeurIPS 2025Poster
6.8
4

CHPO: Constrained Hybrid-action Policy Optimization for Reinforcement Learning

NeurIPS 2025Poster
4.8
4

Solving Continual Offline RL through Selective Weights Activation on Aligned Spaces

ICLR 2025Rejected
6.0
4

Continual Model Merging without Data: Dual Projections for Balancing Stability and Plasticity

NeurIPS 2025Poster
4.5
4

LoRA Recycle: Towards Fine-Tuning-Free Visual Foundation Model via Double-Efficient Data-Free Meta-Learning

ICLR 2025withdrawn
8.0
4

Open-Vocabulary Customization from CLIP via Data-Free Knowledge Distillation

ICLR 2025Oral
6.8
4

Tackling Continual Offline RL through Selective Weights Activation on Aligned Spaces

NeurIPS 2025Poster
8.3
4

Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning

ICML 2025Oral
6.1
4

Contextual Bandits for Unbounded Context Distributions

ICML 2025Poster
7.5
4

Enhancing Learning with Label Differential Privacy by Vector Approximation

ICLR 2025Spotlight
5.8
3

Efficient Federated Learning against Byzantine Attacks and Data Heterogeneity via Aggregating Normalized Gradients

NeurIPS 2025Poster
7.0
3

Self-Verification Provably Prevents Model Collapse in Recursive Synthetic Training

NeurIPS 2025Poster
7.8
4

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

NeurIPS 2025Spotlight
7.3
4

AlphaDecay: Module-wise Weight Decay for Heavy-Tailed Balancing in LLMs

NeurIPS 2025Poster
6.4
4

Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging

NeurIPS 2025Poster
6.8
5

Near-Optimal Online Learning for Multi-Agent Submodular Coordination: Tight Approximation and Communication Efficiency

ICLR 2025Spotlight
6.8
4

MixPrompt: Efficient Mixed Prompting for Multimodal Semantic Segmentation

NeurIPS 2025Poster
2.3
3

Language Model for Large-Text Transmission in Noisy Quantum Communications

ICLR 2025withdrawn
7.8
4

NBSP: A Neuron-Level Framework for Balancing Stability and Plasticity in Deep Reinforcement Learning

NeurIPS 2025Rejected
7.3
4

Analytic Energy-Guided Policy Optimization for Offline Reinforcement Learning

NeurIPS 2025Poster
6.4
4

Robust Policy Expansion for Offline-to-Online RL under Diverse Data Corruption

NeurIPS 2025Poster
4.8
4

Continual Task Learning through Adaptive Policy Self-Composition

ICLR 2025withdrawn
4.0
4

Memory-Efficient Block Coordinate Descent for Hessian-Informed Zeroth-Order Optimizer

ICLR 2025withdrawn
7.0
4

Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace

ICLR 2025Poster
7.8
3

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

ICML 2025Poster
4.9
4

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

ICML 2025Poster
4.4
4

Memory Efficient Block Coordinate Descent Method for Forward-Only Second-Order Finetuning of LLM Models

ICML 2025Rejected
8.0
4

Combatting Dimensional Collapse in LLM Pre-Training Data via Submodular File Selection

ICLR 2025Oral
5.8
4

Understanding the Stability-based Generalization of Personalized Federated Learning

ICLR 2025Poster
8.3
4

Retrieval-Augmented Perception: High-resolution Image Perception Meets Visual RAG

ICML 2025Oral
6.4
4

RoMa: A Robust Model Watermarking Scheme for Protecting IP in Diffusion Models

NeurIPS 2025Poster
6.3
3

Multinoulli Extension: A Lossless Yet Effective Probabilistic Framework for Subset Selection over Partition Constraints

ICML 2025Poster
7.6
3

Unveiling the Power of Multiple Gossip Steps: A Stability-Based Generalization Analysis in Decentralized Training

NeurIPS 2025Spotlight
5.0
4

Towards Constraint-aware Learning for Resource Allocation in NFV-enabled Networks

ICLR 2025Rejected
4.4
5

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs

ICLR 2025Rejected
6.0
4

Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought

NeurIPS 2025Poster
5.5
3

GraphCL: Graph-based Clustering for Semi-Supervised Medical Image Segmentation

ICML 2025Poster
7.3
4

Effective Policy Learning for Multi-Agent Online Coordination Beyond Submodular Objectives

NeurIPS 2025Poster
6.4
4

R1-ShareVL: Incentivizing Reasoning Capabilities of Multimodal Large Language Models via Share-GRPO

NeurIPS 2025Poster
3.8
4

AGLP: A Graph Learning Perspective for Semi-supervised Domain Adaptation

ICLR 2025withdrawn
4.5
4

Open-World Test-Time Training: Self-Training with Contrastive Learning

ICLR 2025withdrawn
2.3
3

SgCG: Semantic-guided Contrastive Generalization for Medical Image Segmentation

ICLR 2025withdrawn
6.8
4

Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization

NeurIPS 2025Poster
7.8
4

Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search

NeurIPS 2025Spotlight

202427

6.3
4

A-FedPD: Aligning Dual-Drift is All Federated Primal-Dual Learning Needs

NeurIPS 2024Spotlight
4.5
4

Which mode is better for federated learning? Centralized or Decentralized

ICLR 2024Rejected
5.0
4

Exploring the Generalization Capabilities of AID-based Bi-level Optimization

ICLR 2024Rejected
4.0
4

Solving Continual Offline Reinforcement Learning with Decision Transformer

ICLR 2024withdrawn
6.0
4

Prompt Tuning with Diffusion for Few-Shot Pre-trained Policy Generalization

ICLR 2024Rejected
5.3
4

Decomposed Prompt Decision Transformer for Efficient Unseen Task Generalization

NeurIPS 2024Poster
7.0
4

Learning Multi-Agent Communication from Graph Modeling Perspective

ICLR 2024Poster
4.5
4

Graph Decision Transformer

ICLR 2024withdrawn
4.5
4

Prompt-Tuning Decision Transformer with Preference Ranking

ICLR 2024withdrawn
7.0
4

Parameter-Efficient Multi-Task Model Fusion with Partial Linearization

ICLR 2024Poster
4.8
4

Task-Distributionally Robust Data-Free Meta-Learning

ICLR 2024withdrawn
6.0
3

A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacy

NeurIPS 2024Poster
5.8
4

($\texttt{PASS}$) Visual Prompt Locates Good Structure Sparisty through a Recurent HyperNetwork

ICLR 2024Rejected
5.3
4

A Unified and General Framework for Continual Learning

ICLR 2024Poster
6.5
4

AdaMerging: Adaptive Model Merging for Multi-Task Learning

ICLR 2024Poster
6.7
3

Improving Non-Transferable Representation Learning by Harnessing Content and Style

ICLR 2024Spotlight
6.4
5

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

ICLR 2024Poster
5.2
5

Graph-PDE: Coupled ODE Structure for Graph Neural Networks

ICLR 2024withdrawn
6.0
4

Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense

NeurIPS 2024Spotlight
5.5
4

Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy

ICLR 2024Rejected
4.8
4

Enhancing Personal Decentralized Federated Learning through Model Decoupling

ICLR 2024Rejected
4.0
4

Asymmetrically Decentralized Federated Learning

ICLR 2024withdrawn
4.3
4

Federated Tuning for Black Box Large Models

ICLR 2024withdrawn
4.3
3

Instructed Diffuser with Temporal Condition Guidance for Offline Reinforcement Learning

ICLR 2024withdrawn
6.0
4

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

ICLR 2024Poster
3.0
4

Are Large Language Models Really Robust to Word-Level Perturbations?

ICLR 2024withdrawn
5.7
3

Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?

NeurIPS 2024Poster