Jian Li

45

Papers

304

Total Citations

Papers (45)

Combinatorial Multi-Armed Bandit with General Reward Functions

NeurIPS 2016arXiv

Bilateral Propagation Network for Depth Completion

Backdoor Federated Learning by Poisoning Backdoor-Critical Layers

Unveiling the Ignorance of MLLMs: Seeing Clearly, Answering Incorrectly

MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection

Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints

Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior

FactorGCL: A Hypergraph-Based Factor Model with Temporal Residual Contrastive Learning for Stock Returns Prediction

Understanding LLM Behaviors via Compression: Data Generation, Knowledge Acquisition and Scaling Laws

NeurIPS 2025arXiv

Decentralized Federated Learning with Model Caching on Mobile Agents

High-Dimensional Analysis for Generalized Nonlinear Regression: From Asymptotics to Algorithm

Rethinking the Uniformity Metric in Self-Supervised Learning

Block-Based Multi-Scale Image Rescaling

Rethinking Mobile Block for Efficient Attention-based Models

From Zero to Detail: Deconstructing Ultra-High-Definition Image Restoration from Progressive Spectral Perspective

On Top-k Selection in Multi-Armed Bandits and Hidden Bipartite Graphs

Stochastic Online Greedy Learning with Semi-bandit Feedbacks

Towards Universal Dataset Distillation via Task-Driven Diffusion

Adapting to Non-Stationary Environments: Multi-Armed Bandit Enhanced Retrieval-Augmented Generation on Knowledge Graphs

Online Restless Multi-Armed Bandits with Long-Term Fairness Constraints

Cheaper and Faster: Distributed Deep Reinforcement Learning with Serverless Computing

DePRL: Achieving Linear Convergence Speedup in Personalized Decentralized Learning with Shared Representations

Provably Efficient Reinforcement Learning for Adversarial Restless Multi-Armed Bandits with Unknown Transitions and Bandit Feedback

Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers

DSFD: Dual Shot Face Detector

Convolution of Convolution: Let Kernels Spatially Collaborate

Learning With Noisy Labels via Self-Supervised Adversarial Noisy Masking

Learning From Noisy Labels With Decoupled Meta Label Purifier

FCC: Feature Clusters Compression for Long-Tailed Visual Recognition

Meta-GF: Training Dynamic-Depth Neural Networks Harmoniously

Multi-Class Learning: From Theory to Algorithm

BRITS: Bidirectional Recurrent Imputation for Time Series

A Simple Proximal Stochastic Gradient Method for Nonsmooth Nonconvex Optimization

Improved Algorithms for Convex-Concave Minimax Optimization

Online Algorithms for Multi-shop Ski Rental with Machine Learned Advice

Kalman Filtering Attention for User Behavior Modeling in CTR Prediction

Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model

Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation

Analyzing Sharpness along GD Trajectory: Progressive Sharpening and Edge of Stability

Generalization Bounds for Gradient Methods via Discrete and Continuous Prior

Learning Infinite-Horizon Average-Reward Restless Multi-Action Bandits via Index Awareness

Finite-Time Analysis of Whittle Index based Q-Learning for Restless Multi-Armed Bandits with Neural Network Function Approximation

GLIME: General, Stable and Local LIME Explanation

K-Means Clustering with Distributed Dimensions

Learning Gradient Descent: Better Generalization and Longer Horizons