Wei Chen

85

Papers

957

Total Citations

Papers (85)

R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization

Combinatorial Multi-Armed Bandit with General Reward Functions

NeurIPS 2016arXiv

A Communication-Efficient Parallel Algorithm for Decision Tree

NeurIPS 2016arXiv

Paying More Attention to Images: A Training-Free Method for Alleviating Hallucination in LVLMs

Improving Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms and Its Applications

NeurIPS 2017arXiv

Language-Image Pre-training with Long Captions

Finite Sample Analysis of the GTD Policy Evaluation Algorithms in Markov Setting

NeurIPS 2017arXiv

Mechanism Design for LLM Fine-tuning with Multiple Reward Models

Perturbation-Invariant Adversarial Training for Neural Ranking Models: Improving the Effectiveness-Robustness Trade-Off

CoMM: A Coherent Interleaved Image-Text Dataset for Multimodal Understanding and Generation

GRPose: Learning Graph Relations for Human Image Generation with Pose Priors

Identification of Causal Structure with Latent Variables Based on Higher Order Cumulants

HMoRA: Making LLMs More Effective with Hierarchical Mixture of LoRA Experts

Expand and Compress: Exploring Tuning Principles for Continual Spatio-Temporal Graph Forecasting

Smoothness Really Matters: A Simple Yet Effective Approach for Unsupervised Graph Domain Adaptation

Fully Exploiting Every Real Sample: SuperPixel Sample Gradient Model Stealing

Sparse Fine-Tuning of Transformers for Generative Tasks

Gradient-Guided Credit Assignment and Joint Optimization for Dependency-Aware Spatial Crowdsourcing

EVODiff: Entropy-aware Variance Optimized Diffusion Inference

Structural-Entropy-Based Sample Selection for Efficient and Effective Learning

Achieving Speed-Accuracy Balance in Vision-based 3D Occupancy Prediction via Geometric-Semantic Disentanglement

Make Domain Shift a Catastrophic Forgetting Alleviator in Class-Incremental Learning

Correlation-Attention Masked Temporal Transformer for User Identity Linkage Using Heterogeneous Mobility Data

Debiased Active Learning with Variational Gradient Rectifier

G2L-Net: Global to Local Network for Real-Time 6D Pose Estimation With Embedding Vector Features

FS-Net: Fast Shape-Based Network for Category-Level 6D Object Pose Estimation With Decoupled Rotation Mechanism

Lifelong Person Re-Identification via Adaptive Knowledge Accumulation

Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart

TO-FLOW: Efficient Continuous Normalizing Flows With Temporal Optimization Adjoint With Moving Speed

Action Detection by Implicit Intentional Motion Clustering

Low-Rank Tensor Completion: A Pseudo-Bayesian Learning Approach

Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-Trained Vision-Language Models

Dual Refinement Underwater Object Detection Network

Stochastic Online Greedy Learning with Semi-bandit Feedbacks

LightGBM: A Highly Efficient Gradient Boosting Decision Tree

Influence Maximization with $\varepsilon$-Almost Submodular Threshold Functions

D2-TPred: Discontinuous Dependency for Trajectory Prediction under Traffic Lights

HoliTracer: Holistic Vectorization of Geographic Objects from Large-Size Remote Sensing Imagery

Self-supervised Learning of Hybrid Part-aware 3D Representations of 2D Gaussians and Superquadrics

NAPPure: Adversarial Purification for Robust Image Classification under Non-Additive Perturbations

A3GS: Arbitrary Artistic Style into Arbitrary 3D Gaussian Splatting

Curve-Aware Gaussian Splatting for 3D Parametric Curve Reconstruction

M2EIT: Multi-Domain Mixture of Experts for Robust Neural Inertial Tracking

FDPT: Federated Discrete Prompt Tuning for Black-Box Visual-Language Models

Task-Decoupled Bézier Surface Constraint for Uneven Low-Light Image Enhancement

DiffDVC: Accurate Event Detection for Dense Video Captioning via Diffusion Models

Scalable Trajectory-User Linking with Dual-Stream Representation Networks

Spatial-Temporal Knowledge Distillation for Takeaway Recommendation

CognTKE: A Cognitive Temporal Knowledge Extrapolation Framework

Learnware Specification via Label-Aware Neural Embedding

FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learning

A Systematic Exploration of Knowledge Graph Alignment with Large Language Models in Retrieval Augmented Generation

Synergistic Multi-Agent Framework with Trajectory Learning for Knowledge-Intensive Tasks

TNPAR: Topological Neural Poisson Auto-Regressive Model for Learning Granger Causal Structure from Event Sequences

Dual-Prior Augmented Decoding Network for Long Tail Distribution in HOI Detection

Position: What Can Large Language Models Tell Us about Time Series Analysis

Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyond

From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning

Learning for Disparity Estimation Through Feature Constancy

DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-To-Image Synthesis

On the Local Hessian in Back-propagation

Community Exploration: From Offline Optimization to Online Learning

Adaptive Influence Maximization with Myopic Feedback

Online Influence Maximization under Linear Threshold Model

Learning Causal Semantic Representation for Out-of-Distribution Prediction

R-Drop: Regularized Dropout for Neural Networks

Recovering Latent Causal Factor for Generalization to Distributional Shifts

Combinatorial Pure Exploration with Bottleneck Reward Function

Optimizing Information-theoretical Generalization Bound via Anisotropic Noise of SGLD

The Hardness Analysis of Thompson Sampling for Combinatorial Semi-bandits with Greedy Oracle

Tiered Reinforcement Learning: Pessimism in the Face of Uncertainty and Constant Regret

Feature-Proxy Transformer for Few-Shot Segmentation

Batch-Size Independent Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms or Independent Arms

Multivariate Time-Series Forecasting with Temporal Polynomial Graph Neural Networks

Does Momentum Change the Implicit Regularization on Separable Data?

Multi-Fidelity Multi-Armed Bandits Revisited

Closing the gap between the upper bound and lower bound of Adam's iteration complexity

Scalable Fair Influence Maximization

Inner Product-based Neural Network Similarity

Multi-Task Learning for Subspace Segmentation

Contextual Combinatorial Cascading Bandits

Dual Supervised Learning

Asynchronous Stochastic Gradient Descent with Delay Compensation

Towards Binary-Valued Gates for Robust LSTM Training

Thompson Sampling for Combinatorial Semi-Bandits