Ji-Rong Wen

papers

1,606

total citations

papers (24)

Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

ECCV 2024arXiv

101

citations

COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval

CVPR 2022arXiv

citations

Evaluating and Improving Tool-Augmented Computation-Intensive Math Reasoning

NEURIPS 2023arXiv

citations

Dynamic Prompt Optimizing for Text-to-Image Generation

CVPR 2024arXiv

citations

Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers

AAAI 2025arXiv

citations

MemSim: A Bayesian Simulator for Evaluating Memory of LLM-based Personal Assistants

NEURIPS 2025arXiv

citations

Unlocking the Power of Spatial and Temporal Information in Medical Multimodal Pre-training

ICML 2024arXiv

citations

One Token Can Help! Learning Scalable and Pluggable Virtual Tokens for Retrieval-Augmented Large Language Models

AAAI 2025arXiv

citations

Your Career Path Matters in Person-Job Fit

AAAI 2024

citations

Enhancing Reward Models for High-quality Image Generation: Beyond Text-Image Alignment

ICCV 2025arXiv

citations

Regulatory DNA Sequence Design with Reinforcement Learning

ICLR 2025arXiv

citations

Reward Imputation with Sketching for Contextual Batched Bandits

NEURIPS 2023arXiv

citations

MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval

NEURIPS 2025arXiv

citations

Irrational Complex Rotations Empower Low-bit Optimizers

NEURIPS 2025arXiv

citations

REASONER: An Explainable Recommendation Dataset with Comprehensive Labeling Ground Truths

NEURIPS 2023

citations

Compressed Video Contrastive Learning

NEURIPS 2021

citations

Log-Polar Space Convolution Layers

NEURIPS 2022

citations

Debiased, Longitudinal and Coordinated Drug Recommendation through Multi-Visit Clinic Records

NEURIPS 2022

citations

Toward Verifiable Instruction-Following Alignment for Retrieval Augmented Generation

AAAI 2025

citations

Ji-Rong Wen

papers (24)

Counterfactual VQA: A Cause-Effect Look at Language Bias

Learning To Answer Questions in Dynamic Audio-Visual Scenarios

WebThinker: Empowering Large Reasoning Models with Deep Research Capability

Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited

Scalable Graph Neural Networks via Bidirectional Propagation

Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval

Evaluating and Improving Tool-Augmented Computation-Intensive Math Reasoning

Dynamic Prompt Optimizing for Text-to-Image Generation

Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers

MemSim: A Bayesian Simulator for Evaluating Memory of LLM-based Personal Assistants

Unlocking the Power of Spatial and Temporal Information in Medical Multimodal Pre-training

One Token Can Help! Learning Scalable and Pluggable Virtual Tokens for Retrieval-Augmented Large Language Models

Your Career Path Matters in Person-Job Fit

Enhancing Reward Models for High-quality Image Generation: Beyond Text-Image Alignment

Regulatory DNA Sequence Design with Reinforcement Learning

Reward Imputation with Sketching for Contextual Batched Bandits

MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval

Irrational Complex Rotations Empower Low-bit Optimizers

REASONER: An Explainable Recommendation Dataset with Comprehensive Labeling Ground Truths

Compressed Video Contrastive Learning

Log-Polar Space Convolution Layers

Debiased, Longitudinal and Coordinated Drug Recommendation through Multi-Visit Clinic Records

Toward Verifiable Instruction-Following Alignment for Retrieval Augmented Generation

papers (24)

Counterfactual VQA: A Cause-Effect Look at Language Bias

Learning To Answer Questions in Dynamic Audio-Visual Scenarios

WebThinker: Empowering Large Reasoning Models with Deep Research Capability

Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited

Scalable Graph Neural Networks via Bidirectional Propagation

Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models

COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval

Evaluating and Improving Tool-Augmented Computation-Intensive Math Reasoning

Dynamic Prompt Optimizing for Text-to-Image Generation

Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers

MemSim: A Bayesian Simulator for Evaluating Memory of LLM-based Personal Assistants

Unlocking the Power of Spatial and Temporal Information in Medical Multimodal Pre-training

One Token Can Help! Learning Scalable and Pluggable Virtual Tokens for Retrieval-Augmented Large Language Models

Your Career Path Matters in Person-Job Fit

Enhancing Reward Models for High-quality Image Generation: Beyond Text-Image Alignment

Regulatory DNA Sequence Design with Reinforcement Learning

Reward Imputation with Sketching for Contextual Batched Bandits

MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval

Irrational Complex Rotations Empower Low-bit Optimizers

REASONER: An Explainable Recommendation Dataset with Comprehensive Labeling Ground Truths

Compressed Video Contrastive Learning

Log-Polar Space Convolution Layers

Debiased, Longitudinal and Coordinated Drug Recommendation through Multi-Visit Clinic Records

Toward Verifiable Instruction-Following Alignment for Retrieval Augmented Generation