Jindong Wang

Assistant Professor@William & Mary·美国·OpenReview

研究方向

large language models · AI for social sciences · robust/trustworthy/responsible ML · domain generalization · transfer learning · semi-supervised learning · federated learning · domain adaptation · sensor-based human activity recognition

Jindong Wang

KnowledgeSmith: Uncovering Knowledge Updating in LLMs with Model Editing and Unlearning

SparseEval: Efficient Evaluation of Large Language Models by Sparse Optimization

Harnessing Temporal Databases for Systematic Evaluation of Factual Time-Sensitive Question-Answering in LLMs

CAReDiO: Enhancing Cultural Alignment of LLM via Representativeness and Distinctiveness Guided Data Optimization

CultureVLM: Characterizing and Improving Cultural Understanding of Vision-Language Models

CAT-VIDEO: CORRUPTION-AWARE TRAINING FOR ROBUST VIDEO DIFFUSION MODELS

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Resource-Constrained Decision Making and Revision

On the Diversity of Synthetic Data and its Impact on Training Large Language Models

RewardAnything: Generalizable Principle-Following Reward Models

On alignment of unified multimodal large language models

Irrelevant Context Helps: Understanding the Impact of Context in Large Language Models

From Pretraining to Pathology: How Noise Leads to Catastrophic Inheritance in Medical Models

Realistic Evaluation of Deep Partial-Label Learning Algorithms

On Fairness of Unified Multimodal Large Language Model for Image Generation

Personalized Safety in LLMs: A Benchmark and A Planning-Based Agent Approach

Exposing and Patching the Flaws of Large Language Models in Social Character Simulation

Masked Autoencoders Are Effective Tokenizers for Diffusion Models

CycleResearcher: Improving Automated Research via Automated Review

StringLLM: Understanding the String Processing Capability of Large Language Models

Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist

Automatic Dataset Construction (ADC): Sample Collection, Data Curation, and Beyond

On the Diversity of Synthetic Data and its Impact on Training Large Language Models

Topology-aware Neural Flux Prediction Guided by Physics

Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

MentalArena: Self-play Training of Language Models for Diagnosis and Treatment of Mental Health Disorders

Can I Understand What I Create? Self-Knowledge Evaluation of Large Language Models

On the Robustness of Vision-Language Models Against Distractions