Hao Wang

Assistant Professor@Rutgers University·美国·OpenReview

研究方向

Bayesian Deep Learning · Data Mining · Machine Learning · Domain Adaptation · Graph Learning · Deep Learning · Recommender Systems · Probabilistic Methods

Hao Wang

TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning

Lost in the Middle: An Emergent Property from Information Retrieval Demands in LLMs

Visual Sparse Steering (VS2): Unsupervised Adaptation for Image Classification via Sparsity-Guided Steering Vectors

SSR: Socratic Self-Refine for Large Language Model Reasoning

CaSBRE: Causality-inspired Semi-supervised Biomedical Relation Extraction

Tracking the Feature Dynamics in LLM Training: A Mechanistic Study

Online Domain Indexing

When Does Multimodality Lead to Better Time Series Forecasting?

Reducing Hallucinations in Multimodal Large Language Models via Causal Fusion

Structured Visual Landscape: Generating Preferred Representations in Multi-modal Biological and Artificial Neural Networks

Toward Reliable Domain Adaptation under Continuous Spurious Shift

LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs

NetFormer: An interpretable model for recovering dynamical connectivity in neuronal population dynamics

PoGDiff: Product-of-Gaussians Diffusion Models for Imbalanced Text-to-Image Generation

Training-Free Bayesianization for Low-Rank Adapters of Large Language Models

Towards Domain Adaptive Neural Contextual Bandits

Implicit In-context Learning

On Calibration of LLM-based Guard Models for Reliable Content Moderation

GenVP: Generating Visual Puzzles with Contrastive Hierarchical VAEs

Effectively Steer LLM To Follow Preference via Building Confident Directions

PoGDiff: Product-of-Gaussians Diffusion Models for Imbalanced Text-to-Image Generation

Concept-Based Unsupervised Domain Adaptation

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models Via Visual Information Steering

Energy-Based Conceptual Diffusion Model

Domain Indexing Collaborative Filtering for Recommender System

PRUC & Play: Probabilistic Residual User Clustering for Recommender Systems

Taming Continuous Spurious Shift in Domain Adaptation