Hanghang Tong
YOU?
Author Swipe
View article: Few-Shot Knowledge Graph Completion via Transfer Knowledge from Similar Tasks
Few-Shot Knowledge Graph Completion via Transfer Knowledge from Similar Tasks Open
View article: Fine-Grained Graph Rationalization
Fine-Grained Graph Rationalization Open
View article: ClimateBench-M: A Multi-Modal Climate Data Benchmark with a Simple Generative Method
ClimateBench-M: A Multi-Modal Climate Data Benchmark with a Simple Generative Method Open
View article: PyG-SSL: A Graph Self-Supervised Learning Toolkit
PyG-SSL: A Graph Self-Supervised Learning Toolkit Open
View article: <scp>InterFormer:</scp> Effective Heterogeneous Interaction Learning for Click-Through Rate Prediction
<span>InterFormer:</span> Effective Heterogeneous Interaction Learning for Click-Through Rate Prediction Open
View article: Sparse Autoencoders in Collaborative Filtering Enhanced LLM-based Recommender Systems
Sparse Autoencoders in Collaborative Filtering Enhanced LLM-based Recommender Systems Open
View article: Continual Recommender Systems
Continual Recommender Systems Open
View article: Seeing but Not Believing: Probing the Disconnect Between Visual Attention and Answer Correctness in VLMs
Seeing but Not Believing: Probing the Disconnect Between Visual Attention and Answer Correctness in VLMs Open
Vision-Language Models (VLMs) achieve strong results on multimodal tasks such as visual question answering, yet they can still fail even when the correct visual evidence is present. In this work, we systematically investigate whether these…
View article: Hephaestus: Mixture Generative Modeling with Energy Guidance for Large-scale QoS Degradation
Hephaestus: Mixture Generative Modeling with Energy Guidance for Large-scale QoS Degradation Open
We study the Quality of Service Degradation (QoSD) problem, in which an adversary perturbs edge weights to degrade network performance. This setting arises in both network infrastructures and distributed ML systems, where communication qua…
View article: Imposing the 'Right' Structural Constraints in High-Dimensional Regression
Imposing the 'Right' Structural Constraints in High-Dimensional Regression Open
View article: Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum Open
Supervised fine-tuning (SFT) is the standard approach for post-training large language models (LLMs), yet it often shows limited generalization. We trace this limitation to its default training objective: negative log likelihood (NLL). Whi…
View article: Graph Homophily Booster: Rethinking the Role of Discrete Features on Heterophilic Graphs
Graph Homophily Booster: Rethinking the Role of Discrete Features on Heterophilic Graphs Open
Graph neural networks (GNNs) have emerged as a powerful tool for modeling graph-structured data. However, existing GNNs often struggle with heterophilic graphs, where connected nodes tend to have dissimilar features or labels. While numero…
View article: PowerGrow: Feasible Co-Growth of Structures and Dynamics for Power Grid Synthesis
PowerGrow: Feasible Co-Growth of Structures and Dynamics for Power Grid Synthesis Open
Modern power systems are becoming increasingly dynamic, with changing topologies and time-varying loads driven by renewable energy variability, electric vehicle adoption, and active grid reconfiguration. Despite these changes, publicly ava…
View article: Learning to Slice: Self-Supervised Interpretable Hierarchical Representation Learning with Graph Auto-Encoder Tree
Learning to Slice: Self-Supervised Interpretable Hierarchical Representation Learning with Graph Auto-Encoder Tree Open
View article: Flow Matching Meets Biology and Life Science: A Survey
Flow Matching Meets Biology and Life Science: A Survey Open
Over the past decade, advances in generative modeling, such as generative adversarial networks, masked autoencoders, and diffusion models, have significantly transformed biological research and discovery, enabling breakthroughs in molecule…
View article: Embracing Plasticity: Balancing Stability and Plasticity in Continual Recommender Systems
Embracing Plasticity: Balancing Stability and Plasticity in Continual Recommender Systems Open
View article: Continual Recommender Systems
Continual Recommender Systems Open
Modern recommender systems operate in uniquely dynamic settings: user interests, item pools, and popularity trends shift continuously, and models must adapt in real time without forgetting past preferences. While existing tutorials on cont…
View article: A Weakly Supervised Transformer for Rare Disease Diagnosis and Subphenotyping from EHRs with Pulmonary Case Studies
A Weakly Supervised Transformer for Rare Disease Diagnosis and Subphenotyping from EHRs with Pulmonary Case Studies Open
Rare diseases affect an estimated 300-400 million people worldwide, yet individual conditions remain underdiagnosed and poorly characterized due to their low prevalence and limited clinician familiarity. Computational phenotyping offers a …
View article: Saffron-1: Safety Inference Scaling
Saffron-1: Safety Inference Scaling Open
Existing safety assurance research has primarily focused on training-phase alignment to instill safe behaviors into LLMs. However, recent studies have exposed these methods' susceptibility to diverse jailbreak attacks. Concurrently, infere…
View article: From Images to Signals: Are Large Vision Models Useful for Time Series Analysis?
From Images to Signals: Are Large Vision Models Useful for Time Series Analysis? Open
Transformer-based models have gained increasing attention in time series research, driving interest in Large Language Models (LLMs) and foundation models for time series analysis. As the field moves toward multi-modality, Large Vision Mode…
View article: PLANETALIGN: A Comprehensive Python Library for Benchmarking Network Alignment
PLANETALIGN: A Comprehensive Python Library for Benchmarking Network Alignment Open
Network alignment (NA) aims to identify node correspondence across different networks and serves as a critical cornerstone behind various downstream multi-network learning tasks. Despite growing research in NA, there lacks a comprehensive …
View article: Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting
Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting Open
Time-series forecasting plays a critical role in many real-world applications. Although increasingly powerful models have been developed and achieved superior results on benchmark datasets, through a fine-grained sample-level inspection, w…
View article: MORALISE: A Structured Benchmark for Moral Alignment in Visual Language Models
MORALISE: A Structured Benchmark for Moral Alignment in Visual Language Models Open
Warning: This paper contains examples of harmful language and images. Reader discretion is advised. Recently, vision-language models have demonstrated increasing influence in morally sensitive domains such as autonomous driving and medical…
View article: Joint Optimal Transport and Embedding for Network Alignment
Joint Optimal Transport and Embedding for Network Alignment Open
View article: ResMoE: Space-efficient Compression of Mixture of Experts LLMs via Residual Restoration
ResMoE: Space-efficient Compression of Mixture of Experts LLMs via Residual Restoration Open
Mixture-of-Experts (MoE) Transformer, the backbone architecture of multiple phenomenal language models, leverages sparsity by activating only a fraction of model parameters for each input token. The sparse structure, while allowing constan…
View article: Generalizable Recommender System During Temporal Popularity Distribution Shifts
Generalizable Recommender System During Temporal Popularity Distribution Shifts Open
View article: Joint Optimal Transport and Embedding for Network Alignment
Joint Optimal Transport and Embedding for Network Alignment Open
Network alignment, which aims to find node correspondence across different networks, is the cornerstone of various downstream multi-network and Web mining tasks. Most of the embedding-based methods indirectly model cross-network node relat…
View article: Enhancing biomedical named entity recognition with parallel boundary detection and category classification
Enhancing biomedical named entity recognition with parallel boundary detection and category classification Open
View article: Harnessing Vision Models for Time Series Analysis: A Survey
Harnessing Vision Models for Time Series Analysis: A Survey Open
Time series analysis has witnessed the inspiring development from traditional autoregressive models, deep learning models, to recent Transformers and Large Language Models (LLMs). Efforts in leveraging vision models for time series analysi…
View article: Language in the Flow of Time: Time-Series-Paired Texts Weaved into a Unified Temporal Narrative
Language in the Flow of Time: Time-Series-Paired Texts Weaved into a Unified Temporal Narrative Open
While many advances in time series models focus exclusively on numerical data, research on multimodal time series, particularly those involving contextual textual information commonly encountered in real-world scenarios, remains in its inf…