Ruizhong Qiu

PLANETALIGN: A Comprehensive Python Library for Benchmarking Network Alignment

Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum

Inference Scaling of LLM Ensembling: Bridging Token Spaces with Token Translation

Influence-Preserving Proxies for Gradient-Based Data Selection in LLM FineTuning

Graph homophily booster: Reimagining the role of discrete features in heterophilic graph learning

Geometri-Disentangelment Unlearning

Rethinking Fair Anomaly Detection From The Group Imbalance Perspective

Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluation

ReMix: Reinforcement Routing for Mixtures of LoRAs in LLM Finetuning

DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts

WAPITI: A Watermark for Finetuned Open-Source LLMs

TRQA: Time Series Reasoning Question And Answering Benchmark

Moralise: A Structured Benchmark for Moral Alignment in Visual Language Models

Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning

Graph Data Selection for Domain Adaptation: A Model-Free Approach

How efficient is LLM-generated code? A rigorous & high-standard benchmark

Ask, and it shall be given: On the Turing completeness of prompting

Fair Anomaly Detection For Imbalanced Groups

Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting

Robust Watermarking for Diffusion Models: A Unified Multi-Dimensional Recipe

WAPITI: A Watermark for Finetuned Open-Source LLMs