Fan Yang

The paper proposes PROVFUSION, a multi-view fusion framework that integrates anomaly signals from attribute, structure, and causality views to overcome the limitations of single node- or edge-centric provenance-based intrusion detection.

The paper proposes PRAETORIAN, a novel defense mechanism for Graph Neural Networks (GNNs) that targets the intrinsic structural requirements of backdoor attacks, significantly reducing the attack success rate while maintaining high clean accuracy.

VCap introduces a novel Witness-Adjudicator reward mechanism that provides highly precise, factually grounded feedback for visual captioning, enabling state-of-the-art performance in RL-trained multimodal models.

VCap introduces a novel Witness-Adjudicator reward mechanism that provides highly precise, factually grounded feedback for visual captioning, enabling state-of-the-art performance in RL-trained multimodal models.

The paper proposes OneReason, a framework that enhances the reasoning capability of generative recommendation models by focusing on improving item perception and structuring user behavior into coherent latent interests.

The paper proposes OneReason, a framework that enhances the reasoning capability of generative recommendation models by focusing on improving item perception and structuring user behavior into coherent latent interests.

The paper proposes OneReason, a framework that enhances the reasoning capability of generative recommendation models by focusing on improving item perception and structuring user behavior into coherent latent interests.

This paper investigates and quantifies API key leakage in iOS applications that use large language models.

AwakeForest is an interactive platform for large-scale forest imagery analysis that integrates model-assisted inference, automatic annotation, and human-in-the-loop refinement.

This paper introduces Arachne, a framework for efficient Text-to-Video model training at scale, reducing iteration time by up to 65% over leading frameworks.

MagicSelector is a framework for tool retrieval in agents using counterfactual task decomposition, progressive reranking, and dynamic Top-K.

TileSight is a tile-centric performance-modeling tool that predicts single-GPU kernel latency and cache hit rates with low error, outperforming state-of-the-art baselines and transferring well across architectures.

This paper proposes a federated longitudinal-survival modeling framework for collaborative system failure prognostics, enabling decentralized estimation of interval-specific failure hazards, reliability curves, and system remaining useful life.

Argus is a persistent, self-evolving runtime system that achieves better long-horizon reasoning results than Direct Copilot in seven GPT-5.5 benchmark arenas, with improvements in solve-input tokens, active workflow time, and verification-gated self-evolution.

This paper proposes AirFlow, a pollutant-aware dual-stream framework for accurate air quality forecasting using a statistic-guided normalization routing mechanism and a hierarchical dual-stream state model.

One clear sentence describing what this paper does