PPL
Hao Wang
Papers (19)
Reinforcement Learning with Robust Rubric RewardsiLoRA: Bayesian Low-Rank Adaptation with Latent Interaction Graphs for Microbiome DiagnosisMACReD: A Multi-Agent Collaborative Reasoning Framework for Reaction Diagram ParsingOphIn-500K: Curating Web-Scale Visual Instructions for Scaling Ophthalmic Multimodal Large Language ModelsDeep ZakaiJ: Structured Filtering for Jump-Diffusion Time Series ForecastingHybrid Kolmogorov-Arnold Network and XGBoost Framework for Week-Ahead Price Forecasting in Australia's National Electricity MarketIncentive-Aligned Vehicle-to-Vehicle Energy Trading via Nash-Integrated Multi-Agent Reinforcement LearningFedSDR: Federated Self-Distillation with RectificationSNLP: Layer-Parallel Inference via Structured Newton CorrectionsPrivacy-Preserving Generation Fraud Detection for Distributed Photovoltaic Systems: A Solar Irradiance-Fused Federated Learning FrameworkTFZ-Tree: An Ultra-Lightweight Waveform Classification Framework for Resource-Constrained DevicesDo Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJackStepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement LearningOffline Policy Evaluation for Manipulation Policies via Discounted Liveness FormulationBabelDOC: Better Layout-Preserving PDF Translation via Intermediate RepresentationLoopVLA: Learning Sufficiency in Recurrent Refinement for Vision-Language-Action ModelsBeyond the All-in-One Agent: Benchmarking Role-Specialized Multi-Agent Collaboration in Enterprise WorkflowsSparse Autoencoders as Plug-and-Play Firewalls for Adversarial Attack Detection in VLMsEfficient Serving for Dynamic Agent Workflows with Prediction-based KV-Cache Management