publications
(*) denote for equal contribution.
2025
-
- ICLR WSTrajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-TrainingICLR Workshop on Open Science for Foundation Models, 2025
- ICLR WSOutsourced Diffusion Sampling: Efficient Posterior Inference in Latent Spaces of Generative ModelsICLR workshop on Deep Generative Model in Machine Learning, 2025
- ICLRAdaptive Teachers for Amortized SamplersInternational Conference on Learning Representations., 2025
- ICLRGenerative Flows on Synthetic Pathway for Drug DesignInternational Conference on Learning Representations. Previously presented at NeurIPS AIDrugX Workshop, 2025
- ICLRMOFFlow: Flow Matching for Structure Prediction of Metal-Organic FrameworksInternational Conference on Learning Representations. Previously presented at NeurIPS AIDrugX Workshop, 2025
- ICLRLearning Diverse Attacks on Large Language Models for Robust Red-teaming and Safety TuningInternational Conference on Learning Representations. Previously presented at NeurIPS Redteaming Workshop, 2025
2024
- TMLRDecoupled Sequence and Structure Generation for Realistic Antibody DesignTransactions on Machine Learning Research, 2024
- NeurIPS WSChiplet Placement and Routing Optimization: A Novel Benchmark and Neural SolverNeurIPS Workshop on Machine Learning for Systems, 2024
- NeurIPSPessimistic Backward Policy for GFlowNetsAdvances in Neural Information Processing Systems, 2024
2023
- NeurIPS WSRl4co: an Extensive Reinforcement Learning for Combinatorial Optimization BenchmarkNeurIPS Workshop on New Frontiers in Graph Learning, 2023
- Appl. Intell.Temporal enhanced inductive graph knowledge tracingApplied Intelligence, 2023
- IEEE TransactionBayesian Exploration Imitation Learning-Based Contextual via Design Optimization Method of PAM-4-Based High-Speed Serial LinkIEEE Transactions on Electromagnetic Compatibility, 2023
- IEEE TransactionDeep Reinforcement Learning-based Optimal and Fast Hybrid Equalizer Design Method for High Bandwidth Memory (HBM) ModuleIEEE Transactions on Components, Packaging and Manufacturing Technology, 2023
- NeurIPSBootstrapped Training of Score-Conditioned Generator for Offline Design of Biological SequencesAdvances in Neural Information Processing Systems, 2023
- ICMLMeta-SAGE: A Scale Meta-Learning Scheduled Adaptation with Guided Exploration for Large Scale Combinatorial OptimizationInternational Conference on Machine Learning, 2023
- ICMLDevFormer: A Symmetric Transformer for Context-Aware Device PlacementInternational Conference on Machine Learning, 2023
2022
- NeurIPS WSNeural Coarsening Process for Multi-level Graph Combinatorial OptimizationIn NeurIPS Workshop on New Frontiers in Graph Learning, 2022
- DesignConData-Efficient Machine Learning Method for Hardware Routing: Signal Integrity Demonstration to 2PDC and PCIe 6.0In DesignCon, 2022
- IEEE TransactionTransformer Network-based Reinforcement Learning Method for Power Distribution Network (PDN) Optimization of High Bandwidth Memory (HBM)IEEE Transactions on Microwave Theory and Techniques, 2022
- IEEE TransactionThermal and Signal Integrity Co-Design and Verification of Embedded Cooling Structure with Thermal Transmission Line (ECS-TTL) for High Bandwidth Memory ModuleIEEE Transactions on Components, Packaging and Manufacturing Technology, 2022
2021
- DesignConNeural Language Model Enables Extremely Fast and Robust Routing on InterposerIn DesignCon, 2021
- IEEE TransactionReinforcement-Learning-Based Signal Integrity Optimization and Analysis of a Scalable 3-D X-Point Array StructureIEEE Transactions on Components, Packaging and Manufacturing Technology, 2021