pith. sign in

Hongwu Peng

Identifiers

  • name variant Hongwu Peng 0.60 · backfill

Papers (31)

  1. Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs cs.AI · 2026 · author #8
  2. Complete-muE: Optimal Hyperparameter Transfer and Scaling for MoE Models cs.LG · 2026 · author #1
  3. DTop-p MoE: Sparsity-Controlled Dynamic Top-p MoE for Foundation Model Pre-training cs.AI · 2025 · author #2
  4. DR-CircuitGNN: Training Acceleration of Heterogeneous Circuit Graph Neural Network on GPUs cs.LG · 2025 · author #6
  5. Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning cs.AI · 2025 · author #2
  6. RankFlow: A Multi-Role Collaborative Reranking Workflow Utilizing Large Language Models cs.IR · 2025 · author #2
  7. RTop-K: Ultra-Fast Row-Wise Top-K Selection for Neural Network Acceleration on GPUs cs.DC · 2024 · author #3
  8. APEER: Automatic Prompt Engineering Enhances Large Language Model Reranking cs.AI · 2024 · author #2
  9. SSNet: A Lightweight Multi-Party Computation Scheme for Practical Privacy-Preserving Machine Learning Service in the Cloud cs.CR · 2024 · author #3
  10. Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate cs.LG · 2024 · author #3
  11. Zero-Space Cost Fault Tolerance for Transformer-based Language Models on ReRAM cs.LG · 2024 · author #5
  12. Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads cs.LG · 2024 · author #4
  13. MaxK-GNN: Extremely Fast GPU Kernel Design for Accelerating Graph Neural Networks Training cs.LG · 2023 · author #1
  14. Advanced Large Language Model (LLM)-Driven Verilog Development: Enhancing Power, Performance, and Area Optimization in Code Synthesis cs.LG · 2023 · author #4
  15. Evaluating Emerging AI/ML Accelerators: IPU, RDU, and NVIDIA/AMD GPUs cs.AR · 2023 · author #1
  16. LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inference cs.LG · 2023 · author #1
  17. Accel-GCN: High-Performance GPU Accelerator Design for Graph Convolution Networks cs.AR · 2023 · author #2
  18. AutoReP: Automatic ReLU Replacement for Fast Private Network Inference cs.CR · 2023 · author #1
  19. PASNet: Polynomial Architecture Search Framework for Two-party Computation-based Secure Neural Network Deployment cs.CR · 2023 · author #1
  20. RRNet: Towards ReLU-Reduced Neural Network for Two-party Computation Based Private Inference cs.CR · 2023 · author #1
  21. Dynamic Sparse Training via Balancing the Exploration-Exploitation Trade-off cs.LG · 2022 · author #4
  22. Aerial Manipulation Using a Novel Unmanned Aerial Vehicle Cyber-Physical System cs.RO · 2022 · author #2
  23. PolyMPCNet: Towards ReLU-free Neural Architecture Search in Two-party Computation Based Private Inference cs.CR · 2022 · author #1
  24. Towards Sparsification of Graph Neural Networks cs.LG · 2022 · author #1
  25. A Length Adaptive Algorithm-Hardware Co-design of Transformer on FPGA Through Sparse Attention and Dynamic Pipelining cs.LG · 2022 · author #1
  26. An Automatic and Efficient BERT Pruning for Edge AI Systems cs.CL · 2022 · author #4
  27. Accelerating Framework of Transformer by Hardware Design and Model Compression Co-Optimization cs.LG · 2021 · author #4
  28. Detecting Gender Bias in Transformer-based Models: A Case Study on BERT cs.CL · 2021 · author #2
  29. Optimizing FPGA-based Accelerator Design for Large-Scale Molecular Similarity Search cs.AR · 2021 · author #1
  30. Binary Complex Neural Network Acceleration on FPGA cs.LG · 2021 · author #1
  31. Improving DNN Fault Tolerance using Weight Pruning and Differential Crossbar Mapping for ReRAM-based Edge AI cs.LG · 2021 · author #10

Mentions

  • 2508.16769 #6 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2504.09772 #2 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2406.14449 #2 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2409.00822 #3 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2402.02769 #3 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2401.10774 #4 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2406.02629 #3 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2312.08656 #1 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2311.04417 #1 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2401.11664 #5 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2312.01022 #4 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2309.14331 #1 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2308.11825 #2 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2308.10134 #1 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2306.15513 #1 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2211.16667 #4 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2209.04766 #1 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2302.02292 #1 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2209.09424 #1 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2210.15632 #2 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2208.03646 #1 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2206.10461 #4 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2110.15733 #2 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2110.10030 #4 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2109.06355 #1 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2108.04811 #1 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2106.09166 #10 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2606.00726 #8 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2512.13996 #2 · arxiv_oai · confidence 0.70 Hongwu Peng
  • 2605.23893 #1 · arxiv_oai · confidence 0.70 Hongwu Peng

Frequent Coauthors