pith. sign in

Pengfei Hu

Identifiers

  • name variant Pengfei Hu 0.60 · backfill

Papers (56)

  1. Conflict-Aware Retriever Editing for Knowledge Injection Attacks on LLM-Based RAG Systems cs.CR · 2026 · author #5
  2. Training Prompt Matters: State-Adaptive Optimization for Robust Fine-Tuning cs.CL · 2026 · author #6
  3. PEARL: Training Socratic Tutors with Pedagogically Aligned Reinforcement Learning cs.LG · 2026 · author #4
  4. VUDA: Breaking CUDA-Vulkan Isolation for Spatial Sharing of Compute and Graphics on the Same GPU cs.OS · 2026 · author #2
  5. S-GRPO: Unified Post-Training for Large Vision-Language Models cs.LG · 2026 · author #7
  6. Exploring Accurate and Transparent Domain Adaptation in Predictive Healthcare via Concept-Grounded Orthogonal Inference cs.LG · 2026 · author #1
  7. An Empirical Study on Virtual Reality Software Security Weaknesses cs.CR · 2025 · author #6
  8. Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding cs.SD · 2025 · author #7
  9. Enhancing the Geometric Problem-Solving Ability of Multimodal LLMs via Symbolic-Neural Integration cs.CL · 2025 · author #3
  10. MMC: Iterative Refinement of VLM Reasoning via MCTS-based Multimodal Critique cs.MM · 2025 · author #3
  11. RF Sensing Security and Malicious Exploitation: A Comprehensive Survey cs.HC · 2025 · author #7
  12. PRM-BAS: Enhancing Multimodal Reasoning through PRM-guided Beam Annealing Search cs.MM · 2025 · author #1
  13. Video SimpleQA: Towards Factuality Evaluation in Large Video Language Models cs.CV · 2025 · author #2
  14. Skeleton and Font Generation Network for Zero-shot Chinese Character Generation cs.CV · 2025 · author #6
  15. Joint Knowledge Editing for Information Enrichment and Probability Promotion cs.CL · 2024 · author #6
  16. RFL: Simplifying Chemical Structure Recognition with Ring-Free Language cs.CV · 2024 · author #4
  17. MPLite: Multi-Aspect Pretraining for Mining Clinical Health Records cs.LG · 2024 · author #2
  18. LLM-NEO: Parameter Efficient Knowledge Distillation for Large Language Models cs.CL · 2024 · author #4
  19. Bridging Stepwise Lab-Informed Pretraining and Knowledge-Guided Learning for Diagnostic Reasoning cs.LG · 2024 · author #1
  20. DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking Head Video Generation cs.CV · 2024 · author #5
  21. t-READi: Transformer-Powered Robust and Efficient Multimodal Inference for Autonomous Driving cs.CV · 2024 · author #1
  22. See then Tell: Enhancing Key Information Extraction with Vision Grounding cs.CV · 2024 · author #3
  23. UniTabNet: Bridging Vision and Language Models for Enhanced Table Structure Recognition cs.CV · 2024 · author #3
  24. DocMamba: Efficient Document Pre-training with State Space Model cs.CL · 2024 · author #1
  25. A Practical Trigger-Free Backdoor Attack on Neural Networks cs.CR · 2024 · author #4
  26. Exploring Audio-Visual Information Fusion for Sound Event Localization and Detection In Low-Resource Realistic Scenarios eess.AS · 2024 · author #5
  27. SRFUND: A Multi-Granularity Hierarchical Structure Reconstruction Benchmark in Form Understanding cs.CL · 2024 · author #7
  28. SEMv3: A Fast and Robust Approach to Table Separation Line Detection cs.CV · 2024 · author #3
  29. A Poisson-Gamma Dynamic Factor Model with Time-Varying Transition Dynamics cs.LG · 2024 · author #5
  30. Bidirectional Trained Tree-Structured Decoder for Handwritten Mathematical Expression Recognition cs.CV · 2023 · author #3
  31. Decoupling and Interacting Multi-Task Learning Network for Joint Speech and Accent Recognition cs.SD · 2023 · author #4
  32. Incentivizing Massive Unknown Workers for Budget-Limited Crowdsensing: From Off-Line and On-Line Perspectives cs.AI · 2023 · author #4
  33. Hierarchical Audio-Visual Information Fusion with Multi-label Joint Decoding for MER 2023 eess.AS · 2023 · author #10
  34. Speech2Lip: High-fidelity Speech to Lip Generation by Learning from a Short Video cs.CV · 2023 · author #2
  35. Count, Decode and Fetch: A New Approach to Handwritten Chinese Character Error Correction cs.CV · 2023 · author #1
  36. HRDoc: Dataset and Baseline Method Toward Hierarchical Reconstruction of Document Structures cs.CL · 2023 · author #3
  37. SEMv2: Table Separation Line Detection Based on Instance Segmentation cs.CV · 2023 · author #2
  38. Multimodal Tree Decoder for Table of Contents Extraction in Document Images cs.CV · 2022 · author #1
  39. AccEar: Accelerometer Acoustic Eavesdropping with Unconstrained Vocabulary cs.SD · 2022 · author #1
  40. Federated Learning Hyper-Parameter Tuning from a System Perspective cs.LG · 2022 · author #4
  41. Learning Audio-Visual embedding for Person Verification in the Wild cs.CV · 2022 · author #7
  42. High Speed Rotation Estimation with Dynamic Vision Sensors cs.CV · 2022 · author #4
  43. Defensive Patches for Robust Recognition in the Physical World cs.CV · 2022 · author #3
  44. Linguistic-Acoustic Similarity Based Accent Shift for Accent Recognition cs.SD · 2022 · author #6
  45. Leveraging Phone Mask Training for Phonetic-Reduction-Robust E2E Uyghur Speech Recognition cs.SD · 2022 · author #2
  46. MFA-Conformer: Multi-scale Feature Aggregation Conformer for Automatic Speaker Verification cs.SD · 2022 · author #5
  47. Iota: A Framework for Analyzing System-Level Security of IoTs cs.CR · 2022 · author #4
  48. PM-MMUT: Boosted Phone-Mask Data Augmentation using Multi-Modeling Unit Training for Phonetic-Reduction-Robust E2E Speech Recognition cs.SD · 2021 · author #2
  49. VRM-Phase I VKW system description of long-short video customizable keyword wakeup challenge cs.SD · 2021 · author #4
  50. Membership Inference Attacks Against Recommender Systems cs.CR · 2021 · author #6
  51. Dual Synchronous Generator: Inertial Current Source based Grid-Forming Solution for VSC eess.SY · 2021 · author #3
  52. Blockchain Meets COVID-19: A Framework for Contact Information Sharing and Risk Notification System cs.CR · 2020 · author #7
  53. IoTGaze: IoT Security Enforcement via Wireless Context Analysis cs.CR · 2020 · author #5
  54. Shielding Collaborative Learning: Mitigating Poisoning Attacks through Client-Side Detection cs.CR · 2019 · author #7
  55. FlowIntent: Detecting Privacy Leakage from User Intention to Network Traffic Mapping cs.CR · 2016 · author #5
  56. Trust Exploitation and Attention Competition: A Game Theoretical Model cs.GT · 2016 · author #4

Mentions

  • 2409.19573 #3 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2503.18923 #2 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2507.17324 #6 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2505.15380 #7 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2504.12773 #3 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2410.19955 #1 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2504.11009 #3 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2504.10969 #7 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2504.10222 #1 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2410.13726 #5 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2411.06839 #4 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2409.11887 #1 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2412.07594 #4 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2501.08062 #6 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2412.17872 #6 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2410.09747 #1 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2411.11161 #2 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2409.13148 #3 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2408.11444 #4 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2406.15160 #5 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2406.08757 #7 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2402.16297 #5 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2405.11862 #3 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2303.04384 #2 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2309.12113 #4 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2401.00435 #3 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2311.07062 #4 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2309.07925 #10 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2309.04814 #2 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2307.16253 #1 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2303.13839 #3 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2212.02896 #1 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2212.01042 #1 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2211.13656 #4 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2203.15249 #5 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2209.04093 #7 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2209.02205 #4 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2112.06721 #2 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2204.03398 #6 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2204.06213 #3 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2204.00819 #2 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2202.02506 #4 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2007.10529 #7 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2110.15316 #4 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2109.08045 #6 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2107.01805 #3 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2006.15827 #5 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 1910.13111 #7 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 1604.07139 #4 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 1605.04025 #5 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2606.18310 #5 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2602.12542 #1 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2606.01967 #6 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2605.29582 #4 · arxiv_oai · confidence 0.70 Pengfei Hu
  • 2604.16557 #7 · backfill · confidence 0.70 Pengfei Hu

Frequent Coauthors