pith. sign in

Hang Su

Identifiers

  • name variant Hang Su 0.60 · backfill

Papers (54)

  1. SpeakerCard-1M: An Evidence-Grounded Speaker Card Corpus for In-the-Wild Speaker Verification eess.AS · 2026 · author #6
  2. WALL-WM: Carving World Action Modeling at the Event Joints cs.RO · 2026 · author #28
  3. Wall-OSS-0.5 Technical Report cs.RO · 2026 · author #23
  4. RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations cs.SE · 2026 · author #4
  5. Reducing Linguistic Hallucination in LM-Based Speech Enhancement via Noise-Invariant Acoustic-Semantic Distillation eess.AS · 2026 · author #3
  6. Skills-Coach: A Self-Evolving Skill Optimizer via Training-Free GRPO cs.CL · 2026 · author #7
  7. Listening with Time: Precise Temporal Awareness for Long-Form Audio Understanding eess.AS · 2026 · author #2
  8. Match-Any-Events: Zero-Shot Motion-Robust Feature Matching Across Wide Baselines for Event Cameras cs.CV · 2026 · author #2
  9. PolarMAE: Efficient Fetal Ultrasound Pre-training via Semantic Screening and Polar-Guided Masking cs.CV · 2026 · author #3
  10. CoPA: Benchmarking Personalized Question Answering with Data-Informed Cognitive Factors cs.CL · 2026 · author #1
  11. LCO: LLM-based Constraint Optimization for Safer Agentic LLMs in Real-world Tasks cs.CL · 2026 · author #5
  12. Borderless Long Speech Synthesis cs.SD · 2026 · author #11
  13. MePo: Meta Post-Refinement for Rehearsal-Free General Continual Learning cs.AI · 2026 · author #6
  14. Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection cs.LG · 2026 · author #5
  15. Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation cs.CV · 2026 · author #4
  16. Break Me If You Can: Self-Jailbreaking of Aligned LLMs via Lexical Insertion Prompting cs.CL · 2026 · author #2
  17. TimeColor: Flexible Reference Colorization via Temporal Concatenation cs.CV · 2026 · author #5
  18. Motus: A Unified Latent Action World Model cs.CV · 2025 · author #15
  19. Red Teaming Large Reasoning Models cs.CR · 2025 · author #8
  20. DiffusionNFT: Online Diffusion Reinforcement with Forward Process cs.LG · 2025 · author #7
  21. Vidar: Embodied Video Diffusion Model for Generalist Manipulation cs.LG · 2025 · author #7
  22. AnyPos: Automated Task-Agnostic Actions for Bimanual Manipulation cs.CV · 2025 · author #7
  23. Exploring the Secondary Risks of Large Language Models cs.LG · 2025 · author #7
  24. GLEAN: Active Generalized Category Discovery with Diverse LLM Feedback cs.CL · 2025 · author #7
  25. RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation cs.RO · 2024 · author #8
  26. Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection cs.CV · 2023 · author #10
  27. DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection cs.CV · 2022 · author #5
  28. Boosting Generative Models by Leveraging Cascaded Meta-Models cs.LG · 2019 · author #2
  29. Pixel-Adaptive Convolutional Neural Networks cs.CV · 2019 · author #1
  30. Efficient Decision-based Black-box Adversarial Attacks on Face Recognition cs.CV · 2019 · author #2
  31. Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks cs.CV · 2019 · author #3
  32. Reward Shaping via Meta-Learning cs.LG · 2019 · author #4
  33. Towards Interpretable Deep Neural Networks by Leveraging Adversarial Examples cs.LG · 2019 · author #3
  34. Analyzing the Noise Robustness of Deep Neural Networks cs.LG · 2018 · author #3
  35. Deep Structured Generative Models cs.LG · 2018 · author #4
  36. Open Logo Detection Challenge cs.CV · 2018 · author #1
  37. Robust and Efficient Graph Correspondence Transfer for Person Re-identification cs.CV · 2018 · author #4
  38. Graph Correspondence Transfer for Person Re-identification cs.CV · 2018 · author #4
  39. Scalable Deep Learning Logo Detection cs.CV · 2018 · author #1
  40. Sparse Adversarial Perturbations for Videos cs.CV · 2018 · author #3
  41. SPLATNet: Sparse Lattice Networks for Point Cloud Processing cs.CV · 2018 · author #1
  42. Understanding Human Behaviors in Crowds by Imitating the Decision-Making Process cs.CV · 2018 · author #2
  43. Learning to Write Stylized Chinese Characters by Reading a Handful of Examples cs.CV · 2017 · author #4
  44. Incorporating External Knowledge to Answer Open-Domain Visual Questions with Dynamic Memory Networks cs.CV · 2017 · author #2
  45. Boosting Adversarial Attacks with Momentum cs.LG · 2017 · author #4
  46. End-to-end Face Detection and Cast Grouping in Movies Using Erd\H{o}s-R\'{e}nyi Clustering cs.CV · 2017 · author #2
  47. Towards Interpretable Deep Neural Networks by Leveraging Adversarial Examples cs.CV · 2017 · author #2
  48. Learning Accurate Low-Bit Deep Neural Networks with Stochastic Quantization cs.CV · 2017 · author #6
  49. SAM: Semantic Attribute Modulation for Language Modeling and Style Variation cs.CL · 2017 · author #4
  50. Improving Interpretability of Deep Neural Networks with Semantic Information cs.CV · 2017 · author #2
  51. Deep Learning Logo Detection with Data Expansion by Synthesising Context cs.CV · 2016 · author #1
  52. FLASH: Fast Bayesian Optimization for Data Analytic Pipelines cs.LG · 2016 · author #3
  53. Experiments on Parallel Training of Deep Neural Network using Model Averaging cs.LG · 2015 · author #1
  54. Multi-view Convolutional Neural Networks for 3D Shape Recognition cs.CV · 2015 · author #1

Mentions

  • 1507.01239 #1 · backfill · confidence 0.70 Hang Su
  • 1505.00880 #1 · backfill · confidence 0.70 Hang Su
  • 2606.03283 #6 · arxiv_oai · confidence 0.70 Hang Su
  • 2606.01955 #28 · arxiv_oai · confidence 0.70 Hang Su
  • 2605.30877 #23 · arxiv_oai · confidence 0.70 Hang Su
  • 2605.27375 #5 · arxiv_oai · confidence 0.70 Hang Su
  • 2605.26177 #4 · arxiv_oai · confidence 0.70 Hang Su
  • 2602.02214 #4 · arxiv_oai · confidence 0.70 Hang Su
  • 2507.12898 #7 · arxiv_oai · confidence 0.70 Hang Su

Frequent Coauthors