pith. sign in

Yifan Wu

Identifiers

  • name variant Yifan Wu 0.60 · backfill

Papers (38)

  1. When Chatbots Accommodate: What AI Companions Optimize for in Vulnerable Conversations cs.HC · 2026 · author #2
  2. StepFinder: A Temporal Semantic Framework for Failure Attribution in Multi-Agent Systems cs.AI · 2026 · author #2
  3. OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification cs.LG · 2026 · author #3
  4. Feature to Dynamics: Feature-space to Autoregression strategy for Zero-shot Time Series Forecasting cs.LG · 2026 · author #1
  5. Aligned but Fragile: Enhancing LLM Safety Robustness via Zeroth-Order Optimization cs.AI · 2026 · author #2
  6. Out of Sight, Not Out of Mind: Unveiling Latent Attack in Latent-based Multi-Agent Systems cs.CR · 2026 · author #5
  7. Foundation Protocol: A Coordination Layer for Agentic Society cs.AI · 2026 · author #14
  8. DiagEval: Trajectory-Conditioned Diagnosis for Reliable Software Evaluation with GUI Agents cs.SE · 2026 · author #5
  9. Agentic Recommender System with Hierarchical Belief-State Memory cs.CL · 2026 · author #3
  10. Token Economics for LLM Agents: A Dual-View Study from Computing and Economics cs.AI · 2026 · author #6
  11. Knowledge Transfer Scaling Laws for 3D Medical Imaging cs.CV · 2026 · author #7
  12. Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation cs.AI · 2026 · author #7
  13. Support theorem of universal compactified Jacobians math.AG · 2026 · author #1
  14. Distributional Alignment Games for Answer-Level Fine-Tuning cs.LG · 2026 · author #3
  15. From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning cs.AI · 2026 · author #8
  16. DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation cs.SE · 2026 · author #3
  17. Pay Attention to Sequence Split: Uncovering the Impacts of Sub-Sequence Splitting on Sequential Recommendation Models cs.IR · 2026 · author #2
  18. Synthetic Sandbox for Training Machine Learning Engineering Agents cs.CL · 2026 · author #3
  19. OpenAI GPT-5 System Card cs.CL · 2025 · author #463
  20. Graph-Regularized Sparse Autoencoders for LLM Safety Steering cs.LG · 2025 · author #3
  21. Agent Learning via Early Experience cs.AI · 2025 · author #30
  22. Truthful Calibration Errors for Multi-Class Prediction cs.LG · 2025 · author #2
  23. A Perfectly Truthful Calibration Measure cs.LG · 2025 · author #3
  24. Behavior Regularized Offline Reinforcement Learning cs.LG · 2019 · author #1
  25. Enhanced generative adversarial network for 3D brain MRI super-resolution eess.IV · 2019 · author #3
  26. Programming with Timespans in Interactive Visualizations cs.HC · 2019 · author #1
  27. Securely Trading Unverifiable Information without Trust cs.GT · 2019 · author #3
  28. Predicting Academic Performance for College Students: A Campus Behavior Perspective cs.CY · 2019 · author #4
  29. Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment cs.LG · 2019 · author #1
  30. Repetitive Motion Estimation Network: Recover cardiac and respiratory signal from thoracic imaging cs.CV · 2018 · author #3
  31. The Laplacian in RL: Learning Representations with Efficient Approximations cs.LG · 2018 · author #1
  32. Privacy-Protective-GAN for Face De-identification cs.CV · 2018 · author #1
  33. Generating Synthetic X-ray Images of a Person from the Surface Geometry cs.CV · 2018 · author #6
  34. Towards Understanding the Generalization Bias of Two Layer Convolutional Linear Classifiers with Gradient Descent cs.LG · 2018 · author #1
  35. Orderness Predicts Academic Performance: Behavioral Analysis on Campus Lifestyle physics.soc-ph · 2017 · author #7
  36. Planar Object Tracking in the Wild: A Benchmark cs.CV · 2017 · author #2
  37. Conservative Bandits stat.ML · 2016 · author #1
  38. Online Learning with Gaussian Payoffs and Side Observations stat.ML · 2015 · author #1

Mentions

  • 2606.04431 #2 · arxiv_oai · confidence 0.70 Yifan Wu
  • 2606.03467 #2 · arxiv_oai · confidence 0.70 Yifan Wu
  • 2606.01476 #3 · arxiv_oai · confidence 0.70 Yifan Wu
  • 2606.01289 #1 · arxiv_oai · confidence 0.70 Yifan Wu
  • 2605.03097 #1 · arxiv_oai · confidence 0.70 Yifan Wu
  • 2605.29396 #2 · arxiv_oai · confidence 0.70 Yifan Wu
  • 2605.28214 #5 · arxiv_oai · confidence 0.70 Yifan Wu
  • 2510.08558 #30 · arxiv_oai · confidence 0.70 Yifan Wu
  • 2605.23218 #14 · arxiv_oai · confidence 0.70 Yifan Wu
  • 2605.17439 #5 · arxiv_oai · confidence 0.70 Yifan Wu
  • 2510.06388 #2 · arxiv_oai · confidence 0.70 Yifan Wu
  • 2605.14401 #3 · arxiv_oai · confidence 0.70 Yifan Wu
  • 2512.06655 #3 · arxiv_oai · confidence 0.70 Yifan Wu

Frequent Coauthors