pith. sign in

Junyuan Hong

Identifiers

  • name variant Junyuan Hong 0.60 · backfill

Papers (33)

  1. A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models cs.CV · 2026 · author #7
  2. The Last Human-Written Paper: Agent-Native Research Artifacts cs.LG · 2026 · author #31
  3. LLMs Can Get "Brain Rot": A Pilot Study on Twitter/X cs.CL · 2025 · author #2
  4. LAD-VF: LLM-Automatic Differentiation Enables Fine-Tuning-Free Robot Planning from Formal Methods Feedback cs.RO · 2025 · author #2
  5. LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning cs.LG · 2025 · author #6
  6. Scaling Textual Gradients via Sampling-Based Momentum cs.CL · 2025 · author #2
  7. More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment cs.AI · 2025 · author #10
  8. MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models cs.CL · 2025 · author #3
  9. ChatWise: A Strategy-Guided Chatbot for Enhancing Cognitive Support in Older Adults cs.CY · 2025 · author #2
  10. GuideLLM: Exploring LLM-Guided Conversation with Applications in Autobiography Interviewing cs.CL · 2025 · author #9
  11. Extracting and Understanding the Superficial Knowledge in Alignment cs.CL · 2025 · author #7
  12. LLM-PBE: Assessing Data Privacy in Large Language Models cs.CR · 2024 · author #2
  13. GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning cs.LG · 2024 · author #4
  14. Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression cs.CL · 2024 · author #1
  15. Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk cs.LG · 2024 · author #2
  16. On the Generalization Ability of Unsupervised Pretraining cs.LG · 2024 · author #2
  17. Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark cs.LG · 2024 · author #3
  18. Who Leaked the Model? Tracking IP Infringers in Accountable Federated Learning cs.CR · 2023 · author #2
  19. DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer cs.CL · 2023 · author #1
  20. Understanding Deep Gradient Leakage via Inversion Influence Functions cs.LG · 2023 · author #2
  21. Safe and Robust Watermark Injection with a Single OoD Image cs.CV · 2023 · author #2
  22. FedNoisy: Federated Noisy Label Learning Benchmark cs.LG · 2023 · author #3
  23. Revisiting Data-Free Knowledge Distillation with Poisoned Teachers cs.LG · 2023 · author #1
  24. On the Hardness of Robustness Transfer: A Perspective from Rademacher Complexity over Symmetric Difference Hypothesis Space cs.LG · 2023 · author #3
  25. A Privacy-Preserving Hybrid Federated Learning Framework for Financial Crime Detection cs.LG · 2023 · author #2
  26. Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling cs.LG · 2022 · author #1
  27. Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork cs.CR · 2022 · author #2
  28. How Robust is Your Fairness? Evaluating and Sustaining Fairness under Unseen Distribution Shifts cs.LG · 2022 · author #2
  29. Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization cs.LG · 2022 · author #1
  30. Federated Robustness Propagation: Sharing Robustness in Heterogeneous Federated Learning cs.LG · 2021 · author #1
  31. Data-Free Knowledge Distillation for Heterogeneous Federated Learning cs.LG · 2021 · author #2
  32. Dynamic Privacy Budget Allocation Improves Data Efficiency of Differentially Private Gradient Descent cs.LG · 2021 · author #1
  33. Disturbance Grassmann Kernels for Subspace-Based Learning cs.LG · 2018 · author #1

Mentions

  • 2504.02193 #10 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2506.15606 #6 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2503.05740 #2 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2306.11650 #3 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2502.14302 #3 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2502.06494 #9 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2502.04602 #7 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2408.12787 #2 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2403.15447 #1 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2402.11592 #3 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2403.09450 #2 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2312.03724 #1 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2309.01786 #2 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2403.06871 #2 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2309.13016 #2 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2312.03205 #2 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2306.02368 #1 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2302.03654 #2 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2302.12351 #3 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2210.12575 #1 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2101.07413 #1 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2210.06428 #2 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2106.10196 #1 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2207.01168 #2 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2203.09747 #1 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2105.10056 #2 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 1802.03517 #1 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2506.00400 #2 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2606.28757 #7 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2509.18384 #2 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2406.09187 #4 · arxiv_oai · confidence 0.70 Junyuan Hong
  • 2604.24658 #31 · arxiv_oai · confidence 0.70 Junyuan Hong

Frequent Coauthors