pith. sign in

Tianyu Pang

Identifiers

  • name variant Tianyu Pang 0.60 · backfill

Papers (25)

  1. Balancing Learning Rates Across Layers: Exact Two-Step Dynamics and Optimal Scaling in Linear Neural Networks cs.LG · 2026 · author #1
  2. Unveiling Multi-regime Patterns in SciML: Distinct Failure Modes and Regime-specific Optimization cs.LG · 2026 · author #6
  3. Reinforcing Few-step Generators via Reward-Tilted Distribution Matching cs.CV · 2026 · author #6
  4. Scalable Token-Level Hallucination Detection in Large Language Models cs.CL · 2026 · author #2
  5. OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents cs.CV · 2026 · author #10
  6. Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw cs.CR · 2026 · author #8
  7. RMNP: Row-Momentum Normalized Preconditioning for Scalable Matrix-Based Optimization cs.LG · 2026 · author #3
  8. HTMuon: Improving Muon via Heavy-Tailed Spectral Correction cs.LG · 2026 · author #1
  9. SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification cs.CV · 2026 · author #4
  10. Rethinking the Trust Region in LLM Reinforcement Learning cs.LG · 2026 · author #4
  11. Depth, Not Data: An Analysis of Hessian Spectral Bifurcation cs.LG · 2026 · author #4
  12. Suspicious Alignment of SGD: A Fine-Grained Step Size Condition Analysis cs.LG · 2026 · author #4
  13. LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Reasoning-Focused Supervised Fine-Tuning cs.LG · 2025 · author #2
  14. Understanding R1-Zero-Like Training: A Critical Perspective cs.LG · 2025 · author #5
  15. LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification cs.CL · 2025 · author #5
  16. Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety cs.CR · 2025 · author #34
  17. LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation cs.CL · 2024 · author #5
  18. When Attention Sink Emerges in Language Models: An Empirical View cs.CL · 2024 · author #2
  19. Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks cs.CV · 2019 · author #2
  20. Improving Adversarial Robustness via Promoting Ensemble Diversity cs.LG · 2019 · author #1
  21. Adversarial Attacks and Defences Competition cs.CV · 2018 · author #7
  22. Max-Mahalanobis Linear Discriminant Analysis Networks cs.LG · 2018 · author #1
  23. Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser cs.CV · 2017 · author #4
  24. Boosting Adversarial Attacks with Momentum cs.LG · 2017 · author #3
  25. Towards Robust Detection of Adversarial Examples cs.LG · 2017 · author #1

Mentions

  • 2606.00340 #1 · arxiv_oai · confidence 0.70 Tianyu Pang
  • 2605.29153 #6 · arxiv_oai · confidence 0.70 Tianyu Pang
  • 2602.13600 #4 · arxiv_oai · confidence 0.70 Tianyu Pang
  • 2602.04879 #4 · arxiv_oai · confidence 0.70 Tianyu Pang
  • 2605.26108 #6 · arxiv_oai · confidence 0.70 Tianyu Pang
  • 2603.10067 #1 · arxiv_oai · confidence 0.70 Tianyu Pang
  • 2602.00545 #4 · arxiv_oai · confidence 0.70 Tianyu Pang
  • 2410.13846 #5 · arxiv_oai · confidence 0.70 Tianyu Pang
  • 2410.10781 #2 · arxiv_oai · confidence 0.70 Tianyu Pang

Frequent Coauthors