PPaperPicks

Niao He

26 papers at tracked venues · 16 at CORE A* · active 2024–2025

DBLP profile ↗ORCID search ↗

Venues

NeurIPS ×8AISTATS ×7ICML ×5AAMAS ×2ICLR ×2AAAI ×1UAI ×1

Frequent coauthors

Bingcong Li
×6
Liang Zhang
×6
Jiawei Huang
×5
Zebang Shen
×4
Andreas Krause
×4
Ilyas Fatkhullin
×3
Vinzenz Thoma
×3
Batuhan Yardim
×3
Riccardo De Santi
×2
Marin Vlastelica
×2
Ya-Ping Hsieh
×2
Florian Hübler
×2

Papers

  1. AmorLIP: Efficient Language-Image Pretraining via Amortization
    NeurIPS 2025 ·
    Haotian Sun
    ,
    Yitong Li
    ,
    Yuchen Zhuang
    , Niao He,
    Hanjun Dai
    ,
    Bo Dai
  2. Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective
    ICML 2025 ·
    Jiawei Huang
    ,
    Bingcong Li
    ,
    Christoph Dann
    , Niao He
  3. Efficiently Escaping Saddle Points for Policy Optimization
    UAI 2025 ·
    Mohammadsadegh Khorasani
    ,
    Saber Salehkaleybar
    ,
    Negar Kiyavash
    , Niao He,
    Matthias Grossglauser
  4. Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning
    NeurIPS 2025 ·
    Riccardo De Santi
    ,
    Marin Vlastelica
    ,
    Ya-Ping Hsieh
    ,
    Zebang Shen
    , Niao He,
    Andreas Krause
  5. From Gradient Clipping to Normalization for Heavy Tailed SGD
    AISTATS 2025 ·
    Florian Hübler
    ,
    Ilyas Fatkhullin
    , Niao He
  6. Learning to Steer Markovian Agents under Model Uncertainty
    ICLR 2025 ·
    Jiawei Huang
    ,
    Vinzenz Thoma
    ,
    Zebang Shen
    ,
    Heinrich H. Nax
    , Niao He
  7. Natural Gradient VI: Guarantees for Non-Conjugate Models
    NeurIPS 2025 ·
    Fangyuan Sun
    ,
    Ilyas Fatkhullin
    , Niao He
  8. On the Crucial Role of Initialization for Matrix Factorization
    ICLR 2025 ·
    Bingcong Li
    ,
    Liang Zhang
    ,
    Aryan Mokhtari
    , Niao He
  9. PoLAR: Polar-Decomposed Low-Rank Adapter Representation
    NeurIPS 2025 ·
    Kai Lion
    ,
    Liang Zhang
    ,
    Bingcong Li
    , Niao He
  10. Provable Maximum Entropy Manifold Exploration via Diffusion Models
    ICML 2025 ·
    Riccardo De Santi
    ,
    Marin Vlastelica
    ,
    Ya-Ping Hsieh
    ,
    Zebang Shen
    , Niao He,
    Andreas Krause
  11. Scalable Neural Incentive Design with Parameterized Mean-Field Approximation
    NeurIPS 2025 ·
    Nathan Corecco
    ,
    Batuhan Yardim
    ,
    Vinzenz Thoma
    ,
    Zebang Shen
    , Niao He
  12. Steering No-Regret Agents in MFGs under Model Uncertainty
    AISTATS 2025 ·
    Leo Widmer
    ,
    Jiawei Huang
    , Niao He
  13. Zeroth-Order Optimization Finds Flat Minima
    NeurIPS 2025 ·
    Liang Zhang
    ,
    Bingcong Li
    ,
    Kiran Koshy Thekumparampil
    ,
    Sewoong Oh
    ,
    Michael Muehlebach
    , Niao He
  14. Achieving Near-Optimal Convergence for Distributed Minimax Optimization with Adaptive Stepsizes
    NeurIPS 2024 ·
    Yan Huang
    ,
    Xiang Li
    ,
    Yipeng Shen
    , Niao He,
    Jinming Xu
  15. Automated Design of Affine Maximizer Mechanisms in Dynamic Settings
    AAAI 2024 ·
    Michael J. Curry
    ,
    Vinzenz Thoma
    ,
    Darshan Chakrabarti
    ,
    Stephen McAleer
    ,
    Christian Kroer
    ,
    Tuomas Sandholm
    , Niao He,
    Sven Seuken
  16. DPZero: Private Fine-Tuning of Language Models without Backpropagation
    ICML 2024 ·
    Liang Zhang
    ,
    Bingcong Li
    ,
    Kiran Koshy Thekumparampil
    ,
    Sewoong Oh
    , Niao He
  17. Generalization Bounds of Nonconvex-(Strongly)-Concave Stochastic Minimax Optimization
    AISTATS 2024 ·
    Siqi Zhang
    ,
    Yifan Hu
    ,
    Liang Zhang
    , Niao He
  18. Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems
    NeurIPS 2024 ·
    Bingcong Li
    ,
    Liang Zhang
    , Niao He
  19. Independent Learning in Constrained Markov Potential Games
    AISTATS 2024 ·
    Philip Jordan
    ,
    Anas Barakat
    , Niao He
  20. Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL
    ICML 2024 ·
    Jiawei Huang
    , Niao He,
    Andreas Krause
  21. On the Statistical Efficiency of Mean-Field Reinforcement Learning with General Function Approximation
    AISTATS 2024 ·
    Jiawei Huang
    ,
    Batuhan Yardim
    , Niao He
  22. Parameter-Agnostic Optimization under Relaxed Smoothness
    AISTATS 2024 ·
    Florian Hübler
    ,
    Junchi Yang
    ,
    Xiang Li
    , Niao He
  23. Provably Learning Nash Policies in Constrained Markov Potential Games
    AAMAS 2024 ·
    Pragnya Alatur
    ,
    Giorgia Ramponi
    , Niao He,
    Andreas Krause
  24. Taming Nonconvex Stochastic Mirror Descent with General Bregman Divergence
    AISTATS 2024 ·
    Ilyas Fatkhullin
    , Niao He
  25. Truly No-Regret Learning in Constrained MDPs
    ICML 2024 ·
    Adrian Müller
    ,
    Pragnya Alatur
    ,
    Volkan Cevher
    ,
    Giorgia Ramponi
    , Niao He
  26. When is Mean-Field Reinforcement Learning Tractable and Relevant?
    AAMAS 2024 ·
    Batuhan Yardim
    ,
    Artur Goldman
    , Niao He