Niao He

Venues

Frequent coauthors

Papers

1. AmorLIP: Efficient Language-Image Pretraining via Amortization
   NeurIPS 2025 ·

   Haotian Sun

   DBLP profile ↗ORCID search ↗
2. Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective
   ICML 2025 ·

   Jiawei Huang

   DBLP profile ↗ORCID search ↗
3. Efficiently Escaping Saddle Points for Policy Optimization
   UAI 2025 ·

   Mohammadsadegh Khorasani

   DBLP profile ↗ORCID search ↗
4. Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning
   NeurIPS 2025 ·

   Riccardo De Santi

   DBLP profile ↗ORCID search ↗
5. From Gradient Clipping to Normalization for Heavy Tailed SGD
   AISTATS 2025 ·

   Florian Hübler

   DBLP profile ↗ORCID search ↗
6. Learning to Steer Markovian Agents under Model Uncertainty
   ICLR 2025 ·

   Jiawei Huang

   DBLP profile ↗ORCID search ↗
7. Natural Gradient VI: Guarantees for Non-Conjugate Models
   NeurIPS 2025 ·

   Fangyuan Sun

   DBLP profile ↗ORCID search ↗
8. On the Crucial Role of Initialization for Matrix Factorization
   ICLR 2025 ·

   Bingcong Li

   DBLP profile ↗ORCID search ↗
9. PoLAR: Polar-Decomposed Low-Rank Adapter Representation
   NeurIPS 2025 ·

   Kai Lion

   DBLP profile ↗ORCID search ↗
10. Provable Maximum Entropy Manifold Exploration via Diffusion Models
    ICML 2025 ·

    Riccardo De Santi

    DBLP profile ↗ORCID search ↗
11. Scalable Neural Incentive Design with Parameterized Mean-Field Approximation
    NeurIPS 2025 ·

    Nathan Corecco

    DBLP profile ↗ORCID search ↗
12. Steering No-Regret Agents in MFGs under Model Uncertainty
    AISTATS 2025 ·

    Leo Widmer

    DBLP profile ↗ORCID search ↗
13. Zeroth-Order Optimization Finds Flat Minima
    NeurIPS 2025 ·

    Liang Zhang

    DBLP profile ↗ORCID search ↗
14. Achieving Near-Optimal Convergence for Distributed Minimax Optimization with Adaptive Stepsizes
    NeurIPS 2024 ·

    Yan Huang

    DBLP profile ↗ORCID search ↗
15. Automated Design of Affine Maximizer Mechanisms in Dynamic Settings
    AAAI 2024 ·

    Michael J. Curry

    DBLP profile ↗ORCID search ↗
16. DPZero: Private Fine-Tuning of Language Models without Backpropagation
    ICML 2024 ·

    Liang Zhang

    DBLP profile ↗ORCID search ↗
17. Generalization Bounds of Nonconvex-(Strongly)-Concave Stochastic Minimax Optimization
    AISTATS 2024 ·

    Siqi Zhang

    DBLP profile ↗ORCID search ↗
18. Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems
    NeurIPS 2024 ·

    Bingcong Li

    DBLP profile ↗ORCID search ↗
19. Independent Learning in Constrained Markov Potential Games
    AISTATS 2024 ·

    Philip Jordan

    DBLP profile ↗ORCID search ↗
20. Model-Based RL for Mean-Field Games is not Statistically Harder than Single-Agent RL
    ICML 2024 ·

    Jiawei Huang

    DBLP profile ↗ORCID search ↗
21. On the Statistical Efficiency of Mean-Field Reinforcement Learning with General Function Approximation
    AISTATS 2024 ·

    Jiawei Huang

    DBLP profile ↗ORCID search ↗
22. Parameter-Agnostic Optimization under Relaxed Smoothness
    AISTATS 2024 ·

    Florian Hübler

    DBLP profile ↗ORCID search ↗
23. Provably Learning Nash Policies in Constrained Markov Potential Games
    AAMAS 2024 ·

    Pragnya Alatur

    DBLP profile ↗ORCID search ↗
24. Taming Nonconvex Stochastic Mirror Descent with General Bregman Divergence
    AISTATS 2024 ·

    Ilyas Fatkhullin

    DBLP profile ↗ORCID search ↗
25. Truly No-Regret Learning in Constrained MDPs
    ICML 2024 ·

    Adrian Müller

    DBLP profile ↗ORCID search ↗
26. When is Mean-Field Reinforcement Learning Tractable and Relevant?
    AAMAS 2024 ·

    Batuhan Yardim

    DBLP profile ↗ORCID search ↗