Lune

Profiles2020-2026

Qiang Liu

University of Texas at Austin

32Papers
24Last author
55Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers32

  1. Gumbel Distillation for Parallel Text GenerationAuthor 4 of 4ICLR 2026 · 2 citations
  2. ϕ\phi-Balancing for Mixture-of-Experts TrainingAuthor 8 of 8ICML 2026
  3. Improving Rectified Flow with Boundary ConditionsAuthor 8 of 8ICCV 2025
  4. PIPA: Preference Alignment as Prior-Informed Statistical EstimationAuthor 3 of 3ICML 2025
  5. Steepest Descent Density Control for Compact 3D Gaussian SplattingAuthor 10 of 12CVPR 2025
  6. InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image GenerationAuthor 5 of 5ICLR 2024 · 358 citations
  7. AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based PoliciesAuthor 4 of 4NeurIPS 2024 · 73 citations
  8. Taming Mode Collapse in Score Distillation for Text-to-3D GenerationAuthor 9 of 11CVPR 2024 · 8 citations
  9. Quadratic Quantum Variational Monte CarloAuthor 2 of 2NeurIPS 2024 · 3 citations
  10. FAMO: Fast Adaptive Multitask OptimizationAuthor 4 of 4NeurIPS 2023 · 127 citations
  11. Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified FlowAuthor 3 of 3ICLR 2023 · 75 citations
  12. Metric Residual Network for Sample Efficient Goal-Conditioned Reinforcement LearningAuthor 3 of 4AAAI 2023 · 20 citations
  13. Sampling with Mollified Interaction Energy DescentAuthor 2 of 5ICLR 2023 · 2 citations
  14. Fast Point Cloud Generation with Straight FlowsAuthor 9 of 9CVPR 2023
  15. FlowGrad: Controlling the Output of Generative ODEs with GradientsAuthor 6 of 6CVPR 2023
  16. BOME! Bilevel Optimization Made Easy: A Simple First-Order ApproachAuthor 5 of 5NeurIPS 2022 · 170 citations
  17. Diffusion-based Molecule Generation with Informative Prior BridgesAuthor 5 of 5NeurIPS 2022 · 165 citations
  18. How to Fill the Optimum Set? Population Gradient Descent with Harmless DiversityAuthor 3 of 4ICML 2022 · 4 citations
  19. Conflict-Averse Gradient Descent for Multi-task learningAuthor 5 of 5NeurIPS 2021 · 686 citations
  20. VCNet and Functional Targeted Regularization For Learning Causal Effects of Continuous TreatmentsAuthor 3 of 4ICLR 2021 · 81 citations
  21. AlphaNet: Improved Training of Supernets with Alpha-DivergenceAuthor 4 of 5ICML 2021 · 52 citations
  22. Non-asymptotic Confidence Intervals of Off-policy Evaluation: Primal and Dual BoundsAuthor 4 of 4ICLR 2021 · 13 citations
  23. KeepAugment: A Simple Information-Preserving Data Augmentation ApproachAuthor 5 of 5CVPR 2021
  24. MaxUp: Lightweight Adversarial Training With Data Augmentation Improves Neural Network TrainingAuthor 4 of 4CVPR 2021
  25. Certified Monotonic Neural NetworksAuthor 4 of 4NeurIPS 2020 · 116 citations
  26. Firefly Neural Architecture Descent: a General Approach for Growing Neural NetworksAuthor 4 of 4NeurIPS 2020 · 79 citations
  27. Doubly Robust Bias Reduction in Infinite Horizon Off-Policy EstimationAuthor 5 of 5ICLR 2020 · 72 citations
  28. Black-Box Certification with Randomized Smoothing: A Functional Optimization Based FrameworkAuthor 5 of 5NeurIPS 2020 · 71 citations
  29. Black-box Off-policy Estimation for Infinite-Horizon Reinforcement LearningAuthor 3 of 5ICLR 2020 · 33 citations
  30. Greedy Optimization Provably Wins the Lottery: Logarithmic Number of Winning Tickets is EnoughAuthor 3 of 3NeurIPS 2020 · 17 citations

Showing the 30 most recent indexed papers.

Dusk over the sea between two cliffs drawn in fine vertical lines