PPaperPicks

Minsu Kim

Mila - Quebec Artificial Intelligence Institute, Montreal, Canada

19 papers at tracked venues · 18 at CORE A* · active 2024–2025

DBLP profile ↗ORCID 0009-0003-8751-0352 ↗Google Scholar ↗Homepage ↗

Venues

NeurIPS ×6ICLR ×5ICML ×4AAAI ×1AISTATS ×1SIGKDD ×1VLDB ×1

Frequent coauthors

Hyeonah Kim
DBLP profile ↗ORCID search ↗
×3
Siddarth Venkatraman
DBLP profile ↗ORCID search ↗
×2
Gyubin Lee
DBLP profile ↗ORCID search ↗
×1
Seonghwan Seo
DBLP profile ↗ORCID search ↗
×1
Seanie Lee
DBLP profile ↗ORCID search ↗
×1
Nayoung Kim
DBLP profile ↗ORCID search ↗
×1
Federico Berto
DBLP profile ↗ORCID search ↗
×1
Brian R. Bartoldson
DBLP profile ↗ORCID search ↗
×1
Jiwoo Son
DBLP profile ↗ORCID search ↗
×1
Marcin Sendera
DBLP profile ↗ORCID search ↗
×1
Hyosoon Jang
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Adaptive Inference-Time Scaling via Cyclic Diffusion Search
    NeurIPS 2025 ·
    Gyubin Lee
    DBLP profile ↗ORCID search ↗
  2. Adaptive teachers for amortized samplers
    ICLR 2025 · Minsu Kim
  3. Ant Colony Sampling with GFlowNets for Combinatorial Optimization
    AISTATS 2025 · Minsu Kim
  4. Generative Flows on Synthetic Pathway for Drug Design
    ICLR 2025 ·
    Seonghwan Seo
    DBLP profile ↗ORCID search ↗
  5. Improved Off-policy Reinforcement Learning in Biological Sequence Design
    ICML 2025 ·
    Hyeonah Kim
    DBLP profile ↗ORCID search ↗
  6. Learning Diverse Attacks on Large Language Models for Robust Red-Teaming and Safety Tuning
    ICLR 2025 ·
    Seanie Lee
    DBLP profile ↗ORCID search ↗
  7. MOFFlow: Flow Matching for Structure Prediction of Metal-Organic Frameworks
    ICLR 2025 ·
    Nayoung Kim
    DBLP profile ↗ORCID search ↗
  8. Outsourced Diffusion Sampling: Efficient Posterior Inference in Latent Spaces of Generative Models
    ICML 2025 ·
    Siddarth Venkatraman
    DBLP profile ↗ORCID search ↗
  9. RL4CO: An Extensive Reinforcement Learning for Combinatorial Optimization Benchmark
    SIGKDD 2025 ·
    Federico Berto
    DBLP profile ↗ORCID search ↗
  10. Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training
    NeurIPS 2025 ·
    Brian R. Bartoldson
    DBLP profile ↗ORCID search ↗
  11. Accelerating String-key Learned Index Structures via Memoization-based Incremental Training
    VLDB 2024 · Minsu Kim
  12. Amortizing intractable inference in diffusion models for vision, language, and control
    NeurIPS 2024 ·
    Siddarth Venkatraman
    DBLP profile ↗ORCID search ↗
  13. Equity-Transformer: Solving NP-Hard Min-Max Routing Problems as Sequential Generation with Equity Context
    AAAI 2024 ·
    Jiwoo Son
    DBLP profile ↗ORCID search ↗
  14. Genetic-guided GFlowNets for Sample Efficient Molecular Optimization
    NeurIPS 2024 ·
    Hyeonah Kim
    DBLP profile ↗ORCID search ↗
  15. Improved off-policy training of diffusion samplers
    NeurIPS 2024 ·
    Marcin Sendera
    DBLP profile ↗ORCID search ↗
  16. Learning to Scale Logits for Temperature-Conditional GFlowNets
    ICML 2024 · Minsu Kim
  17. Local Search GFlowNets
    ICLR 2024 · Minsu Kim
  18. Pessimistic Backward Policy for GFlowNets
    NeurIPS 2024 ·
    Hyosoon Jang
    DBLP profile ↗ORCID search ↗
  19. Symmetric Replay Training: Enhancing Sample Efficiency in Deep Reinforcement Learning for Combinatorial Optimization
    ICML 2024 ·
    Hyeonah Kim
    DBLP profile ↗ORCID search ↗