Latest Research in Machine Learning

Top Research Topics in Machine Learning

• Machine Learning — 105 papers
• Computer Vision and Pattern Recognition — 68 papers
• Artificial Intelligence — 18 papers
• Machine Learning — 11 papers
• Computation and Language — 10 papers
• Multiagent Systems — 7 papers
• Reinforcement Learning in Robotics — 7 papers
• Optimization and Control — 5 papers
• Computer Science and Game Theory — 5 papers
• Systems and Control — 4 papers

Highest-Cited Papers

1. Attention Is All You Need: A Technical Review of the Transformer Architecture and Its Impact on Modern Artificial Intelligence
2. Reinforcement Learning for Intensity Control: An Application to Choice-Based Network Revenue Management
3. Accelerating Q-learning through Efficient Value-Sharing across Actions
4. Scalable Policy Optimization for Networked Multi-Agent Reinforcement Learning with Continuous State-Action Spaces
5. Source-Free Domain Adaptation with Vision-Language Prior
6. Opponent-modeling-enhanced multi-agent reinforcement learning for dynamic games under incomplete information
7. State-based Selection of Expert Policies in Disaster Environments and Reinforcement Learning of a Unified Student Policy via Distillation
8. Not All Layers Need Tuning: Diagnosing and Directing Adaptation in Vision-Language-Action Models
9. Precision autotuning for linear solvers via contextual bandit-based RL
10. CARE-VI: Conservative Adaptive Reliability Estimation for Value Improvement in Off-Policy Actor-Critic Learning
11. Optimal Value Inference for Reinforcement Learning
12. Mitigating Retaliatory Algorithmic Collusion in Repeated Games
13. QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuning
14. Bridging RL and MPC for mixed-integer optimal control with application to Formula 1 race strategies
15. Graph-Based Stochastic Power-UCT: Monte-Carlo Graph Search with Power Mean Estimation
16. Model-based Bootstrap for Offline Policy Evaluation in Tabular Reinforcement Learning
17. The Bias of Nonlinear Two-Time-scale Stochastic Approximation under Constant Step-Sizes
18. Understanding and Exploiting Diagonal Attention Sparsity in Autoregressive Image Generation
19. Socialized UAV Cross-Task Learning: Towards Cross-Granularity Collaboration through Hierarchical Interaction
20. FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation