Latest Research in Computer Science and Game Theory

Top Research Topics in Computer Science and Game Theory

• Machine Learning — 82 papers
• Computer Vision and Pattern Recognition — 31 papers
• Artificial Intelligence — 12 papers
• Machine Learning — 10 papers
• Computer Science and Game Theory — 8 papers
• Optimization and Control — 7 papers
• Ferroelectric and Negative Capacitance Devices — 4 papers
• Systems and Control — 4 papers
• Domain Adaptation and Few-Shot Learning — 3 papers
• Data Structures and Algorithms — 2 papers

Highest-Cited Papers

1. CFR variant and iterate reporting in small imperfect-information games
2. Grokking the Discrete Logarithm: Scaling Across Model Capacity and Mechanistic Analysis
3. A Statistical Perspective on Knowledge Distillation: Foundations, Classical Methods, and Large Language Model Extensions
4. Grokking the Discrete Logarithm: Scaling Across Model Capacity and Mechanistic Analysis
5. Steering Equilibrium Selection in Regularized Self-Play via the Reference Policy
6. A Logarithmic Regret Bound for Optimistic Hedge in General-Sum Games
7. Minimax-Optimal Online Contract Design with Unrestricted Bounded Contracts
8. Odds-Ratio Thompson Sampling: A Specification and Design Guide for Contrast-Based Multi-Armed Bandits
9. Exact Regret Frontiers and Externality Scheduling in Centralized Serial-Dictatorship Bandits
10. Enhanced Knowledge Distillation for Detection Transformer via Teacher Prediction Refinement
11. A Geometric Theory of Decision Boundaries in Structured Markov Decision Processes
12. Approximating Pandora's Knapsack via Simple Policies
13. Performance Guarantees for Data-Driven Sequential Decision-Making
14. Bergson: An Open Source Library for Data Attribution
15. TRIPROBE: Probing Task Separability Beyond Classification for XAI
16. Layer-wise Curriculum Learning for Efficient LLM Compression
17. Learning-Guided Planning in Large Dynamic Action Spaces: Budgeted Tree Search for One-to-Many Mobile Charging
18. Meta-LinEXP3: Online-within-Online Learning for Adversarial Linear Contextual Bandits
19. HyCal: A Training-Free Prototype Calibration Method for Cross-Discipline Few-Shot Class-Incremental Learning
20. What Does Layer-Importance Reveal About Transformers and State-Space Models?