Latest Research in Large Language Models

Top Research Topics in Large Language Models

• Computation and Language — 1,385 papers
• Machine Learning — 1,056 papers
• Computer Vision and Pattern Recognition — 931 papers
• Artificial Intelligence — 917 papers
• Robotics — 596 papers
• Software Engineering — 162 papers
• Information Retrieval — 131 papers
• Topic Modeling — 125 papers
• Cryptography and Security — 120 papers
• Natural Language Processing Techniques — 75 papers

Highest-Cited Papers

1. Beyond Efficiency: A Systematic Survey of Resource-Efficient Large Language Models (40 citations)
2. Collaborative Inference and Learning between Edge SLMs and Cloud LLMs: A Survey of Algorithms, Execution, and Open Challenges (3 citations)
3. What is the Role of Small Models in the LLM Era: A Survey (6 citations)
4. Uncertainty-aware large language models: a scoping review of conformal prediction methods (1 citations)
5. Model-Based Learning of Whittle indices (1 citations)
6. Model Inversion Attacks Through Target-Specific Conditional Diffusion Models (2 citations)
7. Mixed-Precision Quantization for Language Models: Techniques and Prospects (1 citations)
8. Ceiling Effects and Convergence: Null Results for Instruction Repetition in LLM-Agent Pipelines
9. Stratum: Lie Field Layers for Grid Logic Puzzles in Small Transformers
10. The Reflective Budget Governor: Equilibrium-Based Early Stopping for Iterative LLM Refinement
11. WeaveCube: A Feasibility Study of Exact Shared-Word Construction for Rubik's Cube Solving
12. The Agent Harness Playground: A ReAct-Style Agent Harness with Budgeted Multi-Agent Delegation and Embedded Quantitative Equity Research
13. Ceiling Effects and Convergence: Null Results for Instruction Repetition in LLM-Agent Pipelines
14. Token-level defect feedback and alternating optimization for coupled code generation and defect detection with large language models
15. Is there a way to improve language models accuracy in solving physics problems in Russian and English languages?
16. The Reflective Budget Governor: Equilibrium-Based Early Stopping for Iterative LLM Refinement
17. Correct Verdicts, Wrong Field: Attribution and Capability Are Dissociable When Small Language Models Follow a Rubric
18. AI Teacher Latent Basis Reorientation
19. Personalized library knowledge services driven by chain-of-thought large language models
20. The Agent Harness Playground: A ReAct-Style Agent Harness with Budgeted Multi-Agent Delegation and Embedded Quantitative Equity Research

Sub-Regions

• Language Modeling Architecture — 3,123 papers
• Multi-Agent Reinforcement Learning — 886 papers
• Software Security and Reliability — 861 papers
• Embodied Vision-Language Control — 794 papers
• Generative Visual Synthesis — 594 papers