Explore ML Research by Topic

Discover the latest papers across 12 key areas of machine learning and AI

LLM Agents

Autonomous agents powered by large language models, multi-agent systems, and tool-using AI.

Retrieval-augmented generation, knowledge grounding, and neural information retrieval.

Chain-of-thought prompting, logical reasoning, planning, and problem-solving in LLMs.

Parameter-efficient fine-tuning, LoRA, instruction tuning, and supervised fine-tuning.

Vision-language models, multimodal AI, visual question answering, and image-text alignment.

AI-powered code synthesis, program repair, and automated software engineering.

AI alignment, RLHF, harmlessness, robustness, and LLM jailbreak research.

LLM benchmarks, evaluation frameworks, surveys, and leaderboard methodology.

Quantization, pruning, speculative decoding, KV cache, and fast LLM serving.

Large language model pretraining, scaling laws, and foundation model architectures.

RL from human feedback, reward modeling, policy gradient methods, and PPO.

Diffusion models, image generation, text-to-image synthesis, and generative AI.