Home›Papers
Papers
Papers
Papers that changed AI, with a plain-language explainer for each.
Total 45 · Clear filters
- 2025
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
arXiv
The Gemini 2.5 technical report, submitted to arXiv on 7 July 2025, documents Google's Gemini 2.5 Pro and 2.5 Flash models: their reasoning, long-context video handling, and cost-versus-capability positioning.
- 2025
ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems
arXiv
A 2025 paper introducing ARC-AGI-2, a benchmark of input-output puzzle tasks built to measure abstract reasoning in frontier AI systems, with human testing as a baseline and a task set designed to give a more granular signal of progress.
- 2025
Qwen3 Technical Report
arXiv
The Qwen3 Technical Report presents Alibaba's Qwen3 family of dense and mixture-of-experts language models, which unify thinking and non-thinking modes, add a controllable thinking budget, and are released under the Apache 2.0 licence.
- 2025
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
arXiv
A 2025 paper proposing Absolute Zero, a reinforcement-learning paradigm in which one model writes its own code-reasoning tasks and then solves them, with a code executor as the only judge, reaching state of the art on coding and maths without external training data.
- 2025
s1: Simple test-time scaling
arXiv
A paper showing that a 32B model fine-tuned on 1,000 carefully chosen questions and run with a simple "budget forcing" trick can beat o1-preview on competition maths by up to 27%, with model, data and code released.
- 2025
Humanity's Last Exam (HLE)
arXiv
Humanity's Last Exam (HLE) is a 2,500-question, multi-modal benchmark spanning dozens of academic subjects, built by experts worldwide so that frontier language models can still be measured after saturating older tests.
- 2025
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
arXiv
The DeepSeek-R1 report described how a reasoning model was trained largely with reinforcement learning, rewarding correct answers, and reached performance comparable to OpenAI's o1 on math, code and reasoning benchmarks. Its weights were released openly.
- 2024
FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI
arXiv
FrontierMath is a benchmark of hundreds of original, unpublished mathematics problems written and vetted by expert mathematicians, introduced by Epoch AI to test advanced mathematical reasoning in AI. At release, state-of-the-art models solved under 2% of the problems.[^1][^2]
- 2024
MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
arXiv
MMLU-Pro is a 2024 benchmark that makes the widely used MMLU knowledge test harder: its questions are reasoning-focused and each has ten answer options instead of four.
- 2023
GAIA: a benchmark for General AI Assistants
arXiv
GAIA is a benchmark of real-world questions that are easy for humans but hard for AI assistants, testing reasoning, multimodality, web browsing, and tool use. It compares AI progress against average human performance.
- 2023
GPQA: A Graduate-Level Google-Proof Q&A Benchmark
arXiv
GPQA is a benchmark of 448 expert-written multiple-choice questions in biology, physics and chemistry, built so that skilled non-experts cannot look the answers up, and hard enough that the strongest GPT-4 baseline scored 39% while domain experts reached 65%.
- 2023
Sparks of Artificial General Intelligence: Early experiments with GPT-4
arXiv
A March 2023 paper by Microsoft researchers testing an early GPT-4, arguing it shows strikingly general, near-human performance across many domains and could be seen as an early but incomplete step toward AGI.
- 2022
Scalable Diffusion Models with Transformers (DiT)
arXiv
A 2022 paper by William Peebles and Saining Xie that replaces the U-Net backbone of diffusion models with a transformer operating on latent patches, showing that image quality improves predictably as compute grows and reaching a state-of-the-art FID of 2.27 on ImageNet 256×256.
- 2022
Emergent Abilities of Large Language Models
arXiv 2206.07682 (TMLR 2022)
A 2022 paper arguing that some abilities of large language models appear only once models are large enough, and cannot be predicted by extrapolating from smaller models — so further scaling may keep widening what these models can do.
- 2022
Beyond the Imitation Game (BIG-bench)
arXiv
BIG-bench is a large community-built benchmark of 204 tasks designed to test language models on problems believed to lie beyond their current abilities, described in a paper posted in June 2022.
- 2022
Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding (Imagen)
arXiv
Imagen is a text-to-image diffusion model that uses a large pretrained language model to encode prompts; it reached a zero-shot FID of 7.27 on COCO and introduced the DrawBench benchmark.
- 2022
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
NeurIPS
A 2022 paper by Jason Wei and colleagues at Google Research showing that prompting a large language model with examples that include intermediate reasoning steps, rather than answers alone, substantially improves its performance on arithmetic, commonsense and symbolic reasoning tasks.
- 2021
High-Resolution Image Synthesis with Latent Diffusion Models
arXiv 2112.10752 (CVPR 2022)
A 2021 paper by Rombach, Blattmann, Lorenz, Esser and Ommer that runs diffusion models inside the latent space of pretrained autoencoders, cutting the compute needed for high-resolution image synthesis while adding cross-attention for text and bounding-box control.
- 2021
Training Verifiers to Solve Math Word Problems (GSM8K)
arXiv
GSM8K is an OpenAI benchmark of 8.5K grade school math word problems, released with a paper showing that even the largest Transformer models scored poorly, and that training verifiers to select among many candidate solutions improved results.
- 2021
Finetuned Language Models Are Zero-Shot Learners
arXiv 2109.01652
A 2021 paper showing that finetuning a language model on many tasks described by instructions — instruction tuning — makes it much better at unseen tasks without examples, surpassing a larger model on most benchmarks tested.