Search
Every story and research paper Zotpaper has published, and the people, companies and benchmarks in them.
Most read
- 1
Simple retrieval rivals complex memory systems on conversation benchmarks
- 2
Robot policies trained on minimal data struggle on real-world tasks in distributed tests
- 3
Former Sydney private school principal accused of raping 14-year-old boy, refused bail
- 4
Mistral says Large 4 is live for approved teams with 1.05T open weights
- 5
AI email agents can handle standard phishing safely yet obey tailored attacks
- 6
Optimizing AI agents for cost as well as quality improves both
Developing
Texas turns blue: Hinojosa ousts Abbott, Talarico tops Paxton in Democratic sweep
54 sources totalDemocrats sweep midterms, Republicans blame Trump for 'disaster'
115 sources totalDavid Jones collapses, store closures expected before Christmas
31 sources totalIn the news this week
- Donald Trump107
- European Union29
- Google28
- OpenAI28
- Anthropic27
- Nvidia27
- Meta26
- Volodymyr Zelenskyy24
- Andy Burnham21
- United States Department of Justice20
- Anthony Albanese17
- Apple17
- NASA16
- Reserve Bank of Australia16
- Microsoft14
- One Nation14
- Democratic Party13
- Houthis13
The people, companies and organisations in the most stories over the past seven days.
News sections
Research topics
Research threads
All threads →- Agent Self-Improvement103 papers
- Agent Memory Architecture34 papers
- Long-Context Attention Design10 papers
- Process Agent Benchmarks65 papers
- Time Series Foundation Models5 papers
- Benchmark Ecological Validity86 papers
- Evaluation Metric Validity14 papers
- Diffusion Inference Acceleration6 papers
Concepts
All concepts →Benchmarks
All benchmarks →Each one shows the numbers papers report on it. Every figure is as the paper states it.