SOURCES
Official website & sources
Sources
RELATED COLLECTIONS
Related topics
NEWS REPORTS
News stories
View more- Agents Prompt People: Using Agents for Long-Horizon Financial Work
- Exposure Is Not Commitment: Double-Stratified Evaluation of Latent Monitors for Tool-Using Agents
- 3, 7, 14, 17, 42: Instruction Tuning Installs and Sharpens Number-Choice Heuristics in Language Models
- Detect Before You Disambiguate: Perturbation-Based Input Ambiguity Detection in LLMs
- AK_QMUL at ArGuard Shared Tasks: A Single Fine-Tuned JAIS for Arabic Harmful-Prompt Detection
- 斯坦福的研究，红海的珊瑚，与一个中国模型
- Fix evaluation bias to unlock better models on Amazon Bedrock
- NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt
- PRISM: Promoting Sampling Diversity of Large Language Models with Implicit Stochastic Modulation
- Linear-Time Context Compression with State-Space Encoding
