On the Diagram of Thought
Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge
View PDF
International AI Safety Report 2025
International AI Safety Report 2025
Training Large Language Models to Reason in a Continuous Latent Space
LLMs Can Plan Only If We Tell Them
View PDF
Cognition is All You Need -- The Next Layer of AI Above Large...
NeurIPS Poster Large Language Models' Expert-level Global History Knowledge Benchmark (HiST-LLM)
ELIZA Reanimated: The world's first chatbot restored on the...
How is Google using AI for internal code migrations?
View PDF
Lessons From Red Teaming 100 Generative AI Products
View PDF
Titans: Learning to Memorize at Test Time
OpenAI’s Economic Blueprint | OpenAI
Human iPSC-derived microglial cells protect neurons from neurodegeneration in long-term cultured adhesion brain organoids - Communications Biology
ActPC-Geom: Towards Scalable Online Neural-Symbolic Learning via...
TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks
We
Sumner, A J M. (2021). Parallel Thinking: A Technique for Group Interaction and Problem Solving.
Karmakar, P., & Chattopadhyay, K. (2024). Six Thinking Hats: A Educational Technique to Enhance Cognitive Abilities in Education. Asian Journal of Education and Social Studies.
A theory of appropriateness with applications to generative...
View PDF
ActPC-Chem: Discrete Active Predictive Coding for Goal-Guided...
Metagoals Endowing Self-Modifying AGI Systems with Goal Stability...
View PDF
Could Savannah be the Next San Jose? The Downstream Effects of Large Language Models
LearnLM: Improving Gemini for Learning
View PDF
SciAgents: Automating Scientific Discovery Through Bioinspired Multi‐Agent Intelligent Graph Reasoning
GUI Agents: A Survey
Cultural Evolution of Cooperation among LLM Agents
Greenblatt, R. et al. (2024). Alignment faking in large language models.
Martınez, E., Mollica, F., & Gibson, E. Even Laypeople Use Legalese.
"In particular, recent work has revealed legal documents, including both private contracts and federal legislation, to be laden with center-embedded clauses at a rate twice as high as other genres of texts, including those aimed at an educated audience."
Deep and dynamic metabolic and structural imaging in living tissues
micros
Heschl's gyrus and the temporal pole: The cortical lateralization of language - PubMed
Agent-as-a-Judge: Evaluate Agents with Agents
View PDF