September 11, 2026
← Back to resources
Papers & conversations
Journal Club.
Every week, we choose one paper—or a paper idea—as a starting point for discussion and idea generation.
September 2026
September 04, 2026
Scaling Latent Reasoning via Looped Language Models
August 2026
August 28, 2026
Problem-Induced Topologies for Multi-Agent LLM Systems: Conjectures Part II
August 21, 2026
Scalable watermarking for identifying large language model outputs
August 14, 2026
Thermodynamic efficiency of learning a rule in neural networks
August 07, 2026
Large language models for risk-of-bias assessment in randomised clinical trials—a comparative validation study
July 2026
July 17, 2026
LLMs as Noisy Channels: A Shannon Perspective on Model Capacity and Scaling Laws
July 03, 2026
Goedel-Architect: Streamlining Formal Theorem Proving with Blueprint Generation and Refinement
June 2026
June 26, 2026
Reproducing Computational Neuroscience With Agents: Rebuilding the Models Behind the Theories
June 19, 2026
AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
June 12, 2026
Problem-Induced Topologies for Multi-Agent LLM Systems: Conjectures
May 2026
May 29, 2026
KAN for Language Models
May 22, 2026
Spontaneous symmetry breaking and Goldstone modes for deep information propagation
May 15, 2026
Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior
May 08, 2026
Emotion Concepts and their Function in a Large Language Model
April 2026
April 17, 2026
Neural Computers
April 10, 2026
Towards end-to-end automation of AI research
March 2026
March 27, 2026
Toward universal steering and monitoring of AI models
March 13, 2026
Discovering Implicit Large Language Model Alignment Objectives
March 06, 2026
Emergently Misaligned Language Models Show Behavioral Self-Awareness That Shifts With Subsequent Realignment
February 2026
February 27, 2026
Are Aligned Large Language Models Still Misaligned?
February 03, 2026
Emergent Misalignment (article set)
December 2025
December 02, 2025
Mercury: Ultra-Fast Language Models Based on Diffusion
November 2025
November 11, 2025
On the Representational Capacity of Neural Language Models with Chain of Thought Reasoning
November 04, 2025
Language Models are Injective and hence Invertible
October 2025
October 21, 2025
The Curious Case of Curiosity across Human Cultures and LLMs
October 07, 2025
The Virtual Lab of AI agents designs new SARS-CoV-2 nanobodies
September 2025
September 30, 2025
AI Agents can Coordinate Beyond Human Scale
September 23, 2025
Why Language Models Hallucinate
September 02, 2025
Spin glass model of in-context learning
August 2025
August 19, 2025
Building and evaluating alignment auditing agents
August 12, 2025
Moral Foundations of Large Language Models
August 05, 2025