Alignment Faking Depends on the Value, Not Just the Model
Research
Research News
New papers, breakthroughs and academic AI research
Unsatz: Evaluating Scientific Discovery Without a Given Ansatz
Research
EvoGroup: A Self-Evolving Harness for Group Agents in Shared Contexts
Research
Whose startup does the AI back? An algorithm audit of reputation and demographic signals in LLM-assisted crowdfunding
Research
Language Model Augmented Decision Transformer for Multi-Task Offline Reinforcement Learning
Research
Counterexample-driven autonomous research with application to excess radiated energy in a Z-pinch
Research
Low-Rank Hierarchical Merging for Efficient Long-to-Short Reasoning
Research
Learning Directional Randers Geometry for Latent-Space Exploration
Research
FlagRot: Selective Rotation for Low-Bit KV Caches
Research
Functional-Group Knowledge Is Structured in Language Models Before It Is Spoken
Research
EMBERS: Empirically Motivated Robustness Testing of Deep Research Systems via Defect-Guided Fuzzing
Research
El Agente F\'armaco: A Scalable AI Scientist for Drug Discovery
Research