#icml-2026
- GRAM: Modular Pretraining Makes Dual-Use Knowledge Physically Removable from AI Models AE Studio / Anthropic research
- The Deterministic Horizon: Information-Theoretic Proof That Extended CoT Fails and Tool Use Is Necessary research
- PerceptionRubrics: Atomic Rubric Evaluation Reveals 8% Perception Gap Between Open and Closed Models research
- Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence research
- Structural Origin of Attention Sink: Variance Discrepancy, Super Neurons, and a Fix research
- RL Post-Training Actively Builds Compositional Reasoning Strategies, Not Just Amplifies Base Skills research