Reader Proficiency Shapes Layer-wise Surprisal Profiles
Research
Research News
New papers, breakthroughs and academic AI research
Which papyrus HTR is good enough? Character-error-rate tolerance of four papyrological tasks on Greek texts
Research
Do Self-Evolving Skills Generalize to Held-Out Tasks?
Research
Effective Does Not Mean Useful: Conditional Functional Substitutability for Redundancy and Scaling in Transformers
Research
On the Complexity of Preference-Based Bandits
Research
Reliability-Aware Checkpoint Selection for Domain Generalization
Research
Learning Process Rewards via Reasoning State Propagation
Research
Understanding as No-Arbitrage: Bounded Dutch Books as a Definition and Training Objective for Language Models
Research
The Planning Limits of Latent World Models
Research
STAB: Specification-driven Testing for Algorithmic Bottlenecks
Research
Tissue Detection Determines False Positives in Diffusion-Based Histopathology Artifact Detection
Research
Kill-Chain Canaries: Stage-Level Tracking of Prompt Injection Across Attack Surfaces and Five Production LLMs
Research