Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks
Research
Research News
New papers, breakthroughs and academic AI research
Forensic-Aware Continual Adaptation for Image Forgery Localization
Research
Janus: Evidence-Before-Effect Sagas and Offline-Verifiable Provenance for Agentic LLMs
Research
NeuroAtlas: Benchmarking Foundation Models for Clinical EEG and Brain-Computer Interfaces
Research
Argus: Academic Integrity in the Era of Generative AI
Research
SynIL: Leveraging Synergy for Offline Imitation Learning from Imperfect Demonstration Datasets
Research
When Does Randomized Oversight Align AI Agents That Can Conceal?
Research
Near-Linear Accuracy Bounds for Moreau--Yosida Unadjusted Langevin Sampling
Research
A Parameter-Free Zeroth-Order Method with Covariance Matrix Adaptation and Effective Dimension
Research
A Rank Graduation metric for Algorithmic fairness
Research
When Correct Memory Goes Wrong: Fuzzing Persistent Memory Use in LLM Agents
Research
Distribution Matching Distillation for Continuous Diffusion Language Models
Research