AI Organizations are More Effective but Less Aligned than Individual Agents
Judy Hanwen Shen, Daniel Zhu, Siddarth Srinivasan, Henry Sleight et autres
0 citations
arXiv (Cornell University)
Jascha Sohl‐Dickstein
Informations fournies par OpenAlex. Research Africa ne déduit ni nationalité, ni poste, ni coordonnées personnelles.
161Publications signalées
11864Citations signalées
1Affiliations récentes
Les institutions déclarées
Les domaines associés
Neural Networks and ApplicationsMachine Learning and Data ClassificationAdversarial Robustness in Machine LearningGaussian Processes and Bayesian InferenceAdvanced Neural Network Applications
Les publications récentes
AI Organizations are More Effective but Less Aligned than Individual Agents
Judy Hanwen Shen, Daniel Zhu, Siddarth Srinivasan, Henry Sleight et autres
us (code pays fourni par la source)
0 citations
arXiv (Cornell University)
The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?
Alexander Hägele, Aryo Pradipta Gema, Henry Sleight, Ethan Perez et autres
1 citation
arXiv (Cornell University)
The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?
Alexander Hägele, Aryo Pradipta Gema, Henry Sleight, Ethan Perez et autres
ch, gb, us (code pays fourni par la source)
0 citations
arXiv (Cornell University)
Training Language Models on the Knowledge Graph: Insights on Hallucinations and Their Detectability
Jiri Hron, Laura Culp, Gamaleldin F. Elsayed, Rosanne Liu et autres
2 citations
arXiv (Cornell University)
Scaling Exponents Across Parameterizations and Optimizers
Katie Everett, Lechao Xiao, Mitchell Wortsman, Alexander A. Alemi et autres
1 citation
arXiv (Cornell University)
Training LLMs over Neurally Compressed Text
Brian Lester, Jaehoon Lee, Alex Alemi, Jeffrey Pennington et autres
1 citation
arXiv (Cornell University)
The boundary of neural network trainability is fractal
0 citations
arXiv (Cornell University)
Author Correction: Subtle adversarial image manipulations influence both human and machine perception
Vijay Veerabadran, Josh Goldman, Shreya Shankar, Brian Cheung et autres
us (code pays fourni par la source)
0 citations
Nature Communications
Deep unsupervised learning using nonequilibrium thermodynamics
us (code pays fourni par la source)
61 citations
Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models
Avi Singh, John D. Co-Reyes, Rishabh Agarwal, Ankesh Anand et autres
7 citations
arXiv (Cornell University)
Frontier Language Models are not Robust to Adversarial Arithmetic, or "What do I need to say so you agree 2+2=5?
C. Daniel Freeman, Laura Culp, Aaron Parisi, Maxwell L. Bileschi et autres
0 citations
arXiv (Cornell University)
BNTIC News n’est pas le producteur de ces données. Les publications sont interrogées à la demande dans Crossref, OpenAIRE, DOAJ, Europe PMC, HAL, DataCite, AfricArXiv, ROR et la Banque mondiale, sans clé d’accès. OpenAlex reste optionnel. Aucun service payant n’est nécessaire et aucune donnée externe n’est enregistrée en base. Consulter les sources et leurs limites.