Schaeffer, Rylan
- Are Emergent Abilities of Large Language Models a Mirage?
2023/04/28 by Rylan Schaeffer, Brando Miranda, Schaeffer, Rylan +3 · 20 voices · 77 citations
Computer Science · #Explainable Artificial Intelligence (XAI) #Natural Language Processing Techniques #Topic Modeling #cs.AI #cs.LG
- Pretraining on the Test Set Is All You Need
2023/09/13 by Rylan Schaeffer, Schaeffer, Rylan · 16 voices · 6 citations
#cs.CL #cs.AI
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
2025/07/07 by Gheorghe Comanici, Comanici, Gheorghe, Eric Bieber +6844 · 8 voices · 1349 citations
#cs.CL #cs.AI
- Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data
2024/04/01 by Matthias Gerstgrasser, Rylan Schaeffer, Gerstgrasser, Matthias +26 · 16 voices · 31 citations
Computer Science · #Semantic Web and Ontologies #cs.AI #cs.CL #cs.ET #cs.LG #stat.ML
- Best-of-N Jailbreaking
2024/12/04 by John Hughes, John D. Hughes, Hughes, John +18 · 17 voices · 14 citations
Computer Science · #Digital and Cyber Forensics #cs.AI #cs.CL #cs.LG
- Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle
2023/03/24 by Rylan Schaeffer, Mikail Khona, Schaeffer, Rylan +13 · 4 voices · 4 citations
#cs.LG #stat.ML
- DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
2023/06/20 by Boxin Wang, Wang, Boxin, Weixin Chen +35 · 58 citations
Computer Science · Medicine · Social Sciences · #Adversarial Robustness in Machine Learning #Artificial Intelligence in Healthcare and Education #Ethics and Social Impacts of AI
- Collapse or Thrive? Perils and Promises of Synthetic Data in a Self-Generating World
2024/10/22 by Joshua Kazdan, Rylan Schaeffer, Kazdan, Joshua +11 · 2 voices · 9 citations
#cs.LG #cs.AI
- Position: Machine Learning Conferences Should Establish a "Refutations and Critiques" Track
2025/06/24 by Rylan Schaeffer, Schaeffer, Rylan, Joshua Kazdan +25 · 2 voices · 2 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computers and Society (cs.CY) #FOS: Computer and information sciences #Machine Learning (cs.LG) #cs.AI #cs.CL #cs.CY #cs.LG
- Investigating Data Contamination for Pre-training Language Models
2024/01/11 by Minhao Jiang, Ken Ziyu Liu, Jiang, Minhao +11 · 11 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling
- Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?
2024/06/06 by Rylan Schaeffer, Schaeffer, Rylan, Hailey Schoelkopf +15 · 13 citations
Computer Science · #Explainable Artificial Intelligence (XAI)
- Quantifying Variance in Evaluation Benchmarks
2024/06/14 by Lovish Madaan, Madaan, Lovish, Aaditya K. Singh +13 · 11 citations
Decision Sciences · #Artificial Intelligence (cs.AI) #Evaluation and Performance Assessment #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Failures to Find Transferable Image Jailbreaks Between Vision-Language Models
2024/07/21 by Rylan Schaeffer, Schaeffer, Rylan, Dan Valentine +27 · 9 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #Digital Media Forensic Detection #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Beyond Scale: The Diversity Coefficient as a Data Quality Metric for Variability in Natural Language Data
2023/06/24 by Brando Miranda, A. Lee, Miranda, Brando +7 · 6 citations
Computer Science · Decision Sciences · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Data Quality and Management #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Neural and Evolutionary Computing (cs.NE) #Topic Modeling
- What Causes Polysemanticity? An Alternative Origin Story of Mixed Selectivity from Incidental Causes
2023/12/05 by Lecomte, Victor, Thaman, Kushal, Schaeffer, Rylan +3 · 6 citations
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE)
- Deceptive Alignment Monitoring
2023/07/20 by Carranza, Andres, Pai, Dhruv, Schaeffer, Rylan +2 · 4 citations
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- How Do Large Language Monkeys Get Their Power (Laws)?
2025/02/24 by Rylan Schaeffer, Joshua Kazdan, Schaeffer, Rylan +14 · 10 citations
Social Sciences · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Language and cultural evolution #Machine Learning (cs.LG)
- Self-Supervised Learning of Representations for Space Generates Multi-Modular Grid Cells
2023/11/04 by Rylan Schaeffer, Mikail Khona, Schaeffer, Rylan +9 · 5 citations
Biochemistry, Genetics and Molecular Biology · Neuroscience · #Single-cell and spatial transcriptomics #Cell Image Analysis Techniques #Neural dynamics and brain function
- Position: Model Collapse Does Not Mean What You Think
2025/03/05 by Rylan Schaeffer, Schaeffer, Rylan, Joshua Kazdan +5 · 6 citations
Computer Science · Social Sciences · #Generative Adversarial Networks and Image Synthesis #Computational and Text Analysis Methods #Explainable Artificial Intelligence (XAI)
- Invalid Logic, Equivalent Gains: The Bizarreness of Reasoning in Language Model Prompting
2023/07/20 by Schaeffer, Rylan, Pistunova, Kateryna, Khanna, Samar +2 · 1 citation
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences
- No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms
2025/02/26 by Kazdan, Joshua, Puri, Abhay, Schaeffer, Rylan +5 · 1 citation
#Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Jailbreak Defense in a Narrow Domain: Limitations of Existing Methods and a New Transcript-Classifier Approach
2024/12/03 by Tony T. Wang, John Hughes, Wang, Tony T. +17 · 1 voice · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #cs.AI #cs.CL #cs.CR #cs.LG