Roller, Stephen
- OPT: Open Pre-trained Transformer Language Models
2022/05/02 by Susan Zhang, Zhang, Susan, Stephen Roller +35 · 2 voices · 266 citations
#cs.CL #cs.LG
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
2025/07/07 by Gheorghe Comanici, Eric Bieber, Comanici, Gheorghe +6844 · 8 voices · 1372 citations
#cs.CL #cs.AI
- A Theory on Adam Instability in Large-Scale Machine Learning
2023/04/19 by Igor Molybog, Molybog, Igor, Peter J. Albert +33 · 1 voice · 3 citations
Computer Science · #Computational Physics and Python Applications #Neural Networks and Applications #Topic Modeling #cs.AI #cs.LG #math.OC
- Neural Text Generation with Unlikelihood Training
2019/08/12 by Sean Welleck, Welleck, Sean, Ilia Kulikov +9 · 39 citations
Computer Science · #Advanced Text Analysis Techniques #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Natural Language Processing Techniques #Topic Modeling
- Hash Layers For Large Sparse Models
2021/06/08 by Stephen Roller, Roller, Stephen, Sainbayar Sukhbaatar +5 · 1 voice · 22 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Multimodal Machine Learning Applications #Topic Modeling #cs.CL #cs.LG
- Recipes for building an open-domain chatbot
2020/04/28 by Roller, Stephen, Dinan, Emily, Goyal, Naman +9 · 17 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences
- Wizard of Wikipedia: Knowledge-Powered Conversational agents
2018/11/03 by Emily Dinan, Dinan, Emily, Stephen Roller +9 · 13 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling
- Scaling Laws for Generative Mixed-Modal Language Models
2023/01/10 by Armen Aghajanyan, Lili Yu, Aghajanyan, Armen +17 · 14 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 #Speech Recognition and Synthesis #Topic Modeling
- BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage
2022/08/05 by Shuster, Kurt, Xu, Jing, Komeili, Mojtaba +15 · 11 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences
- What makes a good conversation? How controllable attributes affect human judgments
2019/02/22 by See, Abigail, Roller, Stephen, Kiela, Douwe +1 · 6 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences
- Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion
2022/03/24 by Shuster, Kurt, Komeili, Mojtaba, Adolphs, Leonard +3 · 7 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences
- Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings
2019/02/03 by Le, Matt, Roller, Stephen, Papaxanthos, Laetitia +2 · 4 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences
- Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training
2019/11/10 by Li, Margaret, Roller, Stephen, Kulikov, Ilia +4 · 4 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences
- Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions
2020/06/22 by Stephen Roller, Y-Lan Boureau, Roller, Stephen +29 · 4 citations
Computer Science · #AI in Service Interactions #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multi-Agent Systems and Negotiation #Topic Modeling
- Adding Chit-Chat to Enhance Task-Oriented Dialogues
2020/10/24 by Sun, Kai, Moon, Seungwhan, Crook, Paul +7 · 4 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences
- Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents
2022/01/12 by Smith, Eric Michael, Hsu, Orion, Qian, Rebecca +3 · 4 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences
- Distributional Modeling on a Diet: One-shot Word Learning from Text Only
2017/04/14 by Su Wang, Stephen Roller, Wang, Su +3 · 2 citations
Computer Science · #Computation and Language (cs.CL) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling
- Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora
2018/06/08 by Roller, Stephen, Kiela, Douwe, Nickel, Maximilian · 2 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences
- Leveraging Implicit Feedback from Deployment Data in Dialogue
2023/07/26 by Richard Yuanzhe Pang, Stephen Roller, Pang, Richard Yuanzhe +7 · 3 citations
Computer Science · #AI in Service Interactions #Computation and Language (cs.CL) #FOS: Computer and information sciences #Speech and dialogue systems #Topic Modeling
- ACUTE-EVAL: Improved Dialogue Evaluation with Optimized Questions and Multi-turn Comparisons
2019/09/06 by Li, Margaret, Weston, Jason, Roller, Stephen · 1 citation
#Computation and Language (cs.CL) #FOS: Computer and information sciences
- Not All Memories are Created Equal: Learning to Forget by Expiring
2021/05/13 by Sainbayar Sukhbaatar, Da Young Ju, Sukhbaatar, Sainbayar +11 · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling
- Teaching Models new APIs: Domain-Agnostic Simulators for Task Oriented Dialogue
2021/10/13 by Chen, Moya, Crook, Paul A., Roller, Stephen · 1 citation
#Computation and Language (cs.CL) #FOS: Computer and information sciences