Sainbayar Sukhbaatar

87 papers A* 14A 2C 1Misc 1Journal 57Unranked 11

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Reasoning over mathematical objects: on-policy reward modeling and test time aggregation. CoRR Pranjal Aggarwal, Marjan Ghazvininejad, Seungone Kim, Ilia Kulikov, Jack Lanchantin, Xian Li, Tianjian Li, Bo Liu, Graham Neubig, Anaelia Ovalle, Swarnadeep Saha, Sainbayar Sukhbaatar, Sean Welleck, Jason Weston, Chenxi Whitehouse, Adina Williams, Jing Xu, Ping Yu, Weizhe Yuan, Jingyu Zhang, Wenting Zhao
2026	J	`jnl`	Self-Improving Pretraining: using post-trained models to pretrain better models. CoRR Ellen Xiaoqing Tan, Shehzaad Dhuliawala, Jing Xu, Ping Yu, Sainbayar Sukhbaatar, Jason Weston, Olga Golovneva
2025	J	`jnl`	Bridging Offline and Online Reinforcement Learning for LLMs. CoRR Jack Lanchantin, Angelica Chen, Janice Lan, Xian Li, Swarnadeep Saha, Tianlu Wang, Jing Xu, Ping Yu, Weizhe Yuan, Jason E. Weston, Sainbayar Sukhbaatar, Ilia Kulikov
2025	J	`jnl`	CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks. CoRR Ping Yu, Jack Lanchantin, Tianlu Wang, Weizhe Yuan, Olga Golovneva, Ilia Kulikov, Sainbayar Sukhbaatar, Jason Weston, Jing Xu
2025	J	`jnl`	Diverse Preference Optimization. CoRR Jack Lanchantin, Angelica Chen, Shehzaad Dhuliawala, Ping Yu, Jason Weston, Sainbayar Sukhbaatar, Ilia Kulikov
2025	A*	`conf`	Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces. ICLR DiJia Su, Sainbayar Sukhbaatar, Michael Rabbat, Yuandong Tian, Qinqing Zheng
2025	A*	`conf`	Following Length Constraints in Instructions. EMNLP Weizhe Yuan, Ilia Kulikov, Ping Yu, Kyunghyun Cho, Sainbayar Sukhbaatar, Jason E. Weston, Jing Xu
2025	A*	`conf`	Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge. EMNLP Tianhao Wu, Weizhe Yuan, Olga Golovneva, Jing Xu, Yuandong Tian, Jiantao Jiao, Jason E. Weston, Sainbayar Sukhbaatar
2025	J	`jnl`	Multi-Token Attention. CoRR Olga Golovneva, Tianlu Wang, Jason Weston, Sainbayar Sukhbaatar
2025	A*	`conf`	R.I.P.: Better Models by Survival of the Fittest Prompts. ICML Ping Yu, Weizhe Yuan, Olga Golovneva, Tianhao Wu, Sainbayar Sukhbaatar, Jason E. Weston, Jing Xu
2025	J	`jnl`	R.I.P.: Better Models by Survival of the Fittest Prompts. CoRR Ping Yu, Weizhe Yuan, Olga Golovneva, Tianhao Wu, Sainbayar Sukhbaatar, Jason Weston, Jing Xu
2025	J	`jnl`	SPICE: Self-Play In Corpus Environments Improves Reasoning. CoRR Bo Liu, Chuanyang Jin, Seungone Kim, Weizhe Yuan, Wenting Zhao, Ilia Kulikov, Xian Li, Sainbayar Sukhbaatar, Jack Lanchantin, Jason Weston
2025	J	`jnl`	SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks. CoRR Yifei Zhou, Song Jiang, Yuandong Tian, Jason Weston, Sergey Levine, Sainbayar Sukhbaatar, Xian Li
2025	J	`jnl`	Self-Challenging Language Model Agents. CoRR Yifei Zhou, Sergey Levine, Jason Weston, Xian Li, Sainbayar Sukhbaatar
2025	A*	`conf`	Self-Consistency Preference Optimization. ICML Archiki Prasad, Weizhe Yuan, Richard Yuanzhe Pang, Jing Xu, Maryam Fazel-Zarandi, Mohit Bansal, Sainbayar Sukhbaatar, Jason E. Weston, Jane Yu
2025	J	`jnl`	Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback. CoRR Yen-Ting Lin, Di Jin, Tengyu Xu, Tianhao Wu, Sainbayar Sukhbaatar, Chen Zhu, Yun He, Yun-Nung Chen, Jason Weston, Yuandong Tian, Arash Rahnama, Sinong Wang, Hao Ma, Han Fang
2025	J	`jnl`	StepWiser: Stepwise Generative Judges for Wiser Reasoning. CoRR Wei Xiong, Wenting Zhao, Weizhe Yuan, Olga Golovneva, Tong Zhang, Jason Weston, Sainbayar Sukhbaatar
2025	J	`jnl`	Stochastic activations. CoRR Maria Lomeli, Matthijs Douze, Gergely Szilvasy, Loïc Cabannes, Jade Copet, Sainbayar Sukhbaatar, Jason Weston, Gabriel Synnaeve, Pierre-Emmanuel Mazaré, Hervé Jégou
2025	A*	`conf`	Thinking LLMs: General Instruction Following with Thought Generation. ICML Tianhao Wu, Janice Lan, Weizhe Yuan, Jiantao Jiao, Jason E. Weston, Sainbayar Sukhbaatar
2024	J	`jnl`	Adaptive Decoding via Latent Preference Optimization. CoRR Shehzaad Dhuliawala, Ilia Kulikov, Ping Yu, Asli Celikyilmaz, Jason Weston, Sainbayar Sukhbaatar, Jack Lanchantin
2024	J	`jnl`	Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping. CoRR Lucas Lehnert, Sainbayar Sukhbaatar, Paul McVay, Michael Rabbat, Yuandong Tian
2024	J	`jnl`	Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM. CoRR Sainbayar Sukhbaatar, Olga Golovneva, Vasu Sharma, Hu Xu, Xi Victoria Lin, Baptiste Rozière, Jacob Kahn, Daniel Li, Wen-tau Yih, Jason Weston, Xian Li
2024	—	`conf`	Compositional Interfaces for Compositional Generalization. CoLLAs Jelena Luketina, Jack Lanchantin, Sainbayar Sukhbaatar, Arthur Szlam
2024	J	`jnl`	Contextual Position Encoding: Learning to Count What's Important. CoRR Olga Golovneva, Tianlu Wang, Jason Weston, Sainbayar Sukhbaatar
2024	J	`jnl`	Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces. CoRR DiJia Su, Sainbayar Sukhbaatar, Michael Rabbat, Yuandong Tian, Qinqing Zheng
2024	J	`jnl`	Following Length Constraints in Instructions. CoRR Weizhe Yuan, Ilia Kulikov, Ping Yu, Kyunghyun Cho, Sainbayar Sukhbaatar, Jason Weston, Jing Xu
2024	A*	`conf`	Iterative Reasoning Preference Optimization. NeurIPS Richard Yuanzhe Pang, Weizhe Yuan, He He, Kyunghyun Cho, Sainbayar Sukhbaatar, Jason Weston
2024	J	`jnl`	Iterative Reasoning Preference Optimization. CoRR Richard Yuanzhe Pang, Weizhe Yuan, Kyunghyun Cho, He He, Sainbayar Sukhbaatar, Jason Weston
2024	J	`jnl`	Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge. CoRR Tianhao Wu, Weizhe Yuan, Olga Golovneva, Jing Xu, Yuandong Tian, Jiantao Jiao, Jason Weston, Sainbayar Sukhbaatar
2024	J	`jnl`	Reverse Training to Nurse the Reversal Curse. CoRR Olga Golovneva, Zeyuan Allen-Zhu, Jason Weston, Sainbayar Sukhbaatar
2024	J	`jnl`	Self-Consistency Preference Optimization. CoRR Archiki Prasad, Weizhe Yuan, Richard Yuanzhe Pang, Jing Xu, Maryam Fazel-Zarandi, Mohit Bansal, Sainbayar Sukhbaatar, Jason Weston, Jane A. Yu
2024	A*	`conf`	Self-Rewarding Language Models. ICML Weizhe Yuan, Richard Yuanzhe Pang, Kyunghyun Cho, Xian Li, Sainbayar Sukhbaatar, Jing Xu, Jason Weston
2024	J	`jnl`	Self-Rewarding Language Models. CoRR Weizhe Yuan, Richard Yuanzhe Pang, Kyunghyun Cho, Sainbayar Sukhbaatar, Jing Xu, Jason Weston
2024	J	`jnl`	Teaching Large Language Models to Reason with Reinforcement Learning. CoRR Alex Havrilla, Yuqing Du, Sharath Chandra Raparthy, Christoforos Nalmpantis, Jane Dwivedi-Yu, Maksym Zhuravinskyi, Eric Hambro, Sainbayar Sukhbaatar, Roberta Raileanu
2024	J	`jnl`	Thinking LLMs: General Instruction Following with Thought Generation. CoRR Tianhao Wu, Janice Lan, Weizhe Yuan, Jiantao Jiao, Jason Weston, Sainbayar Sukhbaatar
2024	J	`jnl`	Training Large Language Models to Reason in a Continuous Latent Space. CoRR Shibo Hao, Sainbayar Sukhbaatar, DiJia Su, Xian Li, Zhiting Hu, Jason Weston, Yuandong Tian
2023	A*	`conf`	A Data Source for Reasoning Embodied Agents. AAAI Jack Lanchantin, Sainbayar Sukhbaatar, Gabriel Synnaeve, Yuxuan Sun, Kavya Srinet, Arthur Szlam
2023	J	`jnl`	A Data Source for Reasoning Embodied Agents. CoRR Jack Lanchantin, Sainbayar Sukhbaatar, Gabriel Synnaeve, Yuxuan Sun, Kavya Srinet, Arthur Szlam
2023	J	`jnl`	Improving Open Language Models by Learning from Organic Interactions. CoRR Jing Xu, Da Ju, Joshua Lane, Mojtaba Komeili, Eric Michael Smith, Megan Ung, Morteza Behrooz, William Ngan, Rashel Moritz, Sainbayar Sukhbaatar, Y-Lan Boureau, Jason Weston, Kurt Shuster
2023	J	`jnl`	Large Language Model Programs. CoRR Imanol Schlag, Sainbayar Sukhbaatar, Asli Celikyilmaz, Wen-tau Yih, Jason Weston, Jürgen Schmidhuber, Xian Li
2023	J	`jnl`	Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping. CoRR Lina Mezghani, Sainbayar Sukhbaatar, Piotr Bojanowski, Alessandro Lazaric, Karteek Alahari
2023	A*	`conf`	Learning to Reason and Memorize with Self-Notes. NeurIPS Jack Lanchantin, Shubham Toshniwal, Jason Weston, Arthur Szlam, Sainbayar Sukhbaatar
2023	J	`jnl`	Learning to Reason and Memorize with Self-Notes. CoRR Jack Lanchantin, Shubham Toshniwal, Jason Weston, Arthur Szlam, Sainbayar Sukhbaatar
2023	J	`jnl`	MINOTAUR: Multi-task Video Grounding From Multimodal Queries. CoRR Raghav Goyal, Effrosyni Mavroudi, Xitong Yang, Sainbayar Sukhbaatar, Leonid Sigal, Matt Feiszli, Lorenzo Torresani, Du Tran
2023	J	`jnl`	Some things are more CRINGE than others: Preference Optimization with the Pairwise Cringe Loss. CoRR Jing Xu, Andrew Lee, Sainbayar Sukhbaatar, Jason Weston
2023	J	`jnl`	System 2 Attention (is something you might need too). CoRR Jason Weston, Sainbayar Sukhbaatar
2023	—	`conf`	The CRINGE Loss: Learning what language not to model. ACL (1) Leonard Adolphs, Tianyu Gao, Jing Xu, Kurt Shuster, Sainbayar Sukhbaatar, Jason Weston
2023	J	`jnl`	Think Before You Act: Unified Policy for Interleaving Language Reasoning with Actions. CoRR Lina Mezghani, Piotr Bojanowski, Karteek Alahari, Sainbayar Sukhbaatar
2022	J	`jnl`	DIRECTOR: Generator-Classifiers For Supervised Language Modeling. CoRR Kushal Arora, Kurt Shuster, Sainbayar Sukhbaatar, Jason Weston
2022	—	`conf`	Director: Generator-Classifiers For Supervised Language Modeling. AACL/IJCNLP (1) Kushal Arora, Kurt Shuster, Sainbayar Sukhbaatar, Jason Weston
2022	Misc	`conf`	Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping. CoRL Lina Mezghani, Sainbayar Sukhbaatar, Piotr Bojanowski, Alessandro Lazaric, Karteek Alahari
2022	A	`conf`	Memory-Augmented Reinforcement Learning for Image-Goal Navigation. IROS Lina Mezghani, Sainbayar Sukhbaatar, Thibaut Lavril, Oleksandr Maksymets, Dhruv Batra, Piotr Bojanowski, Karteek Alahari
2022	A*	`conf`	Staircase Attention for Recurrent Processing of Sequences. NeurIPS Da Ju, Stephen Roller, Sainbayar Sukhbaatar, Jason Weston
2022	J	`jnl`	Temporal Abstractions-Augmented Temporally Contrastive Learning: An Alternative to the Laplacian in RL. CoRR Akram Erraqabi, Marlos C. Machado, Mingde Zhao, Sainbayar Sukhbaatar, Alessandro Lazaric, Ludovic Denoyer, Yoshua Bengio
2022	A	`conf`	Temporal abstractions-augmented temporally contrastive learning: An alternative to the Laplacian in RL. UAI Akram Erraqabi, Marlos C. Machado, Mingde Zhao, Sainbayar Sukhbaatar, Alessandro Lazaric, Ludovic Denoyer, Yoshua Bengio
2022	J	`jnl`	The CRINGE Loss: Learning what language not to model. CoRR Leonard Adolphs, Tianyu Gao, Jing Xu, Kurt Shuster, Sainbayar Sukhbaatar, Jason Weston
2022	J	`jnl`	Walk the Random Walk: Learning to Discover and Reach Goals Without Supervision. CoRR Lina Mezghani, Sainbayar Sukhbaatar, Piotr Bojanowski, Karteek Alahari
2021	A*	`conf`	Hash Layers For Large Sparse Models. NeurIPS Stephen Roller, Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston
2021	J	`jnl`	Hash Layers For Large Sparse Models. CoRR Stephen Roller, Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston
2021	J	`jnl`	Memory-Augmented Reinforcement Learning for Image-Goal Navigation. CoRR Lina Mezghani, Sainbayar Sukhbaatar, Thibaut Lavril, Oleksandr Maksymets, Dhruv Batra, Piotr Bojanowski, Karteek Alahari
2021	A*	`conf`	Not All Memories are Created Equal: Learning to Forget by Expiring. ICML Sainbayar Sukhbaatar, Da Ju, Spencer Poff, Stephen Roller, Arthur Szlam, Jason Weston, Angela Fan
2021	J	`jnl`	Not All Memories are Created Equal: Learning to Forget by Expiring. CoRR Sainbayar Sukhbaatar, Da Ju, Spencer Poff, Stephen Roller, Arthur Szlam, Jason Weston, Angela Fan
2021	J	`jnl`	Staircase Attention for Recurrent Processing of Sequences. CoRR Da Ju, Stephen Roller, Sainbayar Sukhbaatar, Jason Weston
2020	J	`jnl`	Accessing Higher-level Representations in Sequential Transformers with Feedback Memory. CoRR Angela Fan, Thibaut Lavril, Edouard Grave, Armand Joulin, Sainbayar Sukhbaatar
2020	J	`jnl`	Learning to Visually Navigate in Photorealistic Environments Without any Supervision. CoRR Lina Mezghani, Sainbayar Sukhbaatar, Arthur Szlam, Armand Joulin, Piotr Bojanowski
2019	—	`conf`	Adaptive Attention Span in Transformers. ACL (1) Sainbayar Sukhbaatar, Edouard Grave, Piotr Bojanowski, Armand Joulin
2019	J	`jnl`	Adaptive Attention Span in Transformers. CoRR Sainbayar Sukhbaatar, Edouard Grave, Piotr Bojanowski, Armand Joulin
2019	J	`jnl`	Augmenting Self-attention with Persistent Memory. CoRR Sainbayar Sukhbaatar, Edouard Grave, Guillaume Lample, Hervé Jégou, Armand Joulin
2019	—	`conf`	Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks. ICLR (Poster) Amanpreet Singh, Tushar Jain, Sainbayar Sukhbaatar
2019	—	`conf`	Training Hybrid Language Models by Marginalizing over Segmentations. ACL (1) Edouard Grave, Sainbayar Sukhbaatar, Piotr Bojanowski, Armand Joulin
2018	A*	`conf`	Composable Planning with Attributes. ICML Amy Zhang, Sainbayar Sukhbaatar, Adam Lerer, Arthur Szlam, Rob Fergus
2018	J	`jnl`	Composable Planning with Attributes. CoRR Amy Zhang, Adam Lerer, Sainbayar Sukhbaatar, Rob Fergus, Arthur Szlam
2018	—	`—`	Elements of Intelligence: Memory, Communication and Intrinsic Motivation. Sainbayar Sukhbaatar
2018	—	`conf`	Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play. ICLR (Poster) Sainbayar Sukhbaatar, Zeming Lin, Ilya Kostrikov, Gabriel Synnaeve, Arthur Szlam, Rob Fergus
2018	J	`jnl`	Learning Goal Embeddings via Self-Play for Hierarchical Reinforcement Learning. CoRR Sainbayar Sukhbaatar, Emily Denton, Arthur Szlam, Rob Fergus
2018	J	`jnl`	Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks. CoRR Amanpreet Singh, Tushar Jain, Sainbayar Sukhbaatar
2018	J	`jnl`	Planning with Arithmetic and Geometric Attributes. CoRR David Folqué, Sainbayar Sukhbaatar, Arthur Szlam, Joan Bruna
2017	J	`jnl`	Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play. CoRR Sainbayar Sukhbaatar, Ilya Kostrikov, Arthur Szlam, Rob Fergus
2016	—	`conf`	Learning Multiagent Communication with Backpropagation. NIPS Sainbayar Sukhbaatar, Arthur Szlam, Rob Fergus
2016	J	`jnl`	Learning Multiagent Communication with Backpropagation. CoRR Sainbayar Sukhbaatar, Arthur Szlam, Rob Fergus
2015	—	`conf`	End-To-End Memory Networks. NIPS Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston, Rob Fergus
2015	—	`conf`	Learning from Noisy Labels with Deep Neural Networks. ICLR (Workshop) Sainbayar Sukhbaatar, Rob Fergus
2015	J	`jnl`	MazeBase: A Sandbox for Learning from Games. CoRR Sainbayar Sukhbaatar, Arthur Szlam, Gabriel Synnaeve, Soumith Chintala, Rob Fergus
2015	J	`jnl`	Simple Baseline for Visual Question Answering. CoRR Bolei Zhou, Yuandong Tian, Sainbayar Sukhbaatar, Arthur Szlam, Rob Fergus
2015	J	`jnl`	Weakly Supervised Memory Networks. CoRR Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston, Rob Fergus
2013	—	`conf`	Auto-pooling: Learning to Improve Invariance of Image Features from Image Sequences ICLR (Workshop Poster) Sainbayar Sukhbaatar, Takaki Makino, Kazuyuki Aihara
2011	C	`conf`	Robust Generation of Dynamical Patterns in Human Motion by a Deep Belief Nets. ACML Sainbayar Sukhbaatar, Takaki Makino, Kazuyuki Aihara, Takashi Chikayama