 Self-Training Elicits Concise Reasoning in Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 |
 Learning to Reason from Feedback at Test-TimeAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 |
 Causal Language Modeling Can Elicit Search and Reasoning Capabilities on
Logic PuzzlesNeural Information Processing Systems (NeurIPS), 2024 |
 ALPINE: Unveiling the Planning Capability of Autoregressive Learning in
Language ModelsNeural Information Processing Systems (NeurIPS), 2024 |
 Physics of Language Models: Part 3.2, Knowledge ManipulationInternational Conference on Learning Representations (ICLR), 2023 |
 Physics of Language Models: Part 3.1, Knowledge Storage and ExtractionInternational Conference on Machine Learning (ICML), 2023 |
