news

Mar 22, 2026 We released a new preprint: Make an Offer They Can’t Refuse: Grounding Bayesian Persuasion in Real-World Dialogues without Pre-Commitment.
Jan 31, 2026 Our latest work The AI Hippocampus: How Far are We From Human Memory? is now available on TMLR (with arXiv version: 2601.09113).
Jan 26, 2026 We released a new preprint: BEDA: Belief Estimation as Probabilistic Constraints for Performing Strategic Dialogue Acts.
Jan 24, 2026 We released a new preprint: Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning.
Aug 20, 2025 Our three papers Context Faithfulness in MoE LLMs, Reinforced Query Reasoners, and Adaptive Preference Optimization were accepted to EMNLP 2025.
May 15, 2025 Our papers Look Both Ways and No Sink and ReflectEvo were accepted to ACL 2025 and ACL Findings 2025.
Feb 16, 2025 Our work TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation was accepted to ICML 2025.
Sep 21, 2024 Our paper Varying Sentence Representations via Condition-Specified Routers was accepted to EMNLP 2024.
May 16, 2024 Our papers LangSuit·E and Combining Supervised Learning and Reinforcement Learning for Multi-Label Classification Tasks with Partial Labels were accepted to ACL 2024.