---

1. Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
   2026-06-12alphaXiv arXiv S2
2. Compute Optimal Tokenization
   arXiv.org2026-05-02alphaXiv arXiv S2
3. Are you going to finish that? A Practical Study of the Partial Token Problem
   2026-01-30alphaXiv arXiv S2
4. When One LLM Drools, Multi-LLM Collaboration Rules
   Annual Meeting of the Association for Computational Linguistics2026S2
5. Are you going to finish that? A Practical Study of the Tokenization Boundary Problem
   arXiv.org2026S2
6. Olmo 3
   2025-12-15alphaXiv arXiv S2
7. Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations
   Advances in Neural Information Processing Systems 382025-06-23alphaXiv arXiv S2
8. Sampling from Your Language Model One Byte at a Time
   arXiv.org2025-06-17alphaXiv arXiv S2
9. LLAMAPIE: Proactive In-Ear Conversation Assistants
   Annual Meeting of the Association for Computational Linguistics2025-05-07alphaXiv arXiv S2
10. SuperBPE: Space Travel for Language Models
    arXiv.org2025-03-17alphaXiv arXiv S2
11. When One LLM Drools, Multi-LLM Collaboration Rules
    arXiv.org2025-02-06alphaXiv arXiv S2
12. Olmo 3
    arXiv.org2025S2
13. TÜLU 3: Pushing Frontiers in Open Language Model Post-Training
    arXiv.org2024-11-22alphaXiv arXiv S2
14. Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Models
    North American Chapter of the Association for Computational Linguistics2024-08-12alphaXiv arXiv S2
15. Data Mixture Inference Attack: BPE Tokenizers Reveal Training Data Compositions
    Neural Information Processing Systems2024S2
16. Data Mixture Inference Attack: BPE Tokenizers Reveal Training Data Compositions
    Advances in Neural Information Processing Systems 372024S2
17. Boyd-Graber . A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users . Empirical Methods in Natural Language Processing
    S2
18. Exploring Personalization Shifts in Representation Space of LLMs
    S2
19. Reliability Scales Inversely: Bigger Models Compound Mistakes Faster via a Hidden Auto-Regressive Risk Regime
    S2