---

1. Variable-Width Transformers
   arXiv.org2026-06-16alphaXiv arXiv S2
2. Implicit Representations of Grammaticality in Language Models
   Annual Meeting of the Association for Computational Linguistics2026-05-06alphaXiv arXiv S2
3. Parallel-SFT: Improving Zero-Shot Cross-Programming-Language Transfer for Code RL
   Annual Meeting of the Association for Computational Linguistics2026-04-22alphaXiv arXiv S2
4. Translation or Recitation? Calibrating Evaluation Scores for Machine Translation of Extremely Low-Resource Languages
   Annual Meeting of the Association for Computational Linguistics2026-03-26alphaXiv arXiv S2
5. reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs
   Conference on Empirical Methods in Natural Language Processing2025-03-14alphaXiv arXiv S2
6. SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models
   International Conference on Machine Learning2025-02-13alphaXiv arXiv S2
7. The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities
   International Conference on Learning Representations2024-11-07alphaXiv arXiv S2
8. Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Spatial Reasoning
   Conference on Empirical Methods in Natural Language Processing2024-10-21alphaXiv arXiv S2
9. Ascending the Infinite Ladder: Benchmarking Spatial Deformation Reasoning in Vision-Language Models
   S2