conftrace_

position coupling

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

length generalization (3) arithmetic task (1) multi-operand addition (1) k-sparse planted correlation distributions (1) predictive position coupling (1) non-autoregressive generation (1) text infilling (1) dependency structure (1) maximum-margin solution (1) discrete diffusion model (1)

Papers

Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count ICLR 2025 Flexible-length Text Infilling for Discrete Diffusion Models EMNLP 2025 The Role of Sparsity for Length Generalization in LLMs ICML 2025 Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure NeurIPS 2024