language modeling

MambaExtend: A Training-Free Approach to Improve Long Context Extension of Mamba ICLR 2025 MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model ICLR 2025 Masked Diffusion Language Models with Frequency-Informed Training EMNLP 2025 MIND over Body: Adaptive Thinking using Dynamic Computation ICLR 2025 MoEP: Modular Expert Paths for Sample-Efficient Language Modeling EMNLP 2025 MossNet: Mixture of State-Space Experts is a Multi-Head Attention IJCNLP 2025 NorEval: A Norwegian Language Understanding and Generation Evaluation Benchmark ACL 2025 NOVA-63: Native Omni-lingual Versatile Assessments of 63 Disciplines EMNLP 2025 On the Power of Convolution-Augmented Transformer AAAI 2025 Optimizing Hidden Markov Language Models: An Empirical Study of Reparameterization and Initialization Techniques NAACL 2025 Overcoming Vocabulary Mismatch: Vocabulary-agnostic Teacher Guided Language Modeling ICML 2025 PrimeX: A Dataset of Worldview, Opinion, and Explanation EMNLP 2025 QuASAR: A Question-Driven Structure-Aware Approach for Table-to-Text Generation ACL 2025 Rethinking Addressing in Language Models via Contextualized Equivariant Positional Encoding ICML 2025 Sample-Efficient Language Modeling with Linear Attention and Lightweight Enhancements EMNLP 2025 Scaffold-BPE: Enhancing Byte Pair Encoding for Large Language Models with Simple and Effective Scaffold Token Removal AAAI 2025 Scaling Diffusion Language Models via Adaptation from Autoregressive Models ICLR 2025 Selective Attention Improves Transformer ICLR 2025 SIFT: Grounding LLM Reasoning in Contexts via Stickers EMNLP 2025 so much depends / upon / a whitespace: Why Whitespace Matters for Poets and LLMs EMNLP 2025 Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging ICML 2025 SpikingSSMs: Learning Long Sequences with Sparse and Parallel Spiking State Space Models AAAI 2025 Story Generation with Large Language Models for African Languages ACL 2025 Structure Language Models for Protein Conformation Generation ICLR 2025 Subword models struggle with word learning, but surprisal hides it ACL 2025