Language Models

SelFusion: Self-distillation for Diffusion Language Models ACL 2026 Sigmoid Head for Quality Estimation under Language Ambiguity ACL 2026 TA-GRPO-d: Trajectory-Aware GRPO for Optimizing Denoising Trajectories in Diffusion LLMs ACL 2026 The Role of Mixed-Language Documents for Multilingual Large Language Model Pretraining ACL 2026 Towards Efficient and Effective Diffusion Language Model Inference via Semantic-Aware Adaptive Denoising ACL 2026 T⋆: Progressive Block Scaling for Masked Diffusion Language Models Through Trajectory Aware Reinforcement Learning ACL 2026 TV2TV: A Unified Framework for Interleaved Language and Video Generation CVPR 2026 When transformers learn “impossible” languages, what do they learn? CoNLL 2026 Word predictability estimates from language models are not robust to tokenizer vocabulary CoNLL 2026 You Can Have a Second Chance: Unbiased and Multi-bit Watermarking for Diffusion Language Models with Regret-based Remasking ACL 2026 Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Interspeech 2025 A Compact Model for Mathematics Problem Representations Distilled from BERT AAAI 2025 A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment ACL 2025 Analysis of Semantic and Acoustic Token Variability Across Speech, Music, and Audio Domains Interspeech 2025 Analyzing and Mitigating Inconsistency in Discrete Speech Tokens for Neural Codec Language Models ACL 2025 Analyzing the Linguistic Priors of Language Models with Synthetic Languages ACL 2025 A New Formulation of Zipf’s Meaning-Frequency Law through Contextual Diversity ACL 2025 Assessing Gender Bias of Pretrained Bangla Language Models in STEM and SHAPE Fields ACL 2025 A Text is Worth Several Tokens: Text Embedding from LLMs Secretly Aligns Well with The Key Tokens ACL 2025 BARTABSA++: Revisiting BARTABSA with Decoder LLMs ACL 2025 Beyond Text Compression: Evaluating Tokenizers Across Scales ACL 2025 Child-Directed Language Does Not Consistently Boost Syntax Learning in Language Models EMNLP 2025 Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model AAAI 2025 Comparing Behavioral Patterns of LLM and Human Tutors: A Population-level Analysis with the CIMA Dataset ACL 2025 Controllable Style Arithmetic with Language Models ACL 2025