length generalization

Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models CVPR 2026 Enhancing Auto-regressive Chain-of-Thought through Loop-Aligned Reasoning EACL 2026 Every Token Counts: Generalizing 16M Ultra-Long Context in Large Language Models ACL 2026 Lizard: An Efficient Linearization Framework for Large Language Models ACL 2026 Position Encoding with Random Float Sampling Enhances Length Generalization of Transformers EACL 2026 Universal priors: solving empirical Bayes via Bayesian inference and pretraining COLT 2026 A Formal Framework for Understanding Length Generalization in Transformers ICLR 2025 Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count ICLR 2025 Cognitive Fluctuations Enhanced Attention Network for Knowledge Tracing AAAI 2025 DCIS: Efficient Length Extrapolation of LLMs via Divide-and-Conquer Scaling Factor Search EMNLP 2025 Fourier Position Embedding: Enhancing Attention’s Periodic Extension for Length Generalization ICML 2025 Generalizing Reasoning Problems to Longer Lengths ICLR 2025 How do autoregressive transformers solve full addition? EMNLP 2025 How Do Position Encodings Affect Length Generalization? Case Studies On In-Context Function Learning AAAI 2025 Language Models Need Inductive Biases to Count Inductively ICLR 2025 Learning to Reason from Feedback at Test-Time ACL 2025 Long-Short Alignment for Effective Long-Context Modeling in LLMs ICML 2025 Looped Transformers for Length Generalization ICLR 2025 Mechanisms of Projective Composition of Diffusion Models ICML 2025 Non-Asymptotic Length Generalization ICML 2025 On the Expressiveness and Length Generalization of Selective State Space Models on Regular Languages AAAI 2025 On the Power of Convolution-Augmented Transformer AAAI 2025 Principled Understanding of Generalization for Generative Transformer Models in Arithmetic Reasoning Tasks ACL 2025 Provable Length Generalization in Sequence Prediction via Spectral Filtering ICML 2025 Robust and Unbounded Length Generalization in Autoregressive Transformer-Based Text-to-Speech NAACL 2025