next-token prediction

Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing CVPR 2026 AutoRegressive Generation with B-rep Holistic Token Sequence Representation CVPR 2026 Beyond Tokens: Concept-Level Training Objectives for LLMs EACL 2026 ClusterMark: Towards Robust Watermarking for Autoregressive Image Generators with Visual Token Clustering CVPR 2026 DPAR: Dynamic Patchification for Efficient Autoregressive Visual Generation CVPR 2026 Enhancing Linguistic Competence of Language Models through Pre-training with Language Learning Tasks ACL 2026 Gap-K%: Measuring Top-1 Prediction Gap for Detecting Pretraining Data ACL 2026 Language Models Struggle to Use Representations Learned In-Context ACL 2026 Next Patch Prediction for AutoRegressive Visual Generation AAAI 2026 OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens CVPR 2026 On the scaling relationship between cloze probabilities and language model next-token prediction CoNLL 2026 PPGPT: Transferring Next-Token Modeling from Language to PPG Signals AAAI 2026 Reinforcement Learning on Pre-Training Data ACL 2026 TV2TV: A Unified Framework for Interleaved Language and Video Generation CVPR 2026 Unified Vector Floorplan Generation via Markup Representation CVPR 2026 Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Interspeech 2025 All or None: Identifiable Linear Properties of Next-Token Predictors in Language Modeling AISTATS 2025 A rebuttal of two common deflationary stances against LLM cognition ACL 2025 Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation ICCV 2025 Cautious Next Token Prediction ACL 2025 Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification (extended abstract) COLT 2025 Cuckoo: An IE Free Rider Hatched by Massive Nutrition in LLM’s Nest ACL 2025 From Language to Cognition: How LLMs Outgrow the Human Language Network EMNLP 2025 Generating Physically Stable and Buildable Brick Structures from Text ICCV 2025 Generative Verifiers: Reward Modeling as Next-Token Prediction ICLR 2025