Next-Concept Modeling: Fast, Parallel Coarse-to-Fine Text Generation
cs.CL, cs.AI, cs.LG
Submitted: 2026-10-09
Updated: 2026-10-09
Code: https://github.com/HazyResearch/ncm
Project page: http://skylion007.github.io/OpenWebTextCorpus
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
- Simple and Effective Masked Diffusion Language Models
- Efficient Memory Management for Large Language Model Serving with PagedAttention
- Efficiently Scaling Transformer Inference
- Large Language Diffusion Models
- Mercury: Ultra-Fast Language Models Based on Diffusion
- DiffusionGemma Technical Report
- DFlash: Block Diffusion for Flash Speculative Decoding
- ELF: Embedded Language Flows
- Flow Map Language Models: One-step Language Modeling via Continuous Denoising
- One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling
- Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
- Fast-dLLM v2: Efficient Block-Diffusion LLM
- Neural Discrete Representation Learning
- Continuous diffusion for categorical data
- CANDI: Hybrid Discrete-Continuous Diffusion Models
- AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling
- Generating Diverse High-Fidelity Images with VQ-VAE-2
- Taming Transformers for High-Resolution Image Synthesis
- SoundStream: An End-to-End Neural Audio Codec
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering