Skip to content
Tagged articles

autoregressive models

15 articles · Page 1 of 1
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Nov 16, 2026 · Artificial Intelligence

Diffusion vs. Autoregressive LLMs: Which Leaks More Training Data? Sampling Steps Dramatically Increase Memorization Risk

Aalborg University researchers show diffusion language models leak less training data than autoregressive models at equal scale, but finer sampling steps sharply raise exact memorization risk — LLaDA-8B's extraction success jumps 20× when moving from one-step to token-by-token generation.

Aalborg UniversityLLaDA-8BNeurIPS 2026
0 likes · 11 min read
Diffusion vs. Autoregressive LLMs: Which Leaks More Training Data? Sampling Steps Dramatically Increase Memorization Risk
Machine Heart
Machine Heart
Nov 15, 2026 · Artificial Intelligence

Finer Sampling Steps Boost Privacy Leakage in Diffusion LLMs, NeurIPS 2026 Finds

Aalborg University researchers present a generalized extraction framework showing diffusion language models leak less training data than autoregressive models at same scale, but finer sampling steps significantly increase exact memorization recovery, with LLaDA-8B showing a 20x increase in email extraction when switching from one-step to token-by-token generation.

LLaDANeurIPS 2026autoregressive models
0 likes · 11 min read
Finer Sampling Steps Boost Privacy Leakage in Diffusion LLMs, NeurIPS 2026 Finds
Machine Heart
Machine Heart
Nov 8, 2026 · Artificial Intelligence

LCVN: Predicting Full Navigation Paths from One Frame and Language Instruction

The paper introduces LCVN, a language-conditioned visual navigation task where models predict complete action sequences from a single starting image and a language instruction, comparing a world-model-plus-policy pipeline against a unified autoregressive model on a new dataset with three instruction styles.

LCVNNeurIPS 2026Robotics
0 likes · 11 min read
LCVN: Predicting Full Navigation Paths from One Frame and Language Instruction
PaperAgent
PaperAgent
Oct 29, 2026 · Artificial Intelligence

Lafa: Block-Level Asynchronous Flow LLMs Achieve 2.5x Throughput Over Autoregressive Models

CMU, UC Berkeley, and Amazon introduce Lafa, a continuous flow language model that converts pretrained autoregressive models into block-level asynchronous denoisers, achieving 2.02–2.54x throughput over AR baselines at 8B scale with matched quality, using under 30B tokens for adaptation.

Block-Level Asynchronous FlowCMUContinuous Flow Models
0 likes · 8 min read
Lafa: Block-Level Asynchronous Flow LLMs Achieve 2.5x Throughput Over Autoregressive Models
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Sep 1, 2026 · Artificial Intelligence

How Diffusion Language Models Deliver 5× Faster Agent Inference Than Token‑by‑Token Generation

A joint test by Diffusion Intelligence and Acrab shows that diffusion language models can speed up edge‑side agents by about five times compared to traditional autoregressive models, thanks to parallel token generation and global‑content framing, promising faster, more flexible AI experiences on devices.

AI accelerationagent inferenceautoregressive models
0 likes · 10 min read
How Diffusion Language Models Deliver 5× Faster Agent Inference Than Token‑by‑Token Generation
AIWalker
AIWalker
Apr 20, 2026 · Artificial Intelligence

How VA‑π Bridges Tokenizers and Autoregressive Generators for Pixel‑Perfect Images

VA‑π introduces a lightweight post‑training framework that uses variational inference and reinforcement learning to align tokenizers with visual autoregressive generators, achieving dramatic quality gains, extreme training efficiency, and robust pixel‑level reconstruction across diverse image generation tasks.

Pixel AlignmentPost-Trainingautoregressive models
0 likes · 14 min read
How VA‑π Bridges Tokenizers and Autoregressive Generators for Pixel‑Perfect Images
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Feb 12, 2026 · Artificial Intelligence

Fast Generation, Weak Intelligence? The Harsh Reality of Diffusion Models for Agents

A comprehensive evaluation shows that while diffusion language models achieve higher generation speed through parallel decoding, they suffer from severe causal reasoning and formatting deficiencies, lagging far behind autoregressive models on embodied and tool‑calling agent tasks.

AI-evaluationAgentic workflowsTool Calling
0 likes · 8 min read
Fast Generation, Weak Intelligence? The Harsh Reality of Diffusion Models for Agents
DataFunTalk
DataFunTalk
Jun 8, 2025 · Artificial Intelligence

Why Autoregressive Video Models Like MAGI-1 May Outperform Diffusion Approaches

The article examines the current dominance of diffusion models in commercial video generation, contrasts them with autoregressive methods, and details how the open‑source MAGI‑1 model combines both paradigms to achieve longer, more controllable video synthesis while addressing scalability and quality challenges.

AI researchMAGI-1autoregressive models
0 likes · 70 min read
Why Autoregressive Video Models Like MAGI-1 May Outperform Diffusion Approaches
AI Frontier Lectures
AI Frontier Lectures
May 28, 2025 · Artificial Intelligence

How Token‑Shuffle Enables 2048×2048 Autoregressive Image Generation

The article analyzes the Token‑Shuffle method, which reduces visual token redundancy to allow high‑resolution (2048×2048) autoregressive image generation, detailing its architecture, training pipeline, experimental results, efficiency gains, and comparisons with diffusion and other AR models.

AI researchautoregressive modelshigh-resolution image generation
0 likes · 17 min read
How Token‑Shuffle Enables 2048×2048 Autoregressive Image Generation
AIWalker
AIWalker
May 11, 2025 · Artificial Intelligence

Unified Multimodal Understanding and Generation: A 30K‑Word Survey of Recent Advances

This comprehensive survey reviews the rapid progress of multimodal understanding and text‑to‑image generation models, categorises existing unified architectures into diffusion‑based, autoregressive, and hybrid paradigms, analyses their tokenisation strategies, datasets and benchmarks, and highlights current challenges and future research directions.

BenchmarksSurveyautoregressive models
0 likes · 64 min read
Unified Multimodal Understanding and Generation: A 30K‑Word Survey of Recent Advances
AIWalker
AIWalker
Mar 11, 2025 · Artificial Intelligence

Introducing FAR: A Frequency‑Progressive Autoregressive Paradigm for Image Generation

The paper presents FAR, a frequency‑aware autoregressive framework that predicts image tokens from low‑frequency to high‑frequency components using a continuous tokenizer, and demonstrates its efficiency and quality on ImageNet and text‑to‑image benchmarks compared with existing AR and VAR methods.

AI researchFARImage Generation
0 likes · 20 min read
Introducing FAR: A Frequency‑Progressive Autoregressive Paradigm for Image Generation
AIWalker
AIWalker
Mar 10, 2025 · Artificial Intelligence

FlexVAR: Autoregressive Image Generation with Inpainting and Speed‑Quality Control

FlexVAR replaces residual prediction with direct ground‑truth prediction in visual autoregressive modeling, enabling generation of arbitrary resolutions and aspect ratios, supporting image‑to‑image tasks such as inpainting and upscaling, and offering adjustable inference steps that trade speed for quality while achieving state‑of‑the‑art FID scores.

Image GenerationVQVAEautoregressive models
0 likes · 17 min read
FlexVAR: Autoregressive Image Generation with Inpainting and Speed‑Quality Control
AIWalker
AIWalker
Jan 21, 2025 · Artificial Intelligence

PKU Introduces Next Patch Prediction for Image Generation, Cutting Training Cost to ~0.6×

The paper proposes a Next Patch Prediction (NPP) paradigm that groups image tokens into high‑density patches, enabling autoregressive models to predict patches instead of individual tokens, which reduces training cost to about 0.6× and improves ImageNet FID scores by up to 1.0 across models ranging from 100 M to 1.4 B parameters.

FID improvementImage GenerationLlamaGen
0 likes · 10 min read
PKU Introduces Next Patch Prediction for Image Generation, Cutting Training Cost to ~0.6×
DataFunTalk
DataFunTalk
Dec 5, 2024 · Artificial Intelligence

VAR: Scalable Image Generation via Next‑Scale Prediction Wins NeurIPS 2024 Best Paper

The VAR model, a Visual AutoRegressive framework that introduces a novel multi‑scale “next‑scale prediction” paradigm, dramatically improves image generation efficiency and quality, surpasses diffusion models, validates scaling laws in vision, and earned the Best Paper award at NeurIPS 2024.

Image GenerationNeurIPS2024autoregressive models
0 likes · 7 min read
VAR: Scalable Image Generation via Next‑Scale Prediction Wins NeurIPS 2024 Best Paper