RankE co-evolves AR policy and decoder via alternating ranking optimization, improving both FID and CLIP scores on LlamaGen-XL and Janus-Pro where policy-only RL degrades FID.
hub Mixed citations
Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
Mixed citation behavior. Most common role is background (47%).
76
Pith papers citing it
Background
47% of classified citations
abstract
We introduce LlamaGen, a new family of image generation models that apply original ``next-token prediction'' paradigm of large language models to visual generation domain. It is an affirmative answer to whether vanilla autoregressive models, e.g., Llama, without inductive biases on visual signals can achieve state-of-the-art image generation performance if scaling properly. We reexamine design spaces of image tokenizers, scalability properties of image generation models, and their training data quality. The outcome of this exploration consists of: (1) An image tokenizer with downsample ratio of 16, reconstruction quality of 0.94 rFID and codebook usage of 97% on ImageNet benchmark. (2) A series of class-conditional image generation models ranging from 111M to 3.1B parameters, achieving 2.18 FID on ImageNet 256x256 benchmarks, outperforming the popular diffusion models such as LDM, DiT. (3) A text-conditional image generation model with 775M parameters, from two-stage training on LAION-COCO and high aesthetics quality images, demonstrating competitive performance of visual quality and text alignment. (4) We verify the effectiveness of LLM serving frameworks in optimizing the inference speed of image generation models and achieve 326% - 414% speedup. We release all models and codes to facilitate open-source community of visual generation and multimodal foundation models.
hub tools
citation-role summary
background 10
baseline 6
method 3
citation-polarity summary
claims ledger
- abstract We introduce LlamaGen, a new family of image generation models that apply original ``next-token prediction'' paradigm of large language models to visual generation domain. It is an affirmative answer to whether vanilla autoregressive models, e.g., Llama, without inductive biases on visual signals can achieve state-of-the-art image generation performance if scaling properly. We reexamine design spaces of image tokenizers, scalability properties of image generation models, and their training data quality. The outcome of this exploration consists of: (1) An image tokenizer with downsample ratio o
co-cited works
representative citing papers
HeadKV compresses KV cache for autoregressive image generation via head-aware budget allocation, early head-type identification from consistent patterns, and stratified token eviction.
ToBAC is the first backdoor attack on unified autoregressive models, using data or model poisoning to make triggers elicit cross-modal malicious behavior in text and image generation.
Uni-AdGen uses a unified autoregressive framework with foreground perception, instruction tuning, and coarse-to-fine preference modules to generate personalized image-text ads from noisy user behaviors, outperforming baselines on a new PAd1M dataset.
ExtraVAR enables resolution extrapolation in visual autoregressive models by stage-aware RoPE remapping and entropy-driven attention scaling, suppressing repetition and detail loss.
NTM models each generative reverse step as a conditional normalizing flow with a hybrid shallow-deep architecture, enabling exact-likelihood training and strong four-step sampling performance on text-to-image tasks.
Prologue introduces dedicated prologue tokens to decouple generation and reconstruction in AR visual models, significantly improving generation FID scores on ImageNet while maintaining reconstruction quality.
BEAT tokenizes symbolic music by uniform beat steps with sparse per-beat pitch encodings, producing higher quality and more coherent music continuation and accompaniment than event-based tokenizations.
Masked Logit Nudging aligns visual autoregressive model logits with source token maps under target prompts inside cross-attention masks, delivering top image editing results on PIE benchmarks and strong reconstructions on COCO and OpenImages while running faster than diffusion approaches.
Delta tokens compress VFM feature differences into single tokens, enabling a lightweight generative world model that predicts diverse futures with far lower compute than existing approaches.
Drift-AR achieves 3.8-5.5x speedup in AR-diffusion image models by using entropy to enable entropy-informed speculative decoding and single-step (1-NFE) anti-symmetric drifting decoding.
SOLACE improves text-to-image generation by using intrinsic self-confidence rewards from noise reconstruction accuracy during reinforcement learning post-training without external supervision.
GAR-Font is a global-aware autoregressive framework for multimodal few-shot font generation that adds global tokenization, a language-style adapter, and post-refinement to improve style coherence over patch-based methods.
VVS accelerates visual AR image generation by partially skipping verifications in speculative decoding, achieving 2.8x fewer target forward passes while preserving competitive quality.
Derives exact guidance transition rates for discrete flow matching models that require only one model evaluation per sampling step and unify prior approximation-based methods.
Phoneme-guided autoregressive framework for talking-head animation that reduces inter-frame flicker via causal keyframe generation and timestamp-aware interpolation, outperforming diffusion baselines on FVD and a new BG-Flicker metric.
PacTure uses view packing and next-scale autoregressive prediction to generate consistent multi-view PBR textures faster than prior sequential or cross-attention methods.
OAR distills specialized generation orders from any-order AR models via self-distillation, improving FID from 2.39 to 2.17 on ImageNet 256x256 while preserving multi-task flexibility.
Text-to-image models show significant limitations in integrating world knowledge, as measured by the new WISE benchmark and WiScore metric across 20 models.
T2I-FactualBench is a new three-tier benchmark for factuality of knowledge-intensive concepts in T2I models, using multi-round VQA evaluation to show SOTA models need improvement.
Janus decouples visual encoding into task-specific pathways inside a single autoregressive transformer to unify multimodal understanding and generation while outperforming earlier unified models.
PiD is a pixel diffusion decoder that performs latent-to-pixel conversion and 4-8x upsampling in one generative step, enabling early stopping of latent diffusion and achieving sub-second 2048x2048 decoding with claimed better fidelity than cascaded baselines.
VFMTok builds a generalist image tokenizer on frozen VFMs using adaptive quantization and semantic alignment, delivering gFID 1.36 for autoregressive and 1.25 for continuous generation on ImageNet with 3x faster convergence.
HierEdit enables efficient 4K image editing via low-resolution proxy localization followed by hierarchical local-window diffusion that reuses unaltered regions as conditioning.
citing papers explorer
-
RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution
RankE co-evolves AR policy and decoder via alternating ranking optimization, improving both FID and CLIP scores on LlamaGen-XL and Janus-Pro where policy-only RL degrades FID.
-
Head-Aware Key-Value Compression for Efficient Autoregressive Image Generation
HeadKV compresses KV cache for autoregressive image generation via head-aware budget allocation, early head-type identification from consistent patterns, and stratified token eviction.
-
Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models
ToBAC is the first backdoor attack on unified autoregressive models, using data or model poisoning to make triggers elicit cross-modal malicious behavior in text and image generation.
-
Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models
Uni-AdGen uses a unified autoregressive framework with foreground perception, instruction tuning, and coarse-to-fine preference modules to generate personalized image-text ads from noisy user behaviors, outperforming baselines on a new PAd1M dataset.
-
ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models
ExtraVAR enables resolution extrapolation in visual autoregressive models by stage-aware RoPE remapping and entropy-driven attention scaling, suppressing repetition and detail loss.
-
Normalizing Trajectory Models
NTM models each generative reverse step as a conditional normalizing flow with a hybrid shallow-deep architecture, enabling exact-likelihood training and strong four-step sampling performance on text-to-image tasks.
-
Autoregressive Visual Generation Needs a Prologue
Prologue introduces dedicated prologue tokens to decouple generation and reconstruction in AR visual models, significantly improving generation FID scores on ImageNet while maintaining reconstruction quality.
-
BEAT: Tokenizing and Generating Symbolic Music by Uniform Temporal Steps
BEAT tokenizes symbolic music by uniform beat steps with sparse per-beat pitch encodings, producing higher quality and more coherent music continuation and accompaniment than event-based tokenizations.
-
Prompt-Guided Image Editing with Masked Logit Nudging in Visual Autoregressive Models
Masked Logit Nudging aligns visual autoregressive model logits with source token maps under target prompts inside cross-attention masks, delivering top image editing results on PIE benchmarks and strong reconstructions on COCO and OpenImages while running faster than diffusion approaches.
-
A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens
Delta tokens compress VFM feature differences into single tokens, enabling a lightweight generative world model that predicts diverse futures with far lower compute than existing approaches.
-
Drift-AR: Single-Step Visual Autoregressive Generation via Anti-Symmetric Drifting
Drift-AR achieves 3.8-5.5x speedup in AR-diffusion image models by using entropy to enable entropy-informed speculative decoding and single-step (1-NFE) anti-symmetric drifting decoding.
-
Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewards
SOLACE improves text-to-image generation by using intrinsic self-confidence rewards from noise reconstruction accuracy during reinforcement learning post-training without external supervision.
-
Beyond Patches: Global-aware Autoregressive Model for Multimodal Few-Shot Font Generation
GAR-Font is a global-aware autoregressive framework for multimodal few-shot font generation that adds global tokenization, a language-style adapter, and post-refinement to improve style coherence over patch-based methods.
-
VVS: Accelerating Speculative Decoding for Visual Autoregressive Generation via Partial Verification Skipping
VVS accelerates visual AR image generation by partially skipping verifications in speculative decoding, achieving 2.8x fewer target forward passes while preserving competitive quality.
-
Discrete Guidance Matching: Exact Guidance for Discrete Flow Matching
Derives exact guidance transition rates for discrete flow matching models that require only one model evaluation per sampling step and unify prior approximation-based methods.
-
FluentAvatar: Flicker-Free Talking-Head Animation via Phoneme-Guided Autoregressive Modeling
Phoneme-guided autoregressive framework for talking-head animation that reduces inter-frame flicker via causal keyframe generation and timestamp-aware interpolation, outperforming diffusion baselines on FVD and a new BG-Flicker metric.
-
PacTure: Efficient PBR Texture Generation on Packed Views with Visual Autoregressive Models
PacTure uses view packing and next-scale autoregressive prediction to generate consistent multi-view PBR textures faster than prior sequential or cross-attention methods.
-
Distilling Specialized Orders for Visual Generation
OAR distills specialized generation orders from any-order AR models via self-distillation, improving FID from 2.39 to 2.17 on ImageNet 256x256 while preserving multi-task flexibility.
-
WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation
Text-to-image models show significant limitations in integrating world knowledge, as measured by the new WISE benchmark and WiScore metric across 20 models.
-
T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts
T2I-FactualBench is a new three-tier benchmark for factuality of knowledge-intensive concepts in T2I models, using multi-round VQA evaluation to show SOTA models need improvement.
-
Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation
Janus decouples visual encoding into task-specific pathways inside a single autoregressive transformer to unify multimodal understanding and generation while outperforming earlier unified models.
-
PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion
PiD is a pixel diffusion decoder that performs latent-to-pixel conversion and 4-8x upsampling in one generative step, enabling early stopping of latent diffusion and achieving sub-second 2048x2048 decoding with claimed better fidelity than cascaded baselines.
-
Vision Foundation Models as Generalist Tokenizers for Image Generation
VFMTok builds a generalist image tokenizer on frozen VFMs using adaptive quantization and semantic alignment, delivering gFID 1.36 for autoregressive and 1.25 for continuous generation on ImageNet with 3x faster convergence.
-
HierEdit: Region-Aware Hierarchical Diffusion for Efficient High-Resolution Editing
HierEdit enables efficient 4K image editing via low-resolution proxy localization followed by hierarchical local-window diffusion that reuses unaltered regions as conditioning.
-
FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization
FashionChameleon achieves interactive multi-garment video customization in real time by training a teacher model with in-context learning on single-garment pairs, applying streaming distillation, and using training-free KV cache rescheduling.
-
HyperDiT: Hyper-Connected Transformers for High-Fidelity Pixel-Space Diffusion
HyperDiT achieves FID 1.56 on ImageNet 256x256 in pixel space via hyper-connected cross-scale interactions, cross-attention, SA-RoPE, and VFM registers.
-
HeatKV: Head-tuned KV-cache Compression for Visual Autoregressive Modeling
HeatKV ranks attention heads by their focus on prior scales using offline calibration data and applies a static per-head pruning schedule, delivering 2x higher KV-cache compression than prior methods on the Infinity-2B model with comparable image fidelity.
-
InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation
InsightTok improves text and face fidelity in discrete image tokenization via content-aware perceptual losses, with gains transferring to autoregressive generation.
-
Do multimodal models imagine electric sheep?
Fine-tuning VLMs to output action sequences for puzzles causes emergent internal visual representations that improve performance when integrated into reasoning.
-
FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation
FlashAR accelerates autoregressive image generation up to 22.9x by post-training a pre-trained raster-scan model with a complementary vertical head and dynamic fusion for two-way next-token prediction.
-
dFlowGRPO: Rate-Aware Policy Optimization for Discrete Flow Models
dFlowGRPO is a new rate-aware RL method for discrete flow models that outperforms prior GRPO approaches on image generation and matches continuous flow models while supporting broad probability paths.
-
CASCADE: Context-Aware Relaxation for Speculative Image Decoding
CASCADE formalizes semantic interchangeability and convergence in target model representations to enable context-aware acceptance relaxation in tree-based speculative decoding, delivering up to 3.6x speedup on text-to-image models without quality loss.
-
MUSE: Resolving Manifold Misalignment in Visual Tokenization via Topological Orthogonality
MUSE decouples reconstruction and semantic learning in visual tokenization via topological orthogonality, yielding SOTA generation quality and improved semantic performance over its teacher model.
-
End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer
An end-to-end autoregressive model with a jointly trained 1D semantic tokenizer achieves state-of-the-art FID 1.48 on ImageNet 256x256 generation without guidance.
-
VibeToken: Scaling 1D Image Tokenizers and Autoregressive Models for Dynamic Resolution Generations
VibeToken enables autoregressive image generation at arbitrary resolutions using 64 tokens for 1024x1024 images with 3.94 gFID, constant 179G FLOPs, and better efficiency than diffusion or fixed AR baselines.
-
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
Tuna-2 shows that direct pixel embeddings can replace vision encoders in unified multimodal models, achieving competitive generation and stronger understanding at scale.
-
PILOT: One Physics-Integrated Generation Framework to Unify 2D and 3D Radio Map Construction
PILOT unifies 2D and 3D radio map generation via physics-guided wavefront autoregressive prediction, reporting lowest NMSE on 2D benchmarks and 78% NMSE reduction with 2500x faster inference than diffusion baselines for 3D.
-
Normalizing Flows with Iterative Denoising
iTARFlow augments normalizing flows with diffusion-style iterative denoising during sampling while preserving end-to-end likelihood training, reaching competitive results on ImageNet 64/128/256.
-
Generative Refinement Networks for Visual Synthesis
GRN uses hierarchical binary quantization and entropy-guided refinement to set new ImageNet records of 0.56 rFID for reconstruction and 1.81 gFID for class-conditional generation while releasing code and models.
-
Combating Pattern and Content Bias: Adversarial Feature Learning for Generalized AI-Generated Image Detection
MAFL uses adversarial training to suppress pattern and content biases, guiding models to learn shared generative features for better cross-model generalization in detecting AI images.
-
On the Robustness of Watermarking for Autoregressive Image Generation
Watermarking schemes for autoregressive image generation fail against removal and forgery attacks, enabling false detections and undermining synthetic content filtering.
-
Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compression
RDVQ enables joint rate-distortion optimization for vector-quantized generative image compression via differentiable codebook distribution relaxation and an autoregressive entropy model.
-
SMART: When is it Actually Worth Expanding a Speculative Tree?
SMART uses marginal benefit-cost analysis to dynamically build efficient speculative trees, achieving 15-20% additional speedup in LLM and MLLM inference.
-
TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders
TC-AE improves reconstruction and generative performance in deep compression by decomposing token-to-latent compression into two stages and using joint self-supervised training.
-
Multimodal Large Language Models for Multi-Subject In-Context Image Generation
MUSIC is the first MLLM for multi-subject in-context image generation that uses an automatic data pipeline, vision chain-of-thought reasoning, and semantics-driven spatial layout planning to outperform prior methods on a new MSIC benchmark.
-
MAR-GRPO: Stabilized GRPO for AR-diffusion Hybrid Image Generation
MAR-GRPO stabilizes GRPO for AR-diffusion hybrids via multi-trajectory expectation and uncertainty-based token selection, yielding better visual quality, stability, and spatial understanding than baselines.
-
CausalEmbed: Auto-Regressive Multi-Vector Generation in Latent Space for Visual Document Embedding
CausalEmbed uses auto-regressive generation with iterative margin loss to produce multi-vector embeddings that reduce visual token counts 30-155x while retaining competitive performance on VDR benchmarks.
-
Mirai: Autoregressive Visual Generation Needs Foresight
Mirai injects future-token foresight into autoregressive visual generators, accelerating convergence up to 10x and cutting ImageNet FID from 5.34 to 4.34.
-
Emu3.5: Native Multimodal Models are World Learners
Emu3.5 is a native multimodal world model pre-trained on over 10 trillion vision-language tokens with next-token prediction, post-trained via reinforcement learning, and accelerated by Discrete Diffusion Adaptation for efficient interleaved generation and world exploration.
-
Speculative Coupled Decoding for Training-Free Lossless Acceleration of Autoregressive Visual Generation
Speculative Coupled Decoding stabilizes draft sampling in Speculative Jacobi Decoding via an information-theoretic coupling step, delivering up to 4.2x image and 13.6x video speedups with no quality loss or training.