Parallel Jacobi Decoding accelerates autoregressive image models 4.8x-6.4x by using 2D spatial draft expansion and adjusted attention masks while keeping generation quality competitive.
hub
Lumina-mgpt: Illuminate flexible photorealistic text-to-image generation with multimodal gener- ative pretraining, 2024a
20 Pith papers cite this work. Polarity classification is still indexing.
20
Pith papers citing it
hub tools
citation-role summary
background 1
baseline 1
method 1
other 1
citation-polarity summary
representative citing papers
LD-Pruning applies latent discrepancy to prune tokens and adaptively skip unconditional branches in VAR models for up to 2.35x faster inference with preserved quality.
HIT with token overlap plus DPO regularization lets a 300M-param VAR model deliver state-of-the-art multi-scale ISR in one forward pass without external data.
OA-WAM uses persistent address vectors and dynamic content vectors in object slots to enable addressable world-action prediction, improving robustness on manipulation benchmarks under scene changes.
TextGround4M supplies 4M prompt-aligned image pairs with layout annotations, enabling autoregressive T2I models to render prompt-specified text more accurately via added span tokens, a new benchmark, and layout-aware metrics.
dMLLM-TTS delivers up to 6x more efficient test-time scaling for diffusion MLLMs via O(N+T) hierarchical search and self-verified feedback, improving generation quality on GenEval across three models.
VVS accelerates visual AR image generation by partially skipping verifications in speculative decoding, achieving 2.8x fewer target forward passes while preserving competitive quality.
Per-position AR prediction entropy jointly drives speculative AR decoding and an anti-symmetric single-step drift decoder, yielding 3.8–5.5× faster hybrid visual generation without distillation.
VarKD is a distillation framework for visual AR models that uses student samples and selective teacher supervision to reduce token ambiguity, outperforming prior baselines on ImageNet.
Polaris retrieves and integrates relevant models from a large library of checkpoints and adapters to enable scalable instruction-guided image generation and editing without additional training.
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.
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.
Cross-modal representational alignment between text, image, audio, and video models degrades substantially when evaluated at million-sample scale and under realistic many-to-many pairing assumptions.
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.
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.
Muddit is a unified discrete diffusion transformer that integrates strong visual priors from a pretrained text-to-image model with a lightweight text decoder to enable fast parallel generation across text and image modalities.
FSDrive uses a generated future scene frame as visual spatio-temporal CoT to improve VLA models for safer autonomous driving trajectory prediction.
SSD predicts multiple spatially adjacent tokens at once in autoregressive image models, claiming up to 13.3x inference speedup on DPG-Bench and GenEval with maintained fidelity.
RealSR-R1 introduces VLCoT-GRPO with four rewards to add understanding and reasoning to real-world image super-resolution models.
DeepSight uses parallel latent feature prediction in BEV for long-horizon world modeling and adaptive text reasoning to reach state-of-the-art closed-loop performance on the Bench2drive benchmark.
citing papers explorer
-
Parallel Jacobi Decoding for Fast Autoregressive Image Generation
Parallel Jacobi Decoding accelerates autoregressive image models 4.8x-6.4x by using 2D spatial draft expansion and adjusted attention masks while keeping generation quality competitive.
-
Where to Refine, When to Stop: Rethinking Redundancy via Latent Discrepancy for Efficient Visual Autoregressive Generation
LD-Pruning applies latent discrepancy to prune tokens and adaptively skip unconditional branches in VAR models for up to 2.35x faster inference with preserved quality.
-
Hierarchical Image Tokenization for Multi-Scale Image Super Resolution
HIT with token overlap plus DPO regularization lets a 300M-param VAR model deliver state-of-the-art multi-scale ISR in one forward pass without external data.
-
OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation
OA-WAM uses persistent address vectors and dynamic content vectors in object slots to enable addressable world-action prediction, improving robustness on manipulation benchmarks under scene changes.
-
TextGround4M: A Prompt-Aligned Dataset for Layout-Aware Text Rendering
TextGround4M supplies 4M prompt-aligned image pairs with layout annotations, enabling autoregressive T2I models to render prompt-specified text more accurately via added span tokens, a new benchmark, and layout-aware metrics.
-
dMLLM-TTS: Self-Verified and Efficient Test-Time Scaling for Diffusion Multi-Modal Large Language Models
dMLLM-TTS delivers up to 6x more efficient test-time scaling for diffusion MLLMs via O(N+T) hierarchical search and self-verified feedback, improving generation quality on GenEval across three models.
-
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.
-
Drift-AR: Single-Step Visual Autoregressive Generation via Anti-Symmetric Drifting
Per-position AR prediction entropy jointly drives speculative AR decoding and an anti-symmetric single-step drift decoder, yielding 3.8–5.5× faster hybrid visual generation without distillation.
-
Knowledge Distillation for Visual Autoregressive Models
VarKD is a distillation framework for visual AR models that uses student samples and selective teacher supervision to reduce token ambiguity, outperforming prior baselines on ImageNet.
-
Polaris: Scaling Up Instruction-Guided Image Generation Towards Millions of Personalized Style Needs
Polaris retrieves and integrates relevant models from a large library of checkpoints and adapters to enable scalable instruction-guided image generation and editing without additional training.
-
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.
-
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.
-
Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale
Cross-modal representational alignment between text, image, audio, and video models degrades substantially when evaluated at million-sample scale and under realistic many-to-many pairing assumptions.
-
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.
-
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.
-
Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model
Muddit is a unified discrete diffusion transformer that integrates strong visual priors from a pretrained text-to-image model with a lightweight text decoder to enable fast parallel generation across text and image modalities.
-
FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving
FSDrive uses a generated future scene frame as visual spatio-temporal CoT to improve VLA models for safer autonomous driving trajectory prediction.
-
SSD: Spatially Speculative Decoding Accelerates Autoregressive Image Generation
SSD predicts multiple spatially adjacent tokens at once in autoregressive image models, claiming up to 13.3x inference speedup on DPG-Bench and GenEval with maintained fidelity.
-
RealSR-R1: Reinforcement Learning for Real-World Image Super-Resolution with Vision-Language Chain-of-Thought
RealSR-R1 introduces VLCoT-GRPO with four rewards to add understanding and reasoning to real-world image super-resolution models.
-
DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving
DeepSight uses parallel latent feature prediction in BEV for long-horizon world modeling and adaptive text reasoning to reach state-of-the-art closed-loop performance on the Bench2drive benchmark.