Uni-Edit introduces a data synthesis pipeline turning VQA data into reasoning-intensive editing instructions, enabling single-task tuning that boosts all three capabilities in models like BAGEL and Janus-Pro.
hub
Nextstep-1: Toward autoregressive image generation with continuous tokens at scale
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
hub tools
citation-role summary
background 2
baseline 1
other 1
citation-polarity summary
years
2026 16representative citing papers
Invisible hints such as logos embedded in images are re-rendered by diffusion models during text-guided editing, enabling phishing and model-poisoning attacks with average success rates of 44.4% and 32.2%.
PlanViz is a new benchmark with three sub-tasks and PlanScore metric to evaluate planning-oriented image generation and editing by unified multimodal models for computer-use tasks.
MICE modifies joint attention biases in Multimodal Diffusion Transformers to enable concurrent multi-instance edits while reducing semantic interference via user masks.
CVQ replaces patch-wise vector quantization with channel-wise quantization of feature maps, enabling a next-channel autoregressive model that reports 100% codebook utilization and text-to-image scores of DPG 86.7 and GenEval 0.79.
DIVA factorizes visual representations in unified multimodal models into shared and unique components via complementary information flows and mutual information estimation to convert representation divergence into mutual reinforcement between understanding and generation branches.
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.
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.
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.
Uni-ViGU unifies video generation and understanding by extending a diffusion video generator with unified continuous-discrete flow matching, modality-driven MoE layers, and bidirectional training stages that repurpose generative knowledge for discriminative tasks.
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.
EG-GRPO improves autoregressive text-to-image models by reallocating RL updates according to token entropy, excluding low-entropy tokens from reward signals while adding entropy bonuses to high-entropy ones, yielding state-of-the-art results on standard benchmarks.
LLaMo scales pretrained LLMs for unified motion-language tasks by encoding motion into continuous causal latents and adding a flow-matching head for real-time autoregressive generation and captioning.
F3-Tokenizer adapts audio autoencoder latents with noise-regularized bottleneck (channel normalization and stochastic perturbation) and a representation encoder (RQ-MTP plus frozen-LLM supervision) to support both high-dimensional understanding representations and normalized continuous generation ta
Using understanding tasks as direct supervision during post-training improves image generation and editing in unified multimodal models.