A large-scale empirical study across tokenizers and diffusion backbones identifies Velocity Irreducible Variance (VIV) as one of the most stable predictors of latent diffusion generation quality.
arXiv preprint arXiv:2505.05422 (2025) 2, 4, 7, 9, 1
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
IV-CoT introduces an implicit chain-of-thought framework that decomposes visual queries into a structural-to-semantic cascade with training-only sketch supervision to improve structure-aware text-to-image generation.
HYDRA-X presents the first unified multimodal model using a single ViT for holistic image-video tokenization, with ablations on attention and compression plus a latent-level editing improvement.
Introduces ProductWebGen benchmark for multimodal product webpage generation, compares editing-based vs unified-model workflows on 500 samples, and releases ProductWebGen-1k SFT dataset.
InsightTok improves text and face fidelity in discrete image tokenization via content-aware perceptual losses, with gains transferring to autoregressive generation.
InfoTok uses mutual information constraints to regularize shared visual tokenization in unified MLLMs, improving both understanding and generation performance without extra training data.
SPAR introduces a semantic-pixel self-alignment tokenizer and dynamic token routing to create a unified multimodal model that performs both understanding and generation at claimed state-of-the-art levels.
WinTok is a hybrid visual tokenizer that supplements pixel tokens with learnable semantic tokens distilled asymmetrically from foundation models to improve reconstruction, understanding, and generation.
SenseNova-U1 presents native unified multimodal models that match top understanding VLMs while delivering strong performance in image generation, infographics, and interleaved tasks via the NEO-unify architecture.
UniTranslator adds an Understand-Generation Alignment Module and Spatial Mask Decoder to a unified multimodal model to fix translation inconsistency and spatial misalignment in in-image machine translation, reporting SOTA results on multiple benchmarks.
Show-o2 unifies text, image, and video understanding and generation in a single autoregressive-plus-flow-matching model built on 3D causal VAE representations.
citing papers explorer
-
Diffusing in the Right Space: A Systematic Study of Latent Diffusability
A large-scale empirical study across tokenizers and diffusion backbones identifies Velocity Irreducible Variance (VIV) as one of the most stable predictors of latent diffusion generation quality.
-
IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation
IV-CoT introduces an implicit chain-of-thought framework that decomposes visual queries into a structural-to-semantic cascade with training-only sketch supervision to improve structure-aware text-to-image generation.
-
HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers
HYDRA-X presents the first unified multimodal model using a single ViT for holistic image-video tokenization, with ablations on attention and compression plus a latent-level editing improvement.
-
ProductWebGen: Benchmarking Multimodal Product Webpage Generation
Introduces ProductWebGen benchmark for multimodal product webpage generation, compares editing-based vs unified-model workflows on 500 samples, and releases ProductWebGen-1k SFT dataset.
-
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.
-
InfoTok: Information-Theoretic Regularization for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs
InfoTok uses mutual information constraints to regularize shared visual tokenization in unified MLLMs, improving both understanding and generation performance without extra training data.
-
SPAR: Semantic-Pixel Self-Alignment and Adaptive Routing for Unified Multimodal Models
SPAR introduces a semantic-pixel self-alignment tokenizer and dynamic token routing to create a unified multimodal model that performs both understanding and generation at claimed state-of-the-art levels.
-
WinTok: A Win-Win Hybrid Tokenizer via Decomposing Visual Understanding and Generation with Transferable Tokens
WinTok is a hybrid visual tokenizer that supplements pixel tokens with learnable semantic tokens distilled asymmetrically from foundation models to improve reconstruction, understanding, and generation.
-
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
SenseNova-U1 presents native unified multimodal models that match top understanding VLMs while delivering strong performance in image generation, infographics, and interleaved tasks via the NEO-unify architecture.
-
UniTranslator: A Unified Multi-modal Framework for End-to-end In-Image Machine Translation
UniTranslator adds an Understand-Generation Alignment Module and Spatial Mask Decoder to a unified multimodal model to fix translation inconsistency and spatial misalignment in in-image machine translation, reporting SOTA results on multiple benchmarks.
-
Show-o2: Improved Native Unified Multimodal Models
Show-o2 unifies text, image, and video understanding and generation in a single autoregressive-plus-flow-matching model built on 3D causal VAE representations.