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.
hub Canonical reference
High-resolution image synthesis with latent diffusion models
Canonical reference. 73% of citing Pith papers cite this work as background.
49
Pith papers citing it
Background
73% of classified citations
hub tools
citation-role summary
background 9
method 2
citation-polarity summary
representative citing papers
StreamingEffect enables real-time 720p human-centric video effect generation on one GPU via teacher-student distillation, keyframe control, and a new 130K video dataset.
UniTriGen uses unified diffusion in a shared latent space plus lightweight adapters and scene-balanced sampling to produce high-quality aligned VIS-IR-Label triplets from limited paired data, improving few-shot RGB-T semantic segmentation.
AID amortizes guidance for diffusion inpainting by training a reusable module via an auxiliary Gaussian formulation and continuous-time actor-critic algorithm, improving quality-speed trade-off with under 1% overhead.
Constraint-Aware Flow Matching integrates constraint projections into the flow matching training objective to align model dynamics with constrained sampling and reduce distributional shift.
INSET embeds images as native tokens in interleaved instructions, outperforming prior methods on multi-image consistency and text alignment as complexity grows.
ConFixGS repairs feedforward 3D Gaussian Splatting with confidence-aware diffusion priors, delivering up to 3.68 dB PSNR gains and halved FID scores on Waymo, nuScenes, and KITTI novel view synthesis tasks.
DCR uses a counterfactual attractor and projection-based repulsion to suppress default completion bias in diffusion models, improving fidelity for rare compositional prompts while preserving quality.
LeapAlign fine-tunes flow matching models by constructing two consecutive leaps that skip multiple ODE steps with randomized timesteps and consistency weighting, enabling stable updates at any generation step.
MSDDA derives a closed-form optimal reverse denoising distribution for multi-objective diffusion alignment that is exactly equivalent to step-level RL fine-tuning with no approximation error.
DMax uses On-Policy Uniform Training and Soft Parallel Decoding to enable aggressive parallelism in dLLMs, raising TPF on GSM8K from 2.04 to 5.47 and on MBPP from 2.71 to 5.86 while preserving accuracy.
Text-to-image models show significant limitations in integrating world knowledge, as measured by the new WISE benchmark and WiScore metric across 20 models.
SCOPE adds per-pixel action conditioning to pretrained video diffusion models and releases the CrossFPS multi-game dataset to support cross-game FPS world model simulation with zero-shot transfer.
Spatial Gram Alignment aligns internal self-similarities of LDM features with foundation priors to reconcile global structure and fine details in ultra-high-resolution text-to-image synthesis.
DAR replaces residual addition in DiTs with learnable timestep-adaptive non-incremental aggregation of sublayer outputs, improving FID by 2.11 on ImageNet 256x256 and accelerating convergence by 8.75x.
AVIS applies autoregressive diffusion models to video inverse problems by streaming restoration with measurement-consistent initialization, reducing latency from 114s to 4s and raising throughput to 1.18 FPS (or 5.91 FPS in the Flash variant).
SafeMark integrates a thresholded watermark-decoding loss into diffusion editors to enable text-guided edits that preserve embedded watermarks with high bit accuracy.
LatentBox is a latent-first storage system that cuts persistent storage for AI images by 78.7% while keeping mean and tail latency competitive with traditional pixel storage.
A transformer-based neural renderer that transfers arbitrary PBR lighting to single images via shared intrinsic conditioning extracted from both multi-illumination photos and path-traced coarse 3D renders.
DAD4TS augments small time-series datasets with a diffusion model trained via mathematical geometric projections and guided by reinforcement learning to improve forecasting accuracy.
sREPA enforces structural consistency in relational geometry of pre-trained vision features to accelerate DiT training and improve generation quality.
Flash-GRPO introduces iso-temporal grouping and temporal gradient rectification to enable single-step GRPO training that outperforms full-trajectory methods on video diffusion alignment under low compute budgets.
SEF introduces GAN upsampling for diverse artifacts and expert fusion to reduce domain interference, yielding stronger generalization on 13 benchmarks for AI-generated image detection.
Pretrained instruction-based image editing models exhibit early foreground-background separability that enables a training-free framework for zero-shot referring image segmentation using a single denoising step.
citing papers explorer
-
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.
-
StreamingEffect: Real-Time Human-Centric Video Effect Generation
StreamingEffect enables real-time 720p human-centric video effect generation on one GPU via teacher-student distillation, keyframe control, and a new 130K video dataset.
-
UniTriGen: Unified Triplet Generation of Aligned Visible-Infrared-Label for Few-Shot RGB-T Semantic Segmentation
UniTriGen uses unified diffusion in a shared latent space plus lightweight adapters and scene-balanced sampling to produce high-quality aligned VIS-IR-Label triplets from limited paired data, improving few-shot RGB-T semantic segmentation.
-
Amortized Guidance for Image Inpainting with Pretrained Diffusion Models
AID amortizes guidance for diffusion inpainting by training a reusable module via an auxiliary Gaussian formulation and continuous-time actor-critic algorithm, improving quality-speed trade-off with under 1% overhead.
-
Constraint-Aware Flow Matching: Decision Aligned End-to-End Training for Constrained Sampling
Constraint-Aware Flow Matching integrates constraint projections into the flow matching training objective to align model dynamics with constrained sampling and reduce distributional shift.
-
Images in Sentences: Scaling Interleaved Instructions for Unified Visual Generation
INSET embeds images as native tokens in interleaved instructions, outperforming prior methods on multi-image consistency and text alignment as complexity grows.
-
ConFixGS: Learning to Fix Feedforward 3D Gaussian Splatting with Confidence-Aware Diffusion Priors in Driving Scenes
ConFixGS repairs feedforward 3D Gaussian Splatting with confidence-aware diffusion priors, delivering up to 3.68 dB PSNR gains and halved FID scores on Waymo, nuScenes, and KITTI novel view synthesis tasks.
-
DCR: Counterfactual Attractor Guidance for Rare Compositional Generation
DCR uses a counterfactual attractor and projection-based repulsion to suppress default completion bias in diffusion models, improving fidelity for rare compositional prompts while preserving quality.
-
LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories
LeapAlign fine-tunes flow matching models by constructing two consecutive leaps that skip multiple ODE steps with randomized timesteps and consistency weighting, enabling stable updates at any generation step.
-
Step-level Denoising-time Diffusion Alignment with Multiple Objectives
MSDDA derives a closed-form optimal reverse denoising distribution for multi-objective diffusion alignment that is exactly equivalent to step-level RL fine-tuning with no approximation error.
-
DMax: Aggressive Parallel Decoding for dLLMs
DMax uses On-Policy Uniform Training and Soft Parallel Decoding to enable aggressive parallelism in dLLMs, raising TPF on GSM8K from 2.04 to 5.47 and on MBPP from 2.71 to 5.86 while preserving accuracy.
-
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.
-
SCOPE: Simulating Cross-game Operations in Playable Environments for FPS World Models
SCOPE adds per-pixel action conditioning to pretrained video diffusion models and releases the CrossFPS multi-game dataset to support cross-game FPS world model simulation with zero-shot transfer.
-
Spatial Gram Alignment for Ultra-High-Resolution Image Synthesis
Spatial Gram Alignment aligns internal self-similarities of LDM features with foundation priors to reconcile global structure and fine details in ultra-high-resolution text-to-image synthesis.
-
Rethinking Cross-Layer Information Routing in Diffusion Transformers
DAR replaces residual addition in DiTs with learnable timestep-adaptive non-incremental aggregation of sublayer outputs, improving FID by 2.11 on ImageNet 256x256 and accelerating convergence by 8.75x.
-
Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models
AVIS applies autoregressive diffusion models to video inverse problems by streaming restoration with measurement-consistent initialization, reducing latency from 114s to 4s and raising throughput to 1.18 FPS (or 5.91 FPS in the Flash variant).
-
Are Watermarked Images Editable? SafeMark for Watermark-Preserving Text-Guided Image Editing
SafeMark integrates a thresholded watermark-decoding loss into diffusion editors to enable text-guided edits that preserve embedded watermarks with high bit accuracy.
-
LatentBox: Storing AI-Generated Images at Scale via a Latent-First Design
LatentBox is a latent-first storage system that cuts persistent storage for AI images by 78.7% while keeping mean and tail latency competitive with traditional pixel storage.
-
PIXLRelight: Controllable Relighting via Intrinsic Conditioning
A transformer-based neural renderer that transfers arbitrary PBR lighting to single images via shared intrinsic conditioning extracted from both multi-illumination photos and path-traced coarse 3D renders.
-
DAD4TS: Data-Augmentation-Oriented Diffusion Model for Time-Series Forecasting with Small-Scale Data
DAD4TS augments small time-series datasets with a diffusion model trained via mathematical geometric projections and guided by reinforcement learning to improve forecasting accuracy.
-
Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers
sREPA enforces structural consistency in relational geometry of pre-trained vision features to accelerate DiT training and improve generation quality.
-
Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization
Flash-GRPO introduces iso-temporal grouping and temporal gradient rectification to enable single-step GRPO training that outperforms full-trajectory methods on video diffusion alignment under low compute budgets.
-
Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detection
SEF introduces GAN upsampling for diverse artifacts and expert fusion to reduce domain interference, yielding stronger generalization on 13 benchmarks for AI-generated image detection.
-
Early Semantic Grounding in Image Editing Models for Zero-Shot Referring Image Segmentation
Pretrained instruction-based image editing models exhibit early foreground-background separability that enables a training-free framework for zero-shot referring image segmentation using a single denoising step.
-
Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping
Super-Linear Advantage Shaping (SLAS) introduces a non-linear geometric policy update for RL post-training of text-to-image models that reshapes the local policy space via advantage-dependent Fisher-Rao weighting to reduce reward hacking and improve performance over GRPO baselines.
-
Filtering Memorization from Parameter-Space in Diffusion Models
BAF reduces memorization in diffusion LoRAs by filtering spectral channels of the adaptation weights that show weak alignment with the base model's principal subspace.
-
What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion
Prior-Aligned AutoEncoders shape latent manifolds with spatial coherence, local continuity, and global semantics to improve latent diffusion, achieving SOTA gFID 1.03 on ImageNet 256x256 with up to 13x faster convergence.
-
FREPix: Frequency-Heterogeneous Flow Matching for Pixel-Space Image Generation
FREPix achieves competitive FID scores on ImageNet by decomposing image generation into separate low- and high-frequency paths within a flow matching framework.
-
Intermediate Representations are Strong AI-Generated Image Detectors
Intermediate layer embedding sensitivity to perturbations distinguishes AI-generated images from real ones, yielding higher AUROC on GenImage and Forensics Small benchmarks than prior methods.
-
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.
-
Leveraging Verifier-Based Reinforcement Learning in Image Editing
Edit-R1 builds a CoT-based reasoning reward model (RRM) via SFT and GCPO, then applies it with GRPO to improve image editing models such as FLUX.1-kontext.
-
GENSERVE: Efficient Co-Serving of Heterogeneous Diffusion Model Workloads
GENSERVE improves SLO attainment by up to 44% for co-serving heterogeneous T2I and T2V diffusion workloads via step-level preemption, elastic parallelism, and joint scheduling.
-
Energy-Guided Generative Modeling for Low-Energy Molecular Structure Discovery
EnFlow integrates flow-based conformer generation with energy landscape modeling to enable joint ensemble generation and ground-state identification using only 1-2 ODE steps.
-
Kling-Omni Technical Report
Kling-Omni is a unified multimodal generative system that produces cinematic videos from diverse inputs by integrating generation, editing, and intelligent reasoning in a single end-to-end model.
-
DanceGRPO: Unleashing GRPO on Visual Generation
DanceGRPO applies GRPO to visual generation tasks to achieve stable policy optimization across diffusion models, rectified flows, multiple tasks, and diverse reward models, outperforming prior RL methods.
-
Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation
Mogao presents a causal unified model with deep fusion, dual encoders, and interleaved position embeddings that achieves strong performance on multi-modal understanding, text-to-image generation, and coherent interleaved outputs including zero-shot editing.
-
VideoPhy: Evaluating Physical Commonsense for Video Generation
VideoPhy benchmark shows state-of-the-art text-to-video models follow physical commonsense and text prompts in only 39.6% of cases for the best model.
-
One-Step Distillation of Discrete Diffusion Image Generators via Fixed-Point Iteration
Fixed-Point Distillation constructs one-step correction targets for discrete diffusion generators via partial corruption and single teacher refinement, lifted into continuous features with a multi-bandwidth drift loss and straight-through estimation.
-
MONET: A Massive, Open, Non-redundant and Enriched Text-to-image dataset
MONET is an open 104.9M image-text pair dataset created via safety filtering, deduplication, and multi-VLM recaptioning from 2.9B raw pairs, validated by training a competitive 4B-parameter latent diffusion model.
-
Edit-GRPO: A Locality-Preserving Policy Optimization Framework for Image Editing
Edit-GRPO decouples editing and preservation objectives via region-specific signals in a policy optimization framework to improve locality in image editing tasks.
-
InsHuman: Towards Natural and Identity-Preserving Human Insertion
InsHuman proposes Human-Background Adaptive Fusion, Face-to-Face ID-Preserving, and Bidirectional Data Pairing to enable natural human insertion in images without altering identity.
-
Video Generation with Predictive Latents
PV-VAE improves video latent spaces for generation by unifying reconstruction with future-frame prediction, reporting 52% faster convergence and 34.42 FVD gain over Wan2.2 VAE on UCF101.
-
Scaling Properties of Continuous Diffusion Spoken Language Models
Continuous diffusion spoken language models follow scaling laws for loss and phoneme divergence and generate emotive multi-speaker speech at 16B scale, though long-form coherence stays difficult.
-
GaiaFlow: Semantic-Guided Diffusion Tuning for Carbon-Frugal Search
GaiaFlow combines semantic-guided diffusion tuning with early-exit and quantization methods to lower carbon emissions in neural information retrieval while maintaining competitive effectiveness.
-
A Survey on Vision-Language-Action Models: An Action Tokenization Perspective
The survey frames VLA models as pipelines that generate progressively grounded action tokens and classifies those tokens into eight types to guide future development.
-
Preserve and Personalize: Personalized Text-to-Image Diffusion Models without Distributional Drift
Proposes Lipschitz regularization during fine-tuning to prevent distributional drift in personalized diffusion models, improving subject fidelity and prompt adherence.
-
JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation
JoyAI-Image unifies visual understanding and generation via an MLLM-MMDiT architecture with spatial training signals to reach competitive benchmark performance and stronger spatial intelligence.
-
From Redaction to Restoration: Deep Learning for Medical Image Anonymization and Reconstruction
An end-to-end framework redacts PHI from medical images via CRNN detection and restores them with Stable Diffusion inpainting to enable privacy-preserving data sharing without losing downstream utility.
- STAMBRIDGE: Spectral-Temporal Amplitude-aware Mid-Feature Bridge for EEG Visual Decoding