Text tokens in FLUX.2 absorb reference image properties like color and style to influence outputs while pixel-exact details bypass them, localized to padding tokens via causal interventions.
hub
Scaling rectified flow transformers for high-resolution image synthesis
17 Pith papers cite this work. Polarity classification is still indexing.
17
Pith papers citing it
hub tools
citation-role summary
background 2
method 2
citation-polarity summary
representative citing papers
ImageAttributionBench is a benchmark dataset demonstrating that state-of-the-art image attribution methods lack robustness to image degradation and fail to generalize to semantically disjoint domains.
CausalCine enables real-time causal autoregressive multi-shot video generation via multi-shot training, content-aware memory routing for coherence, and distillation to few-step inference.
InstructMoLE replaces per-token routing with instruction-guided global routing for mixture-of-low-rank-experts in diffusion transformers and adds an output-space orthogonality loss to improve multi-conditional image generation.
Dreamer 4 is the first agent to obtain diamonds in Minecraft from only offline data by reinforcement learning inside a scalable world model that accurately predicts game mechanics.
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.
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).
Latent Action Control learns unobserved action trajectories via variational alignment and GRPO to inject reasoning into flow-based image generation, yielding gains on compositional benchmarks.
sREPA enforces structural consistency in relational geometry of pre-trained vision features to accelerate DiT training and improve generation quality.
Slowly Annealed Langevin Dynamics provides non-asymptotic KL-based convergence guarantees for tracking moving targets and enables training-free guided generation via a velocity-aware correction that accounts for pretrained marginals.
OmniShow unifies text, image, audio, and pose conditions into an end-to-end model for high-quality human-object interaction video generation and introduces the HOIVG-Bench benchmark, claiming state-of-the-art results.
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.
Rosetta proposes a composable multimodal pretraining method with MAOP to prevent catastrophic forgetting when expanding modalities beyond standard MoE and MoT approaches.
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.
PhyWorld improves temporal consistency and physical plausibility in video world models via flow matching fine-tuning followed by DPO on physics preference pairs, with reported gains on VBench and a custom physical-faithfulness benchmark.
Edit-GRPO decouples editing and preservation objectives via region-specific signals in a policy optimization framework to improve locality in image editing tasks.
The survey frames VLA models as pipelines that generate progressively grounded action tokens and classifies those tokens into eight types to guide future development.
citing papers explorer
-
Vision-Language Binding in In-Context Image Generation
Text tokens in FLUX.2 absorb reference image properties like color and style to influence outputs while pixel-exact details bypass them, localized to padding tokens via causal interventions.
-
ImageAttributionBench: How Far Are We from Generalizable Attribution?
ImageAttributionBench is a benchmark dataset demonstrating that state-of-the-art image attribution methods lack robustness to image degradation and fail to generalize to semantically disjoint domains.
-
CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives
CausalCine enables real-time causal autoregressive multi-shot video generation via multi-shot training, content-aware memory routing for coherence, and distillation to few-step inference.
-
InstructMoLE: Instruction-Guided Mixture of Low-rank Experts for Multi-Conditional Image Generation
InstructMoLE replaces per-token routing with instruction-guided global routing for mixture-of-low-rank-experts in diffusion transformers and adds an output-space orthogonality loss to improve multi-conditional image generation.
-
Training Agents Inside of Scalable World Models
Dreamer 4 is the first agent to obtain diamonds in Minecraft from only offline data by reinforcement learning inside a scalable world model that accurately predicts game mechanics.
-
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.
-
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).
-
Latent Action Control for Reasoning-Guided Unified Image Generation
Latent Action Control learns unobserved action trajectories via variational alignment and GRPO to inject reasoning into flow-based image generation, yielding gains on compositional benchmarks.
-
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.
-
Slowly Annealed Langevin Dynamics: Theory and Applications to Training-Free Guided Generation
Slowly Annealed Langevin Dynamics provides non-asymptotic KL-based convergence guarantees for tracking moving targets and enables training-free guided generation via a velocity-aware correction that accounts for pretrained marginals.
-
OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation
OmniShow unifies text, image, audio, and pose conditions into an end-to-end model for high-quality human-object interaction video generation and introduces the HOIVG-Bench benchmark, claiming state-of-the-art results.
-
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.
-
Rosetta: Composable Native Multimodal Pretraining
Rosetta proposes a composable multimodal pretraining method with MAOP to prevent catastrophic forgetting when expanding modalities beyond standard MoE and MoT approaches.
-
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.
-
PhyWorld: Physics-Faithful World Model for Video Generation
PhyWorld improves temporal consistency and physical plausibility in video world models via flow matching fine-tuning followed by DPO on physics preference pairs, with reported gains on VBench and a custom physical-faithfulness benchmark.
-
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.
-
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.