Formalizes video world models as group actions on states and uses latent regularization with synthesized supervision to enforce consistency, introducing GAC and GAR metrics that improve structural correctness in SOTA models.
hub Tool reference
The unrea- sonable effectiveness of deep features as a perceptual metric
Tool reference. 80% of classified Pith citations use this work as a method, library, or software dependency, not as a substantive claim.
23
Pith papers citing it
Method reference
80% of classified citations
hub tools
citation-role summary
method 8
background 2
citation-polarity summary
representative citing papers
Loki replaces RGB conditioning stacks with identity-orthogonal parametric face encodings rasterized for diffusion, achieving efficient cross-ID portrait animation without cross-ID training data.
DRoRAE adaptively fuses multi-layer features from vision encoders via energy-constrained routing to enrich visual tokens, cutting rFID from 0.57 to 0.29 and generation FID from 1.74 to 1.65 on ImageNet-256 while revealing a log-linear scaling law with fusion capacity.
ΔLPS is a gradient-guided discrete posterior sampler for inverse problems that works with masked or uniform discrete diffusion priors and outperforms prior discrete methods on image restoration tasks.
Optimal INR freeze depth matches highest weight stable rank layer; SAEs reveal SIREN atoms are localized while FFMLP atoms trace cohort contours with causal impact on PSNR.
LENS shapes low-frequency eigen noise with a lightweight network to enable efficient, high-quality sampling in distilled diffusion models.
A feed-forward feature-Gaussian plus one-step geometry-aware pixel-flow simulator converts large image collections into 20K interactive scenes and 10M+ navigation samples that improve zero-shot Habitat and real-robot performance.
MADreMIA amplifies membership inference signals by showing that memorized samples maintain higher coherence and slower degradation in chained regeneration trajectories than non-members.
DPPE decouples rotation and translation in camera positional encodings for multi-view transformers to resolve late-stage training stagnation and improve generalization in novel view synthesis.
A hierarchical variational formulation amortizes test-time guidance in diffusion models to achieve strong quality-speed tradeoffs with significantly reduced inference compute.
DiRotQ uses PCA-based rotation-aware activation quantization combined with GPTQ to achieve better FID and PSNR in 4-bit diffusion transformers than prior methods like SVDQuant.
Projecting VAE latents to a fixed spherical radius and replacing linear interpolation with spherical linear interpolation improves class-conditional ImageNet-256 FID while leaving the diffusion architecture unchanged.
TransmissiveGS disentangles reflections from transmissions in Gaussian Splatting via dual-Gaussian modeling, residual cues, and a reflection light field for improved transmissive scene reconstruction.
The paper presents WorldReasonBench, a benchmark that tests video generators on maintaining physical, social, logical, and informational consistency when predicting future states from initial conditions and actions.
SocialDirector uses spatiotemporal actor masking and directional reweighting on cross-attention maps to reduce actor-action mismatches and improve target-directed interactions in generated multi-person videos.
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.
LENSEs improves representation-conditioned molecule generation by jointly training a multi-level representation head, perceptual loss, and REPA alignment on pretrained encoders, yielding 97.28% validity and 98.51% stability on GEOM-DRUG.
UniISP unifies ISP processing with a Hybrid Attention Module and Feature Adapter to produce images that are both visually pleasing for humans and informative for computer vision models.
Slot-MLLM introduces a slot-attention-based object-centric visual tokenizer with Q-Former encoder, diffusion decoder, and residual vector quantization for improved local visual comprehension and generation in multimodal LLMs.
MMGS compresses 3DGS models to 10% primitives with preserved rendering quality and 10x training speedup by combining multi-view geometric ranking with global OT aggregation and densification.
HDRFace injects high-dimensional facial features from low-quality and intermediate images into diffusion models via SDFM fusion, reporting gains on SD V2.1-base and Qwen-Image.
Sword improves world model simulators for VLA policies by disentangling visual style from dynamics and bootstrapping latents for better consistency, outperforming baselines on LIBERO in generalization and RL post-training success.
VRAG improves long-horizon interactive video generation by conditioning autoregressive diffusion on retrieved historical frames and explicit global state, outperforming long-context baselines on the tested Minecraft and RealEstate10K benchmarks.
citing papers explorer
-
World Models as Group Actions
Formalizes video world models as group actions on states and uses latent regularization with synthesized supervision to enforce consistency, introducing GAC and GAR metrics that improve structural correctness in SOTA models.
-
Loki: Representation over Architecture for Diffusion-Based Portrait Animation
Loki replaces RGB conditioning stacks with identity-orthogonal parametric face encodings rasterized for diffusion, achieving efficient cross-ID portrait animation without cross-ID training data.
-
Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenization
DRoRAE adaptively fuses multi-layer features from vision encoders via energy-constrained routing to enrich visual tokens, cutting rFID from 0.57 to 0.29 and generation FID from 1.74 to 1.65 on ImageNet-256 while revealing a log-linear scaling law with fusion capacity.
-
Discrete Langevin-Inspired Posterior Sampling
ΔLPS is a gradient-guided discrete posterior sampler for inverse problems that works with masked or uniform discrete diffusion priors and outperforms prior discrete methods on image restoration tasks.
-
What Cohort INRs Encode and Where to Freeze Them
Optimal INR freeze depth matches highest weight stable rank layer; SAEs reveal SIREN atoms are localized while FFMLP atoms trace cohort contours with causal impact on PSNR.
-
LENS: Low-Frequency Eigen Noise Shaping for Efficient Diffusion Sampling
LENS shapes low-frequency eigen noise with a lightweight network to enable efficient, high-quality sampling in distilled diffusion models.
-
Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator
A feed-forward feature-Gaussian plus one-step geometry-aware pixel-flow simulator converts large image collections into 20K interactive scenes and 10M+ navigation samples that improve zero-shot Habitat and real-robot performance.
-
Amplifying Membership Signal Through Chained Regeneration
MADreMIA amplifies membership inference signals by showing that memorized samples maintain higher coherence and slower degradation in chained regeneration trajectories than non-members.
-
DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View Transformers
DPPE decouples rotation and translation in camera positional encodings for multi-view transformers to resolve late-stage training stagnation and improve generalization in novel view synthesis.
-
Hierarchical Variational Policies for Reward-Guided Diffusion
A hierarchical variational formulation amortizes test-time guidance in diffusion models to achieve strong quality-speed tradeoffs with significantly reduced inference compute.
-
DiRotQ: Rotation-Aware Quantization for 4-bit Diffusion Transformers
DiRotQ uses PCA-based rotation-aware activation quantization combined with GPTQ to achieve better FID and PSNR in 4-bit diffusion transformers than prior methods like SVDQuant.
-
Aligning Latent Geometry for Spherical Flow Matching in Image Generation
Projecting VAE latents to a fixed spherical radius and replacing linear interpolation with spherical linear interpolation improves class-conditional ImageNet-256 FID while leaving the diffusion architecture unchanged.
-
TransmissiveGS: Residual-Guided Disentangled Gaussian Splatting for Transmissive Scene Reconstruction and Rendering
TransmissiveGS disentangles reflections from transmissions in Gaussian Splatting via dual-Gaussian modeling, residual cues, and a reflection light field for improved transmissive scene reconstruction.
-
WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors
The paper presents WorldReasonBench, a benchmark that tests video generators on maintaining physical, social, logical, and informational consistency when predicting future states from initial conditions and actions.
-
SocialDirector: Training-Free Social Interaction Control for Multi-Person Video Generation
SocialDirector uses spatiotemporal actor masking and directional reweighting on cross-attention maps to reduce actor-action mismatches and improve target-directed interactions in generated multi-person videos.
-
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.
-
Toward Better Geometric Representations for Molecule Generative Models
LENSEs improves representation-conditioned molecule generation by jointly training a multi-level representation head, perceptual loss, and REPA alignment on pretrained encoders, yielding 97.28% validity and 98.51% stability on GEOM-DRUG.
-
UniISP: A Unified ISP Framework for Both Human and Machine Vision
UniISP unifies ISP processing with a Hybrid Attention Module and Feature Adapter to produce images that are both visually pleasing for humans and informative for computer vision models.
-
Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLM
Slot-MLLM introduces a slot-attention-based object-centric visual tokenizer with Q-Former encoder, diffusion decoder, and residual vector quantization for improved local visual comprehension and generation in multimodal LLMs.
-
MMGS: 10$\times$ Compressed 3DGS through Optimal Transport Aggregation based on Multi-view Ranking
MMGS compresses 3DGS models to 10% primitives with preserved rendering quality and 10x training speedup by combining multi-view geometric ranking with global OT aggregation and densification.
-
HDRFace: Rethinking Face Restoration with High-Dimensional Representation
HDRFace injects high-dimensional facial features from low-quality and intermediate images into diffusion models via SDFM fusion, reporting gains on SD V2.1-base and Qwen-Image.
-
Sword: Style-Robust World Models as Simulators via Dynamic Latent Bootstrapping for VLA Policy Post-Training
Sword improves world model simulators for VLA policies by disentangling visual style from dynamics and bootstrapping latents for better consistency, outperforming baselines on LIBERO in generalization and RL post-training success.
-
VRAG: Learning World Models for Interactive Video Generation
VRAG improves long-horizon interactive video generation by conditioning autoregressive diffusion on retrieved historical frames and explicit global state, outperforming long-context baselines on the tested Minecraft and RealEstate10K benchmarks.