WorldJen is a new benchmark for generative video models that uses VLM-judged multi-dimensional Likert questionnaires validated against human preferences to achieve perfect tier agreement.
hub
The unreasonable effectiveness of deep features as a perceptual metric
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 11roles
background 1polarities
background 1representative citing papers
A feature-space method that erases usable identity information from face images via learnable perturbations and a Face Revive Generator, rendering them ineffective for deepfake swapping while preserving visual quality.
Proposes World-Ego Modeling with WEM using CP-MoE diffusion and a new HTEWorld benchmark, claiming SOTA on hybrid navigation-manipulation tasks.
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.
VAGS adapts the CFG scale at each ODE step using velocity alignment signals to raise structural fidelity in editing and sample quality in generation over fixed-scale baselines.
ReactiveGWM introduces a decoupled diffusion architecture for player-NPC interactions that learns game-agnostic response logic for zero-shot strategy transfer across games.
DiffST delivers state-of-the-art real-world space-time video super-resolution with 17x faster inference than prior diffusion methods by using one-step sampling, cross-frame context aggregation, and video representation guidance.
PRISM improves text image super-resolution by rectifying global priors with flow-matching and modeling local structural uncertainty in a single diffusion pass, achieving SOTA results at millisecond inference.
Self-supervised models learn to perceive and manipulate the flow of time in videos, supporting speed detection, large-scale slow-motion data curation, and temporally controllable video synthesis.
LPM 1.0 generates infinite-length, identity-stable, real-time audio-visual conversational performances for single characters using a distilled causal diffusion transformer and a new benchmark.
Directly predicting clean data with large-patch pixel Transformers enables strong generative performance in diffusion models where noise prediction fails at high dimensions.
citing papers explorer
-
WorldJen: An End-to-End Multi-Dimensional Benchmark for Generative Video Models
WorldJen is a new benchmark for generative video models that uses VLM-judged multi-dimensional Likert questionnaires validated against human preferences to achieve perfect tier agreement.
-
ID-Eraser: Proactive Defense Against Face Swapping via Identity Perturbation
A feature-space method that erases usable identity information from face images via learnable perturbations and a Face Revive Generator, rendering them ineffective for deepfake swapping while preserving visual quality.
-
World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks
Proposes World-Ego Modeling with WEM using CP-MoE diffusion and a new HTEWorld benchmark, claiming SOTA on hybrid navigation-manipulation tasks.
-
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.
-
VAGS: Velocity Adaptive Guidance Scale for Image Editing and Generation
VAGS adapts the CFG scale at each ODE step using velocity alignment signals to raise structural fidelity in editing and sample quality in generation over fixed-scale baselines.
-
ReactiveGWM: Steering NPC in Reactive Game World Models
ReactiveGWM introduces a decoupled diffusion architecture for player-NPC interactions that learns game-agnostic response logic for zero-shot strategy transfer across games.
-
DiffST: Spatiotemporal-Aware Diffusion for Real-World Space-Time Video Super-Resolution
DiffST delivers state-of-the-art real-world space-time video super-resolution with 17x faster inference than prior diffusion methods by using one-step sampling, cross-frame context aggregation, and video representation guidance.
-
PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolution
PRISM improves text image super-resolution by rectifying global priors with flow-matching and modeling local structural uncertainty in a single diffusion pass, achieving SOTA results at millisecond inference.
-
Seeing Fast and Slow: Learning the Flow of Time in Videos
Self-supervised models learn to perceive and manipulate the flow of time in videos, supporting speed detection, large-scale slow-motion data curation, and temporally controllable video synthesis.
-
LPM 1.0: Video-based Character Performance Model
LPM 1.0 generates infinite-length, identity-stable, real-time audio-visual conversational performances for single characters using a distilled causal diffusion transformer and a new benchmark.
-
Back to Basics: Let Denoising Generative Models Denoise
Directly predicting clean data with large-patch pixel Transformers enables strong generative performance in diffusion models where noise prediction fails at high dimensions.