QWERTY enables training-free motion control in pretrained image-to-video DiTs by warping the frame-invariant semantic subspace of queries in 3D full attention and using the predicted noise as self-guidance for latent optimization.
Canonical reference
Title resolution pending
Canonical reference. 83% of citing Pith papers cite this work as background.
33
Pith papers citing it
Background
83% of classified citations
citation-role summary
background 5
method 1
citation-polarity summary
years
2026 33representative citing papers
ISPA reduces KV cache size by up to 50% in AR video models by transitioning layers to local attention and applying instance-specific least-squares weight modulation to compensate for lost history.
AVBench is a benchmark for human-centric AV generation evaluation featuring ten fine-grained dimensions and preference-learned evaluators that output continuous probabilistic scores from binary decisions.
Video diffusion models can be adapted into permutation-invariant generators for sparse novel view synthesis by treating the problem as video completion and removing temporal order cues.
Grounded Forcing introduces dual memory caching, reference-based positional embeddings, and proximity-weighted recaching to bridge stable semantics with local dynamics, improving long-range consistency in autoregressive video synthesis.
Flow Divergence Sampler refines flow matching by computing velocity field divergence to correct ambiguous intermediate states during inference, improving fidelity in text-to-image and inverse problem tasks.
WCog-VLA couples Game-CoT semantic reasoning with an aligned decoupled diffusion transformer to generate joint multi-agent trajectories and reaches 92.9 PDMS on NAVSIM.
Predicting quantized latent residuals (Latent Drift with FSQ) avoids identity collapse and noise interpolation, improving patient-specific 3D MRI neuro-forecasting over diffusion and autoregressive baselines.
Hybrid T2I generation with teacher-student pseudo-labeling plus VRAIN context-aware I2I rare-class editing improves LVIS instance segmentation AP, especially on rare categories.
GACR reformulates cloud removal as an observation-anchored residual inversion process with geo-contextual prior alignment to preserve semantic structures for improved downstream interpretation tasks.
ICDepth adapts text-to-video diffusion transformers for video depth estimation via in-context conditioning, achieving SOTA results on benchmarks with 6-13x less training data than prior generative methods.
Ink3D decouples geometry from texture by generating dense orbit videos with a conditional video model and baking them via a neural optimizer to produce complex 3D textures.
ChronoFlow-Policy improves visuomotor policy learning by co-training action generation with prediction of past-current-future gripper-object keypoint trajectories.
InterTalk generates real-time multi-participant conversational talking-face videos by iteratively refining each person's lip, eye, and head motions from other participants' audio and motion feedback.
SyncCache accelerates DiT-based audio-driven portrait animation up to 4.12x via spatially-asymmetric probing and modality-decoupled caching while preserving near-lossless quality and audio sync.
Prompt2Effect is a weight-driven hypernetwork that synthesizes LoRA adapters for I2V models from prompts and base weights via SVD parameterization, matching fine-tuned quality at 3.3s inference instead of 56 GPU hours.
Echo4DIR reconstructs continuous 4D cardiac geometry from sparse 2D echocardiography videos using implicit representations, epipolar feature fusion, self-supervised domain adaptation, and radial SDF alignment to achieve up to 98.35% Dice overlap.
StreamEdit enables high-quality training-free video editing by adapting streaming video generation models with dual-branch fast sampling, self-attention bridge, cross-attention grounding, source-oriented guidance, and visual prompting, outperforming prior methods in few-step regimes.
Pretrained autoencoders in medical latent diffusion encode discriminative features well for reconstruction but structure their latent spaces in ways that hinder classifier learning, a gap that persists across architectures and is not closed by domain fine-tuning.
UniFixer is a universal reference-guided framework that fixes spatial, temporal, and backbone-related degradations in diffusion-based view synthesis via coarse-to-fine modules and achieves zero-shot SOTA results on novel view synthesis and stereo conversion.
Embody4D generates novel-view videos from monocular robot videos via a 3D-aware synthesis pipeline, confidence-aware expert modulation, and interaction-aware attention for embodied 4D world modeling.
CoInteract adds a human-aware mixture-of-experts and spatially-structured co-generation to a diffusion transformer to synthesize videos with stable structures and physically plausible human-object contacts.
A decoupled memory branch with hybrid cues, cross-attention, and gating improves spatial consistency and data efficiency in long-horizon camera-trajectory video generation.
Interpolating only the video frames between synchronized exo and ego clips already turns discontinuous cross-view generation into continuous sequence modeling and measurably improves diffusion-based Exo2Ego synthesis.
citing papers explorer
-
QWERTY: Training-Free Motion Control via Query-Warped Video Diffusion Transformers
QWERTY enables training-free motion control in pretrained image-to-video DiTs by warping the frame-invariant semantic subspace of queries in 3D full attention and using the predicted noise as self-guidance for latent optimization.
-
Towards Memory-Efficient Autoregressive Video Generation via Instance-Specific Parametric Absorption
ISPA reduces KV cache size by up to 50% in AR video models by transitioning layers to local attention and applying instance-specific least-squares weight modulation to compensate for lost history.
-
AVBench: Human-Aligned and Automated Evaluation Benchmark for Audio-Video Generative Models
AVBench is a benchmark for human-centric AV generation evaluation featuring ten fine-grained dimensions and preference-learned evaluators that output continuous probabilistic scores from binary decisions.
-
Novel View Synthesis as Video Completion
Video diffusion models can be adapted into permutation-invariant generators for sparse novel view synthesis by treating the problem as video completion and removing temporal order cues.
-
Grounded Forcing: Bridging Time-Independent Semantics and Proximal Dynamics in Autoregressive Video Synthesis
Grounded Forcing introduces dual memory caching, reference-based positional embeddings, and proximity-weighted recaching to bridge stable semantics with local dynamics, improving long-range consistency in autoregressive video synthesis.
-
Training-Free Refinement of Flow Matching with Divergence-based Sampling
Flow Divergence Sampler refines flow matching by computing velocity field divergence to correct ambiguous intermediate states during inference, improving fidelity in text-to-image and inverse problem tasks.
-
WCog-VLA: A Dual-Level World-Cognitive Vision-Language-Action Model for End-to-End Autonomous Driving
WCog-VLA couples Game-CoT semantic reasoning with an aligned decoupled diffusion transformer to generate joint multi-agent trajectories and reaches 92.9 PDMS on NAVSIM.
-
Progression as Latent Drift: Generative Forecasting of Slow-Evolving Pathologies
Predicting quantized latent residuals (Latent Drift with FSQ) avoids identity collapse and noise interpolation, improving patient-specific 3D MRI neuro-forecasting over diffusion and autoregressive baselines.
-
TMI: Text-to-Image Meets Image-to-Image for Complementary Data Synthesis to Boost Long-Tailed Instance Segmentation
Hybrid T2I generation with teacher-student pseudo-labeling plus VRAIN context-aware I2I rare-class editing improves LVIS instance segmentation AP, especially on rare categories.
-
Interpretation-Oriented Cloud Removal via Observation-Anchored Residual Flow with Geo-Contextual Alignment
GACR reformulates cloud removal as an observation-anchored residual inversion process with geo-contextual prior alignment to preserve semantic structures for improved downstream interpretation tasks.
-
ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning
ICDepth adapts text-to-video diffusion transformers for video depth estimation via in-context conditioning, achieving SOTA results on benchmarks with 6-13x less training data than prior generative methods.
-
Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Models
Ink3D decouples geometry from texture by generating dense orbit videos with a conditional video model and baking them via a neural optimizer to produce complex 3D textures.
-
ChronoFlow-Policy: Unifying Past-Current-Future Interaction Flow in Visuomotor Policy Learning
ChronoFlow-Policy improves visuomotor policy learning by co-training action generation with prediction of past-current-future gripper-object keypoint trajectories.
-
Towards Flexible, Natural, Efficient Interaction for Conversational Talking Face Generation
InterTalk generates real-time multi-participant conversational talking-face videos by iteratively refining each person's lip, eye, and head motions from other participants' audio and motion feedback.
-
SyncCache: Exploiting Asymmetric Dynamics for Fast Audio-Driven Portrait Animation
SyncCache accelerates DiT-based audio-driven portrait animation up to 4.12x via spatially-asymmetric probing and modality-decoupled caching while preserving near-lossless quality and audio sync.
-
Prompt2Effect: Training-Free Image-to-Video Model Specialization via LoRA Generation
Prompt2Effect is a weight-driven hypernetwork that synthesizes LoRA adapters for I2V models from prompts and base weights via SVD parameterization, matching fine-tuned quality at 3.3s inference instead of 56 GPU hours.
-
Echo4DIR: 4D Implicit Heart Reconstruction from 2D Echocardiography Videos
Echo4DIR reconstructs continuous 4D cardiac geometry from sparse 2D echocardiography videos using implicit representations, epipolar feature fusion, self-supervised domain adaptation, and radial SDF alignment to achieve up to 98.35% Dice overlap.
-
StreamEdit: Training-Free Video Editing via Few-Step Streaming Video Generation
StreamEdit enables high-quality training-free video editing by adapting streaming video generation models with dual-branch fast sampling, self-attention bridge, cross-attention grounding, source-oriented guidance, and visual prompting, outperforming prior methods in few-step regimes.
-
The Learnability Gap in Medical Latent Diffusion
Pretrained autoencoders in medical latent diffusion encode discriminative features well for reconstruction but structure their latent spaces in ways that hinder classifier learning, a gap that persists across architectures and is not closed by domain fine-tuning.
-
UniFixer: A Universal Reference-Guided Fixer for Diffusion-Based View Synthesis
UniFixer is a universal reference-guided framework that fixes spatial, temporal, and backbone-related degradations in diffusion-based view synthesis via coarse-to-fine modules and achieves zero-shot SOTA results on novel view synthesis and stereo conversion.
-
Embody4D: A Generalist Data Engine for Embodied 4D World Modeling
Embody4D generates novel-view videos from monocular robot videos via a 3D-aware synthesis pipeline, confidence-aware expert modulation, and interaction-aware attention for embodied 4D world modeling.
-
CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation
CoInteract adds a human-aware mixture-of-experts and spatially-structured co-generation to a diffusion transformer to synthesize videos with stable structures and physically plausible human-object contacts.
-
Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation
A decoupled memory branch with hybrid cues, cross-attention, and gating improves spatial consistency and data efficiency in long-horizon camera-trajectory video generation.
-
From Synchrony to Sequence: Exo-to-Ego Generation via Interpolation
Interpolating only the video frames between synchronized exo and ego clips already turns discontinuous cross-view generation into continuous sequence modeling and measurably improves diffusion-based Exo2Ego synthesis.
-
ReplicateAnyScene: Zero-Shot Video-to-3D Composition via Textual-Visual-Spatial Alignment
ReplicateAnyScene performs fully automated zero-shot video-to-compositional-3D reconstruction by cascading alignments of generic priors from vision foundation models across textual, visual, and spatial dimensions.
-
Rein3D: Reinforced 3D Indoor Scene Generation with Panoramic Video Diffusion Models
Rein3D generates photorealistic, globally consistent 3D indoor scenes by using a restore-and-refine process where radial panoramic videos are restored via diffusion models and then used to update a 3D Gaussian field.
-
What Matters in Virtual Try-Off? Dual-UNet Diffusion Model For Garment Reconstruction
A Dual-UNet diffusion model for virtual garment reconstruction from clothed images sets new benchmarks on VITON-HD and DressCode by optimizing Stable Diffusion variants, mask conditioning, and auxiliary losses.
-
Pose-Aware Diffusion for 3D Generation
PAD synthesizes 3D geometry in observation space via depth unprojection as anchor to eliminate pose ambiguity in image-to-3D generation.
-
Allo{SR}$^2$: Rectifying One-Step Super-Resolution to Stay Real via Allomorphic Generative Flows
AlloSR² claims state-of-the-art one-step real-world super-resolution by SNR-guided trajectory init, velocity regularization (FATC), and allomorphic self-adversarial distillation that preserves flow-matching generative priors.
-
UniMesh: Unifying 3D Mesh Understanding and Generation
UniMesh unifies 3D mesh generation and understanding in one model via a Mesh Head interface, Chain of Mesh iterative editing, and an Actor-Evaluator self-reflection loop.
-
SHIFT: Steering Hidden Intermediates in Flow Transformers
SHIFT learns and applies steering vectors to selected layers and timesteps in DiT models to suppress concepts, shift styles, or bias objects while keeping image quality and prompt adherence intact.
-
Dual-End Consistency Model
DE-CM trains a flow-map consistency model on three sub-trajectories (coupling, instantaneous, noise-to-noisy) and reports 1.70 FID one-step on ImageNet 256.
- OmniCamera: A Unified Framework for Multi-task Video Generation with Arbitrary Camera Control