VINS-120K supplies the first large-scale set of instruction-image-edited-image triplets at ultra-high resolution together with an adaptation strategy that improves detail synthesis.
hub Mixed citations
Roformer: Enhanced transformer with rotary position embedding.Neurocomputing, 568:127063
Mixed citation behavior. Most common role is method (60%).
32
Pith papers citing it
Method
60% of classified citations
hub tools
citation-role summary
method 3
background 2
citation-polarity summary
representative citing papers
Reshoot-Anything trains a diffusion transformer on pseudo multi-view triplets created by cropping and warping monocular videos to achieve temporally consistent video reshooting with robust camera control on dynamic scenes.
OneHOI unifies HOI generation and editing in one conditional diffusion transformer using role-aware tokens, structured attention, and joint training on mixed datasets to reach SOTA on both tasks.
ASTRA disentangles subject identity from pose structure in diffusion transformers via retrieval-augmented pose guidance, asymmetric EURoPE embeddings, and a DSM adapter to improve multi-subject generation.
An autoregressive diffusion model on sparse point trajectories predicts multi-modal future scene dynamics from single images with orders-of-magnitude faster sampling than dense video simulators while matching accuracy.
OmniSonic introduces a TriAttn-DiT architecture with MoE gating to jointly generate on-screen, off-screen, and speech audio from video and text, outperforming prior models on a new UniHAGen-Bench.
InCaRPose is a Transformer-based model trained on synthetic data that predicts absolute metric-scale relative poses between distorted in-cabin camera views and generalizes to real images while releasing a new test dataset.
TABLeT uses a pre-trained 2D natural image autoencoder to tokenize 3D fMRI volumes into compact continuous tokens, enabling efficient long-range transformer modeling that outperforms voxel-based baselines on UKB, HCP, and ADHD-200 while using less memory.
UniDAC achieves universal metric depth estimation across camera types by decoupling relative depth prediction from spatially varying scale estimation using a depth-guided module and distortion-aware positional embedding.
DiFlowDubber is the first video dubbing system using a discrete flow matching backbone with two-stage training that pre-trains a zero-shot TTS then adapts it via cross-modal alignment to produce content-consistent, lip-synchronized speech.
ChArtist generates pictorial charts via a Diffusion Transformer using skeleton-based spatial control and reference-image subject control, supported by a new 30,000-triplet dataset and data accuracy metric.
ZipMap achieves linear-time bidirectional 3D reconstruction by zipping image collections into a compact stateful representation via test-time training layers.
LooseRoPE modulates RoPE in diffusion attention maps to continuously trade off between preserving a pasted object's identity and harmonizing it with its new surroundings.
OmniAlpha is a unified multi-task RL framework that uses an alpha-aware VAE, sequence-to-sequence Diffusion Transformer, and layer-aware rewards to improve transparency-aware generation across five task categories.
HierEdit enables efficient 4K image editing via low-resolution proxy localization followed by hierarchical local-window diffusion that reuses unaltered regions as conditioning.
MaTe proposes a training-free diffusion transformer that performs material transfer using only images by integrating them at the token level for unified multi-modal attention in a shared latent space.
VAP is a training-free active-perception method that improves zero-shot long-form video QA performance and frame efficiency up to 5.6x in VLMs by selecting keyframes that differ from priors generated by a text-conditioned video model.
Sculpt4D generates temporally coherent 4D shapes by integrating a block sparse attention mechanism with time-decaying mask into a pretrained 3D diffusion transformer, achieving SOTA results with 56% less computation.
A 64x temporally compressed motion embedding learned from trackers enables efficient conditional flow-matching generation of long-term motions that outperform video models and task-specific methods.
Next-scale autoregressive modeling with cross-scale and in-scale refinements produces SOTA text-to-motion generation by enforcing coarse-to-fine causal hierarchy.
TrajTok learns to tokenize video into object-trajectory tokens end-to-end, improving video CLIP, probing, and VLM performance over patch and token-merging baselines.
MMHNet enables video-to-audio models trained on short clips to generalize and generate audio for videos over 5 minutes long.
RenderFlow replaces iterative diffusion with flow matching for deterministic single-step neural rendering that achieves near real-time photorealistic quality and extends to inverse rendering via an adapter module.
DriveLaW unifies video world modeling and trajectory planning by injecting video-generator latents into a diffusion planner, achieving SOTA video prediction and a new record on the NAVSIM planning benchmark.
citing papers explorer
-
VINS-120K: Ultra High-Resolution Image Editing with A Large-Scale Dataset
VINS-120K supplies the first large-scale set of instruction-image-edited-image triplets at ultra-high resolution together with an adaptation strategy that improves detail synthesis.
-
Reshoot-Anything: A Self-Supervised Model for In-the-Wild Video Reshooting
Reshoot-Anything trains a diffusion transformer on pseudo multi-view triplets created by cropping and warping monocular videos to achieve temporally consistent video reshooting with robust camera control on dynamic scenes.
-
OneHOI: Unifying Human-Object Interaction Generation and Editing
OneHOI unifies HOI generation and editing in one conditional diffusion transformer using role-aware tokens, structured attention, and joint training on mixed datasets to reach SOTA on both tasks.
-
ASTRA: Enhancing Multi-Subject Generation with Retrieval-Augmented Pose Guidance and Disentangled Position Embedding
ASTRA disentangles subject identity from pose structure in diffusion transformers via retrieval-augmented pose guidance, asymmetric EURoPE embeddings, and a DSM adapter to improve multi-subject generation.
-
Envisioning the Future, One Step at a Time
An autoregressive diffusion model on sparse point trajectories predicts multi-modal future scene dynamics from single images with orders-of-magnitude faster sampling than dense video simulators while matching accuracy.
-
OmniSonic: Towards Universal and Holistic Audio Generation from Video and Text
OmniSonic introduces a TriAttn-DiT architecture with MoE gating to jointly generate on-screen, off-screen, and speech audio from video and text, outperforming prior models on a new UniHAGen-Bench.
-
InCaRPose: In-Cabin Relative Camera Pose Estimation Model and Dataset
InCaRPose is a Transformer-based model trained on synthetic data that predicts absolute metric-scale relative poses between distorted in-cabin camera views and generalizes to real images while releasing a new test dataset.
-
Can Natural Image Autoencoders Compactly Tokenize fMRI Volumes for Long-Range Dynamics Modeling?
TABLeT uses a pre-trained 2D natural image autoencoder to tokenize 3D fMRI volumes into compact continuous tokens, enabling efficient long-range transformer modeling that outperforms voxel-based baselines on UKB, HCP, and ADHD-200 while using less memory.
-
UniDAC: Universal Metric Depth Estimation for Any Camera
UniDAC achieves universal metric depth estimation across camera types by decoupling relative depth prediction from spatially varying scale estimation using a depth-guided module and distortion-aware positional embedding.
-
DiFlowDubber: Discrete Flow Matching for Automated Video Dubbing via Cross-Modal Alignment and Synchronization
DiFlowDubber is the first video dubbing system using a discrete flow matching backbone with two-stage training that pre-trains a zero-shot TTS then adapts it via cross-modal alignment to produce content-consistent, lip-synchronized speech.
-
ChArtist: Generating Pictorial Charts with Unified Spatial and Subject Control
ChArtist generates pictorial charts via a Diffusion Transformer using skeleton-based spatial control and reference-image subject control, supported by a new 30,000-triplet dataset and data accuracy metric.
-
ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training
ZipMap achieves linear-time bidirectional 3D reconstruction by zipping image collections into a compact stateful representation via test-time training layers.
-
LooseRoPE: Content-aware Attention Manipulation for Semantic Harmonization
LooseRoPE modulates RoPE in diffusion attention maps to continuously trade off between preserving a pasted object's identity and harmonizing it with its new surroundings.
-
OmniAlpha: Aligning Transparency-Aware Generation via Multi-Task Unified Reinforcement Learning
OmniAlpha is a unified multi-task RL framework that uses an alpha-aware VAE, sequence-to-sequence Diffusion Transformer, and layer-aware rewards to improve transparency-aware generation across five task categories.
-
HierEdit: Region-Aware Hierarchical Diffusion for Efficient High-Resolution Editing
HierEdit enables efficient 4K image editing via low-resolution proxy localization followed by hierarchical local-window diffusion that reuses unaltered regions as conditioning.
-
MaTe: Images Are All You Need for Material Transfer via Diffusion Transformer
MaTe proposes a training-free diffusion transformer that performs material transfer using only images by integrating them at the token level for unified multi-modal attention in a shared latent space.
-
Video Active Perception: Effective Inference-Time Long-Form Video Understanding with Vision-Language Models
VAP is a training-free active-perception method that improves zero-shot long-form video QA performance and frame efficiency up to 5.6x in VLMs by selecting keyframes that differ from priors generated by a text-conditioned video model.
-
Sculpt4D: Generating 4D Shapes via Sparse-Attention Diffusion Transformers
Sculpt4D generates temporally coherent 4D shapes by integrating a block sparse attention mechanism with time-decaying mask into a pretrained 3D diffusion transformer, achieving SOTA results with 56% less computation.
-
Learning Long-term Motion Embeddings for Efficient Kinematics Generation
A 64x temporally compressed motion embedding learned from trackers enables efficient conditional flow-matching generation of long-term motions that outperform video models and task-specific methods.
-
Next-Scale Autoregressive Models for Text-to-Motion Generation
Next-scale autoregressive modeling with cross-scale and in-scale refinements produces SOTA text-to-motion generation by enforcing coarse-to-fine causal hierarchy.
-
TrajTok: Learning Trajectory Tokens enables better Video Understanding
TrajTok learns to tokenize video into object-trajectory tokens end-to-end, improving video CLIP, probing, and VLM performance over patch and token-merging baselines.
-
Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models
MMHNet enables video-to-audio models trained on short clips to generalize and generate audio for videos over 5 minutes long.
-
RenderFlow: Single-Step Neural Rendering via Flow Matching
RenderFlow replaces iterative diffusion with flow matching for deterministic single-step neural rendering that achieves near real-time photorealistic quality and extends to inverse rendering via an adapter module.
-
DriveLaW:Unifying Planning and Video Generation in a Latent Driving World
DriveLaW unifies video world modeling and trajectory planning by injecting video-generator latents into a diffusion planner, achieving SOTA video prediction and a new record on the NAVSIM planning benchmark.
-
Native and Compact Structured Latents for 3D Generation
Introduces O-Voxel omni-voxel representation and Sparse Compression VAE for structured native 3D latents, enabling efficient training of large flow-matching models that produce higher-quality geometry and materials than prior methods.
-
WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling
A real-time video diffusion world model that uses dual action control, reframed position encodings, and context-aligned distillation to keep generated environments consistent over hundreds of frames.
-
Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation
Reward Forcing combines EMA-Sink tokens and Rewarded Distribution Matching Distillation to deliver state-of-the-art streaming video generation at 23.1 FPS without copying initial frames.
-
DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
DeCo decouples high- and low-frequency generation in pixel diffusion via a DiT plus lightweight decoder and a frequency-aware flow-matching loss, reaching FID 1.62 at 256x256 and 2.22 at 512x512 on ImageNet while closing the gap to latent diffusion methods.
-
TAP into the Patch Tokens: Leveraging Vision Foundation Model Features for AI-Generated Image Detection
Modern vision foundation models plus a tunable attention pooling classifier head deliver state-of-the-art detection of AI-generated and inpainted images, outperforming CLIP by over 12 percent accuracy.
-
DreamShot: Personalized Storyboard Synthesis with Video Diffusion Prior
DreamShot generates controllable multi-shot storyboards from text or character references by exploiting video diffusion priors and a Role-Attention Consistency Loss.
-
In Search of Lost DNA Sequence Pretraining
DNA pretraining suffers from inappropriate evaluation datasets, flawed neighbor-masking, and neglected vocabulary design; the authors supply guidelines and a reproducible testbed to fix them.
- simpleposter: A simple baseline for product poster generation