Papers Video Generation
“Video Generation” 태그가 달린 논문 2,973편 · 필터 해제
GRACE: Generation-aware latent compression for efficient video generation
Highly compressed video autoencoders offer an effective way to accelerate video diffusion models, as the Diffusion Transformer (DiT) operates on far fewer tokens. However, such autoencoders are challenging to train, sinc…
Video GenerationSGF+: Decoupling Gradient Flows for Autoregressive Video Generation
Autoregressive video generation requires denoising the current frames while writing their key-value representations as context for future predictions. However, these two roles typically share parameters, and we find that…
Video GenerationAdSpark: A Large-Scale Dataset and Benchmark for Product-Centric Advertisement Video Generation
Product-centric advertisement video generation aims to create promotional videos that preserve fine-grained product identity while presenting selling points through coherent multi-shot narratives. However, this emerging …
Visual StorytellingVideo GenerationWorld Models' Last Exam in Physics
Video world models can produce visually convincing yet physically inconsistent sequences, raising concerns about their reliability for prediction and planning in embodied AI systems. Existing evaluations often rely on mo…
Video GenerationRealtimeWAM: One-Step Asynchronous World Action Models
World Action Models (WAMs) incorporate visual representations from video generation backbones to guide action prediction. Recent efficient WAMs adopt Mixture-of-Transformers (MoT) architectures and compute video represen…
Video GenerationS2PD: Serial-to-Parallel Diffusion for Physically and Logically Consistent Video Generation
Bidirectional video diffusion models denoise entire videos in parallel, yet when trained on effectively unlimited in-distribution data from procedural generators, continue to violate physical laws and simple symbolic rul…
Physical SimulationsVideo GenerationKandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation
We present Kandinsky 6.0 Video, a family of foundation diffusion models for synchronized text-to-audio-video generation, comprising Kandinsky 6.0 Video Lite (3B parameters) and Kandinsky 6.0 Video Pro (29B parameters). B…
Audio GenerationVideo GenerationWorld Embedding Benchmark
Physical fidelity has received increasing attention in world models and video generation, yet how video representations encode physical information remains less understood. We introduce the World Embedding Benchmark, com…
Video GenerationVideo RetrievalProAR: Learning Prospective Reasoning with Autoregressive Video Models
Autoregressive (AR) video models excel at causal generation, but their reliance on next-chunk prediction confines them to a short-sighted, reactive paradigm. This limitation is particularly consequential for reasoning-or…
Visual ReasoningVideo GenerationDuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation
Streaming video generation has benefited from distribution matching distillation (DMD), which matches the joint distribution of video frames to a video teacher's approximation of the real video distribution. Although thi…
Video GenerationIn-Distribution Forcing for Long Video Generation at Test Time
Modern autoregressive (AR) video diffusion models excel at short-horizon video generation, yet generating long videos remains challenging due to drifting, where colors and textures shift, and motion dynamics decay. Exist…
Video GenerationHiPhy: Hierarchical Alignment for Physically-Plausible Multi-Principle Video Generation
Video generation models have achieved remarkable visual fidelity and have strong potential to become general-purpose world simulators. Despite this progress, they still fail to generate videos which adhere to laws of phy…
Reinforcement LearningVideo GenerationDMAD: Distribution Matching as Adversarial Distillation for Fast Visual Generation
Distribution Matching Distillation (DMD) trains a few-step student from the difference between separately estimated target and student scores, so it must keep an auxiliary diffusion model fitted to the student's evolving…
Video GenerationGenerative Cinematographer: Composing Camera and Object Motion in 3D
Current controllable video generation systems often rely on 2D motion trajectories or sparse drag signals for object motion. These controls are ambiguous because the same 2D trajectory can correspond to different 3D moti…
Video GenerationMosaiChunk: Compositing Spatio-Temporal Memory for Autoregressive Video Generation
Long-horizon autoregressive video generation is limited by a finite context window. When an object or scene falls out of context, its fine-grained visual details may be lost and difficult to recover upon reappearance. To…
Video GenerationUniWAM: Unified World-Action Model
Vision-language-action models benefit from the understanding and reasoning capabilities of pretrained vision-language models, but action-only supervision provides limited grounding in world dynamics. Conversely, world-ac…
Visual Question AnsweringInstruction FollowingVideo GenerationToken-Level Video Reinforcement Learning
Reinforcement learning (RL) for video generation usually assigns one scalar reward to an entire sampled video. Yet a video is not uniformly flawed: some visual tokens may already satisfy the prompt, whereas others requir…
Reinforcement LearningVideo GenerationDiVid: Diagnosing Dimension-Specific Diversity Collapse in Video Generation Models
Despite remarkable progress, video generation models often produce highly similar outputs when repeatedly sampled from the same prompt, limiting their usefulness for creative exploration. Existing diversity evaluations p…
Video GenerationVTR-Bench: A Systematic Benchmark for Evaluating Visual Text Rendering in Video Generation
Recent video generation models can produce highly realistic videos from natural language instructions, with visual quality approaching cinematic standards. Existing evaluation benchmarks, however, predominantly assess vi…
Video GenerationEgo2Act: Evaluating Goal-Directed Manipulation in Egocentric Video Generation
Video generation models are increasingly being explored as world simulators for embodied planning and learning. To do so effectively, these models must not only generate visually appealing frames, but also predict how en…
Video Generation