Image & Video Generation

MoviEdit is an end-to-end framework for long-form multi-shot video editing that combines scalable paired-data generation, a cascaded bidirectional–autoregressive editor, and a dedicated benchmark.

The paper reports Kling's experience that video generation quality is the projection of multimodal understanding across the data, conditioning, alignment, and evaluation chain.

Wave Forcing co-designs causal wavefront generation, three-stage training, and Wave Runtime to stream video at one chunk per concurrent forward round after pipeline fill while retaining all denoising updates.

The paper frames video generation through an agent harness that coordinates production, world-model interaction, and development toward recursive self-improvement.

PhotoGuider measures four photographic tokens with compact learned scorers to select 360° view directions, rank and refine crops, output camera parameters, and generate measurement-conditioned explanations.

FrameForge adapts a frozen video diffusion model to unified conditional image generation by selecting input-adaptive temporal RoPE experts and inserting a latent reasoning chain between condition and target.

LARC performs reasoning in continuous latent space for unified multimodal models, using curriculum SFT and self-evolving RL to improve image generation and enable test-time scaling.

Wizard is an agentic game world model that decouples explicit game-state control from video generation to enable real-time, zero-shot control of scenes, characters, and motions.

GLOW-FM is a one-step latent flow-matching framework for low-light image enhancement that uses Terminal Velocity Matching in a frozen Tiny-VAE latent space and requires a single function evaluation.

IDM keeps the full internal DMD correction and adds a feature-moment loss on generator EMA features, improving 2-NFE LongText scores on Z-Image-Turbo and Qwen-Image.

L3G-World combines an online-updated latent 3D Gaussian memory with a memory-conditioned video DiT to generate spatially consistent worlds in real time.

SpecSlot decouples output detail from global attention by splitting a fixed token budget into spatial anchors and spectral slots, sending only the lowest-radial slot per anchor through global blocks.

WeVisCut connects a stateful script-to-video agent harness, a four-stage pipeline that recovers executable supervision from finished videos, and a single 9B policy trained through SFT, runtime-verified RFT, Guided-OPD, and RCF-DAPO, evaluated on a 100-task benchmark with five metrics.

OmniShowcase generates omnidirectional subject-consistent videos from multi-view reference images by combining a 3D-asset-based data synthesis pipeline with surface-normal turntable conditioning reconstructed from the references.

A two-stage paradigm where autoregressive pretraining on semantic tokens acquires visual knowledge and a frozen-backbone pixel-diffusion stage renders images, yielding a 3B text-to-image model trained in about 6,600 H100 GPU-hours that scores 0.86 on GenEval and 87.78 on DPG-Bench.