28 papers
PixelMoE: Scaling Pixel-Space Diffusion with LLM-Style Mixture-of-Experts
Ruixiao Dong, Jianmin Bao, Bozhi Luan +6
Pixel-space diffusion models provide an appealing alternative to latent-space diffusion models by directly modeling raw images without relying on a learned tokenizer. However, scal…
TrajCFG: Token-Wise Classifier-Free Guidance via Denoising Trajectory Feedback
Jingyu Liu, Hao Jiang, Yikang Ding +6
Classifier-free guidance (CFG) typically applies a shared scale to all latent tokens, although their velocity predictions evolve differently during sampling. We introduce Trajector…
DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models
Zhenglin Wan, Jiayu Chen, Zhengfeiyang Zhang +6
Online reinforcement learning (RL) fine-tunes diffusion models with black-box rewards, but reverse-process methods such as Flow-GRPO are limited in efficiency by poor credit assign…
From Evaluation to Enhancement: Benchmarking and Improving Think-with-Video Reasoning for Video Generative Models
Meng Luo, Yicheng Liu, Jiahao Wang +5
Video generation has advanced to produce visually compelling and temporally coherent results. Yet, whether these models can genuinely think with video--executing symbolic rules, re…
Motion Beyond Morphology: Bootstrapping Cross-Category Motion Transfer from Abstract Motion Representations
Zhixue Fang, Zhimin Zhang, Bi'an Du +6
Video motion transfer aims to animate a target object using dynamics from a reference video. Existing formulations largely rely on fixed structural correspondence, which becomes il…
MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control
Kaiqi Liu, Yunyao Mao, Ziqi Cai +8
While recent generative models produce high-fidelity videos, they struggle with the complex narrative control required for coherent multi-shot audio-visual generation. Existing met…
MemLearner: Learning to Query Context memory for Video World Models
Jiwen Yu, Jianxiong Gao, Jianhong Bai +7
Video World Models are interactive video generation models that predict future world states based on user actions and history video frames. A critical challenge in video world mode…
VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization
Junhao Cheng, Liang Hou, Tianxiong Zhong +4
The recent "Reasoning with Video" paradigm utilizes Video Generation Models (VGMs) to generate temporally coherent visual trajectories to complete reasoning tasks. Although state-o…
Edit-R2: Context-Aware Reinforcement Learning for Multi-Turn Image Editing
Yuxiao Ye, Haoran He, Fangyuan Kong +4
Text-guided image editing has advanced rapidly with diffusion models and unified multimodal foundation models. However, most existing methods remain confined to single-turn setting…
AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization
Yu Li, Menghan Xia, Gongye Liu +8
Despite being a pivotal frontier, interactive world modeling remains underexplored in terms of the versatile controllability required by practical scenarios. To bridge this gap, we…
OneReason Technical Report
OneRec Team, Biao Yang, Boyang Ding +81
Generative recommendation models in the OneRec family have been widely deployed in many real-world services, such as short-video, live-streaming, advertising, and e-commerce. Howev…
DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory
Zhenhao Yang, Xiaoshi Wu, Zhengyao Lv +5
Recent advances in video generative models have promoted rapid progress in controllable world models. However, maintaining fine-grained spatio-temporal consistency under long-horiz…
UniCustom: Unified Visual Conditioning for Multi-Reference Image Generation
Yiyan Xu, Qiulin Wang, Wenjie Wang +5
Multi-reference image generation aims to synthesize images from textual instructions while faithfully preserving subject identities from multiple reference images. Existing VLM-enh…
Kling-MotionControl Technical Report
Kling Team, Jialu Chen, Yikang Ding +21
Character animation aims to generate lifelike videos by transferring motion dynamics from a driving video to a reference image. Recent strides in generative models have paved the w…
3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation
Zhixue Fang, Xu He, Songlin Tang +5
Existing methods for human motion control in video generation typically rely on either 2D poses or explicit 3D parametric models (e.g., SMPL) as control signals. However, 2D poses…
Semantic Routing: Exploring Multi-Layer LLM Feature Weighting for Diffusion Transformers
Bozhou Li, Yushuo Guan, Haolin Li +7
Recent DiT-based text-to-image models increasingly adopt LLMs as text encoders, yet text conditioning remains largely static and often utilizes only a single LLM layer, despite pro…
TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions
Linli Yao, Yuancheng Wei, Yaojie Zhang +12
This paper proposes Omni Dense Captioning, a novel task designed to generate continuous, fine-grained, and structured audio-visual narratives with explicit timestamps. To ensure de…
VINO: A Unified Visual Generator with Interleaved OmniModal Context
Junyi Chen, Tong He, Zhoujie Fu +3
We present VINO, a unified visual generator that performs image and video generation and editing within a single framework. Instead of relying on task-specific models or independen…
SemanticGen: Video Generation in Semantic Space
Jianhong Bai, Xiaoshi Wu, Xintao Wang +9
State-of-the-art video generative models typically learn the distribution of video latents in the VAE space and map them to pixels using a VAE decoder. While this approach can gene…
Visual-Aware CoT: Achieving High-Fidelity Visual Consistency in Unified Models
Zixuan Ye, Quande Liu, Cong Wei +5
Recently, the introduction of Chain-of-Thought (CoT) has largely improved the generation ability of unified models. However, it is observed that the current thinking process during…
KlingAvatar 2.0 Technical Report
Kling Team, Jialu Chen, Yikang Ding +25
Avatar video generation models have achieved remarkable progress in recent years. However, prior work exhibits limited efficiency in generating long-duration high-resolution videos…
SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder
Minglei Shi, Haolin Wang, Borui Zhang +11
Visual generation grounded in Visual Foundation Model (VFM) representations offers a highly promising unified pathway for integrating visual understanding, perception, and generati…
FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusion
Xiangyang Luo, Qingyu Li, Xiaokun Liu +7
Current video generation models perform well at single-shot synthesis but struggle with multi-shot videos, facing critical challenges in maintaining character and background consis…
MultiShotMaster: A Controllable Multi-Shot Video Generation Framework
Qinghe Wang, Xiaoyu Shi, Baolu Li +7
Current video generation techniques excel at single-shot clips but struggle to produce narrative multi-shot videos, which require flexible shot arrangement, coherent narrative, and…