17 papers
SEmoEdit: Probing and Harnessing the Editability of Pre-trained Speech Flows
Tianxin Xie, Pengfei Zhang, Kai Jiang +2
Existing training-based speech emotion editing methods often require substantial task-specific training and can be unstable. This motivates us to investigate whether the pretrained…
Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation
Jintao Zhang, Kai Jiang, Jintao Chen +32
We present Vidu S2, which comprises Vidu S2-Avatar, a real-time interactive digital-character model, and Vidu S2-Editing, a real-time video editing model. Moreover, we explore the…
TurboT2VA: Fast Large-Scale Text-to-Video-Audio Generation via Score-Regularized Consistency Distillation
Xiaoda Yang, Yuxiang Liu, Kaiwen Zheng +12
Joint text-to-video-audio generation produces synchronized visual and acoustic content, but the long sampling trajectories and heterogeneous multimodal computation of large models…
Vidu S1: A Real-Time Interactive Video Generation Model
Jintao Zhang, Kai Jiang, Jintao Chen +24
We introduce Vidu S1, a real-time interactive video generation model supporting voice control of digital characters. Users can control video generation content at any moment throug…
TurboServe: Serving Streaming Video Generation Efficiently and Economically
Youhe Jiang, Haoxu Wang, Haotong Bao +5
Streaming video generation is emerging as a new serving workload in which users interact with long-lived sessions that generate video progressively, chunk by chunk. Unlike offline…
KernelBenchX: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels
Han Wang, Jintao Zhang, Kai Jiang +3
LLM-based Triton kernel generation has attracted significant interest, yet a fundamental empirical question remains unanswered: where does this capability break down, and why? We p…
SageBwd: A Trainable Low-bit Attention
Jintao Zhang, Marco Chen, Haoxu Wang +5
Low-bit attention, such as SageAttention, has emerged as an effective approach for accelerating model inference, but its applicability to training remains poorly understood. In pri…
SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
Jintao Zhang, Kai Jiang, Chendong Xiang +5
Many training-free sparse attention methods are effective for accelerating diffusion models. Recently, several works suggest that making sparse attention trainable can further incr…
SLA2: Sparse-Linear Attention with Learnable Routing and Quantization-aware Training
Jintao Zhang, Haoxu Wang, Kai Jiang +6
Sparse-Linear Attention (SLA) combines sparse and linear attention to accelerate diffusion models and has shown strong performance in video generation. However, (i) SLA relies on a…
TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times
Jintao Zhang, Kaiwen Zheng, Kai Jiang +5
We introduce TurboDiffusion, a video generation acceleration framework that can speed up end-to-end diffusion generation by 100-200x while maintaining video quality. TurboDiffusion…
HiGR: Industrial-Scale Hierarchical Generative Slate Recommendation Framework in Tencent
Yunsheng Pang, Zijian Liu, Yudong Li +10
Slate recommendation, which presents users with a ranked item list in a single display, is ubiquitous across mainstream online platforms. While recent generative recommendation met…
PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation
Tianxin Xie, Wentao Lei, Kai Jiang +27
Text-to-audio-video (T2AV) generation is central to applications such as filmmaking and world modeling. However, current models often fail to produce physically plausible sounds. P…
SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention
Jintao Zhang, Haoxu Wang, Kai Jiang +10
In Diffusion Transformer (DiT) models, particularly for video generation, attention latency is a major bottleneck due to the long sequence length and the quadratic complexity. We f…
DiffusionNFT: Online Diffusion Reinforcement with Forward Process
Kaiwen Zheng, Huayu Chen, Haotian Ye +7
Online reinforcement learning (RL) has been central to post-training language models, but its extension to diffusion models remains challenging due to intractable likelihoods. Rece…
VISTAR:A User-Centric and Role-Driven Benchmark for Text-to-Image Evaluation
Kaiyuan Jiang, Ruoxi Sun, Ying Cao +4
We present VISTAR, a user-centric, multi-dimensional benchmark for text-to-image (T2I) evaluation that addresses the limitations of existing metrics. VISTAR introduces a two-tier h…
SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training
Jintao Zhang, Jia Wei, Pengle Zhang +6
The efficiency of attention is important due to its quadratic time complexity. We enhance the efficiency of attention through two key contributions: First, we leverage the new FP4…
Visual Generation Without Guidance
Huayu Chen, Kai Jiang, Kaiwen Zheng +3
Classifier-Free Guidance (CFG) has been a default technique in various visual generative models, yet it requires inference from both conditional and unconditional models during sam…