SDAR is a new type of large language model that integrates autoregressive and discrete diffusion modeling strategies, combining the advantages of efficient training of AR models and parallel inference of diffusion models. It performs comparably to SOTA open - source AR models on general tasks and excels in scientific reasoning tasks, becoming the most powerful diffusion language model.

Natural Language ProcessingTransformers

PARD is a high-performance speculative decoding method that can convert autoregressive draft models into parallel draft models at low cost, significantly improving the inference speed of large language models and reducing deployment complexity and adaptation costs.

Natural Language ProcessingTransformers

SongBloom is an innovative full-length song generation framework that adopts an interleaved paradigm of autoregressive sketch drawing and diffusion-based refinement, combining the high fidelity of diffusion models and the scalability of language models to generate high-quality full-length songs.

PARD is a high-performance speculative decoding method that can convert autoregressive draft models into parallel draft models at low cost, significantly accelerating the inference of large language models.

Natural Language ProcessingTransformers

SkyReels V2 is the first open-source video generation model to adopt an autoregressive diffusion-forced architecture, supporting unlimited-length movie generation and achieving state-of-the-art performance among public models.

Computer VisionDiffusers

SkyReels V2 is an open-source video generation model that adopts an autoregressive diffusion forced architecture, supporting unlimited-length movie generation and achieving state-of-the-art performance among public models.

MultimodalSafetensors

SkyReels V2 is an unlimited-length cinematic generation model that adopts an autoregressive diffusion force architecture, supports 720P HD video generation, and achieves SOTA performance among public models.

Computer VisionSafetensors

SkyReels V2 is the first open-source video generation model adopting an autoregressive diffusion forced architecture, supporting unlimited-length movie generation, achieving state-of-the-art performance among public models.

Computer VisionSafetensors

SkyReels V2 is the first open-source video generation model adopting an autoregressive diffusion architecture, supporting unlimited-length movie generation, achieving state-of-the-art performance among public models.

Computer VisionSafetensors

BD3-LMs is a language model that combines the advantages of autoregressive and diffusion models, achieving efficient sequence generation through block discrete diffusion.

Natural Language ProcessingTransformers

BD3-LMs is a language model that combines the strengths of autoregressive and diffusion models, achieving efficient sequence generation through block discrete diffusion.

Natural Language ProcessingTransformers

BD3-LMs is a language model that combines the advantages of autoregressive and diffusion models, achieving efficient sequence generation through block discrete diffusion

Natural Language ProcessingTransformers

InspireMusic is a unified framework focused on music generation, song generation, and audio generation, combining audio tokenization with autoregressive transformers and flow-matching models to support high-quality long-form audio generation.

Audio ProcessingSafetensorsEnglish

InspireMusic is a unified framework focused on music generation, song generation, and audio generation, integrating autoregressive transformers with flow-matching models through audio tokenization technology, supporting high-quality long audio generation.

Audio ProcessingSafetensorsEnglish

AIMv2 is a series of vision models pretrained with multimodal autoregressive objectives, achieving outstanding performance in multiple multimodal understanding benchmarks.

Computer VisionJax

AIMv2 is a series of vision models pretrained with multimodal autoregressive objectives, demonstrating outstanding performance across multiple multimodal understanding benchmarks.

MultimodalJax

AIMv2 is a series of vision models based on multimodal autoregressive objective pretraining, excelling in multimodal understanding benchmarks

Computer VisionJax

JanusFlow is a powerful framework that unifies image understanding and generation in a single model, combining autoregressive language models with rectified flow methods.

MultimodalTransformers

AIMv2 is a series of vision models pretrained with multimodal autoregressive objectives, excelling in multimodal understanding benchmarks.

Computer VisionJax

AIMv2 is a series of vision models pretrained with multimodal autoregressive objectives, demonstrating excellent performance across multiple visual understanding benchmarks.

Computer VisionJax