A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
AudioLCM introduces a latent consistency model for efficient text-to-audio generation, enabling high-quality synthesis in few sampling steps.
Akshaj Gupta, Hwi Joo Park, Andrea Guzman, et al.
TART is a modular four-stage pipeline that transcribes guitar audio into tablature with string-fret assignments and expressive technique annotations, achieving state-of-the-art zero-shot results.
Andrey Shutkin, Denis Parkhomenko, Ivan Kirillov, et al.
KVAE introduces a family of tokenizers for audio, image, and video that match or surpass frontier open-source tokenizers in reconstruction and generation quality.
Jinsen Su, Yongdong Luo, Yuexiao Ma, et al.
OmniScope is a training-free token compression framework for omnimodal LLMs that decouples audio and video relevance estimation using the query as a shared anchor, achieving up to 3.53x prefill speedup with minimal accuracy loss.
L. McCowan, Daniel Gática-Pérez, Samy Bengio, et al.
This paper proposes HMM-based models that capture interactions between participants from audiovisual features to recognize group actions in meetings.
Unknown
GPT-4o is an omni model that accepts and generates text, audio, images, and video.
Unknown
Gemini 1.5 Pro is a compute-efficient multimodal mixture-of-experts model excelling in long-context retrieval and understanding across text, video, and audio.
Jiayang Wu, Wensheng Gan, Zefeng Chen, et al.
A comprehensive survey of multimodal large language models integrating text, image, audio, and other data types.
Yi Luo, Nima Mesgarani
Conv-TasNet is a fully-convolutional time-domain audio separation network that outperforms ideal time-frequency magnitude masks for speech separation.