StepAudio 3 Realtime is an audio-language foundation model designed for real-time spoken interaction, featuring a continuous listen-converse-think-act loop. It includes Deep Perception for interpreting user intent, Seamless Duplex for handling audio stream synchronization, and Think-While-Speaking to balance reasoning and latency. The model achieves high performance on benchmarks like MMSU and Artificial Analysis Full-Duplex, along with a task-success rate on τ-Voice.
The chart will appear after repeat observations. The current metric comes from the source.
89 source votesReal observations only. History before source connection is not reconstructed.
This model is designed for real-time spoken interaction, making it suitable for applications requiring immediate responses and natural dialogue flow.
StepAudio 3 Music is a large-scale music generation model that uses explicit musical planning and text control. It employs a flow-matching diffusion Transformer to predict audio latents, with a discrete-continuous design and a Mixture-of-Experts autoregressive model for structured music generation.
5 days agoDaily PapersThe paper discusses recursive self-improvement (RSI) in AI systems, outlining its development roadmap from autonomy in improvement execution to recursive meta-improvement. It examines RSI across various scenarios like scientific discovery and software engineering, highlighting different requirements and development speeds.
6 days agoDaily PapersThe paper introduces Vidu S2, a system with two components: Vidu S2-Avatar for real-time interactive digital characters and Vidu S2-Editing for real-time video editing. It also explores real-time spatial video generation for both components. Compared to its predecessor, Vidu S2-Avatar offers improved real-time 720p video generation, dynamic reference updates, and enhanced instruction following. Vidu S2-Editing enables real-time video stream editing with features like style rendering and background replacement.
6 days agoDaily PapersPhysBrain 1.5 is a unified model for understanding physical environments, generating actions, and predicting future states. It uses a vision-language foundation, encodes language responses and motion as sequences, and is pre-trained on human interaction videos. The model achieves strong performance on embodied understanding benchmarks.
2 days agoDaily PapersLynnReal-Omni is a native multimodal video generation framework that combines text-to-video, image-conditioned generation, and structural control into a single model. It includes a 32B shared multimodal diffusion transformer and a 27B Flash version for real-time rendering, with a data pipeline and evaluation method designed for video generation tasks.
2 days agoDaily PapersZGCM-1 is a 7B parameter foundation model designed for math and agentic search, emphasizing efficiency through architectural and system co-design, progressive curriculum learning, and an AI-native R&D workflow. It demonstrates competitive performance against larger models on mathematical and search tasks, with improvements in training efficiency and open-source availability of training materials.
5 days ago