This paper proposes Supervised Memory Training (SMT), a method for training nonlinear RNNs that sidesteps recurrent credit propagation entirely.

This paper proposes a framework for creating low-latency, interactive generative music AI using distillation in a streaming autoregressive latent space and music-aware consistency objectives.

LongLive-RAG proposes a novel Retrieval-Augmented Generation (RAG) framework to stabilize and improve the quality of long-horizon video generation by treating the entire generated history as a searcha…

Chatterbox-Flash introduces a prior-calibrated block diffusion model for zero-shot TTS that achieves high-fidelity, streaming synthesis with significantly lower computational overhead than existing me…

This paper introduces GEAR, a method for training a vector-quantized tokenizer and an autoregressive generator jointly and end-to-end, resolving the issue of non-differentiable VQ indices.

SANA-Streaming introduces a novel, efficient framework that enables real-time, high-resolution streaming video-to-video editing by combining a hybrid diffusion transformer with specialized training an…

This paper introduces Flex-Forcing, a framework for video generation that enables a model to operate under both bidirectional and autoregressive generation regimes, achieving better video quality and…

ProactiveLLM introduces a novel framework that enables streaming LLMs to actively decide when to interact with incoming data by leveraging the model's internal states, significantly reducing latency w…

This paper proposes OPSD-V, an on-policy self-distillation method for reducing long-horizon degradation in few-step autoregressive video diffusion models by introducing real long-video data as tempora…

AdaKoop introduces an efficient streaming algorithm that models complex nonlinear dynamics from nonstationary data streams by leveraging the Koopman operator theory, achieving state-of-the-art accurac…

This paper proposes an online changepoint detection method for autoregressive processes of order p, improving detection power and computational efficiency for data with temporal correlation.

MORPHOS is a novel autoregressive framework that generates dynamic 3D assets (like meshes and radiance fields) from videos by using a unified 4D representation to ensure temporal consistency and handl…

The paper introduces NaRA, a noise-aware LoRA technique that dynamically adapts fine-tuning parameters based on the noise level during diffusion, significantly improving the performance of Diffusion L…

The paper argues that long context windows are necessary for time series forecasting not just to capture long-range dependencies, but primarily to reduce uncertainty about the underlying data-generati…

The paper introduces QuITE, a plug-and-play embedding module that uses learnable query tokens to effectively embed irregular multivariate time series data into latent representations compatible with e…

FLARE is a systematic conversion framework that enables a single checkpoint to support both autoregressive (AR) and diffusion-style parallel decoding for hybrid-attention large language models, achiev…

This paper proposes cumsum-composable phase transport, a streaming-native temporal layer for keyword spotting using unitary transport, prefix differences, and gated residual updates.

The paper introduces X-Stream, a new benchmark for multi-stream video understanding, and finds that current state-of-the-art MLLMs perform poorly when required to process multiple concurrent video str…

This paper introduces a training recipe for sentence-level and long-form streaming speech-to-speech translation using only 2k hours of paired cross-lingual data and auxiliary supervision.