arXiv subjects

Gleb Balitskiy

Publications and source records attributed to Gleb Balitskiy.

3 recordsLinked to original sources

arXiv2026

AVTR-1: Open Stack for Real-Time Interactive Avatars

Talking-head and dyadic models now achieve real-time inference, yet fast motion generation alone does not produce an interactive conversation. A live system must synchronize the model's output with speech from an external voice agent, schedule video frames for playback, and handle interruptions. We introduce AVTR-1, an open stack for real-time interactive avatar conversations, built around a compact 153M-parameter autoregressive flow-matching motion generator conditioned on both participants' audio. We adapt its audio encoder for streaming through self-distillation. The stack turns the model's chunk-based generation into a continuous, synchronized audio-video stream driven by an external voice agent, and we analytically derive its contribution to the user-facing latencies and validate the resulting bounds with two commercial voice agents. Further experiments demonstrate that AVTR-1 leads the compared dyadic systems on all reported visual-quality metrics and most conventional listening-motion metrics while remaining competitive in lip synchronization. Its inference runtime operates in real time on data-center and consumer GPUs. However, conventional listening metrics do not establish whether the paired speaker's speech contributes to generated motion. We therefore introduce the Reference-Based Directed Granger Gain (R-DGG), which measures the additional predictive information carried by speaker speech after accounting for listener history and speaker motion. R-DGG finds statistically supported predictive dependence for recorded listeners and all evaluated dyadic systems, but not for talking-head generators without paired audio or mismatched speaker-listener pairs. We release the model weights, renderer, and serving backend under component-specific licenses.

cs.CV↗

arXiv2023

Federated Privacy-preserving Collaborative Filtering for On-Device Next App Prediction

In this study, we propose a novel SeqMF model to solve the problem of predicting the next app launch during mobile device usage. Although this problem can be represented as a classical collaborative filtering problem, it requires proper modification since the data are sequential, the user feedback is distributed among devices and the transmission of users' data to aggregate common patterns must be protected against leakage. According to such requirements, we modify the structure of the classical matrix factorization model and update the training procedure to sequential learning. Since the data about user experience are distributed among devices, the federated learning setup is used to train the proposed sequential matrix factorization model. One more ingredient of the proposed approach is a new privacy mechanism that guarantees the protection of the sent data from the users to the remote server. To demonstrate the efficiency of the proposed model we use publicly available mobile user behavior data. We compare our model with sequential rules and models based on the frequency of app launches. The comparison is conducted in static and dynamic environments. The static environment evaluates how our model processes sequential data compared to competitors. Therefore, the standard train-validation-test evaluation procedure is used. The dynamic environment emulates the real-world scenario, where users generate new data by running apps on devices, and evaluates our model in this case. Our experiments show that the proposed model provides comparable quality with other methods in the static environment. However, more importantly, our method achieves a better privacy-utility trade-off than competitors in the dynamic environment, which provides more accurate simulations of real-world usage.

cs.IR↗

arXiv2019

Design and Decoding of Polar Codes for the Gaussian Multiple Access Channel

Massive machine-type communications (mMTC) is one of the key application scenarios for future 5G networks. Non-orthogonal multiple access (NOMA) is a promising technique for the use in mMTC scenario. In this paper, we investigate NOMA schemes based on polar codes. We compare two possible decoding techniques: joint successive cancellation algorithm and joint iterative algorithm. In order to optimize the codes (choose frozen bits) we propose a special and efficient design algorithm. We investigate the performance of the resulting scheme in the Gaussian multiple access channel (GMAC) by means of simulations. The scheme is shown to outperform LDPC based solution by approximately 1 dB and to be close to the achievability bound for GMAC.

cs.IT↗