Searcharxiv⌕ Search

arXiv subjects

Eli Shlizerman

Publications and source records attributed to Eli Shlizerman.

At least 37 records · Page 2Linked to original sources
arXiv2025

Tell What You Hear From What You See -- Video to Audio Generation Through Text

The content of visual and audio scenes is multi-faceted such that a video can be paired with various audio and vice-versa. Thereby, in video-to-audio generation task, it is imperative to introduce steering approaches for controlling the generated audio. While Video-to-Audio generation is a well-established generative task, existing methods lack such controllability. In this work, we propose VATT, a multi-modal generative framework that takes a video and an optional text prompt as input, and generates audio and optional textual description of the audio. Such a framework has two advantages: i) Video-to-Audio generation process can be refined and controlled via text which complements the context of visual information, and ii) The model can suggest what audio to generate for the video by generating audio captions. VATT consists of two key modules: VATT Converter, a LLM that is fine-tuned for instructions and includes a projection layer that maps video features to the LLM vector space; and VATT Audio, a transformer that generates audio tokens from visual frames and from optional text prompt using iterative parallel decoding. The audio tokens are converted to a waveform by pretrained neural codec. Experiments show that when VATT is compared to existing video-to-audio generation methods in objective metrics, it achieves competitive performance when the audio caption is not provided. When the audio caption is provided as a prompt, VATT achieves even more refined performance (lowest KLD score of 1.41). Furthermore, subjective studies show that VATT Audio has been chosen as preferred generated audio than audio generated by existing methods. VATT enables controllable video-to-audio generation through text as well as suggesting text prompts for videos through audio captions, unlocking novel applications such as text-guided video-to-audio generation and video-to-audio captioning.

cs.CV↗
arXiv2024

Brain-to-Text Benchmark '24: Lessons Learned

Speech brain-computer interfaces aim to decipher what a person is trying to say from neural activity alone, restoring communication to people with paralysis who have lost the ability to speak intelligibly. The Brain-to-Text Benchmark '24 and associated competition was created to foster the advancement of decoding algorithms that convert neural activity to text. Here, we summarize the lessons learned from the competition ending on June 1, 2024 (the top 4 entrants also presented their experiences in a recorded webinar). The largest improvements in accuracy were achieved using an ensembling approach, where the output of multiple independent decoders was merged using a fine-tuned large language model (an approach used by all 3 top entrants). Performance gains were also found by improving how the baseline recurrent neural network (RNN) model was trained, including by optimizing learning rate scheduling and by using a diphone training objective. Improving upon the model architecture itself proved more difficult, however, with attempts to use deep state space models or transformers not yet appearing to offer a benefit over the RNN baseline. The benchmark will remain open indefinitely to support further work towards increasing the accuracy of brain-to-text algorithms.

cs.CL↗
arXiv2024

Brain-to-Text Decoding with Context-Aware Neural Representations and Large Language Models

Decoding attempted speech from neural activity offers a promising avenue for restoring communication abilities in individuals with speech impairments. Previous studies have focused on mapping neural activity to text using phonemes as the intermediate target. While successful, decoding neural activity directly to phonemes ignores the context dependent nature of the neural activity-to-phoneme mapping in the brain, leading to suboptimal decoding performance. In this work, we propose the use of diphone - an acoustic representation that captures the transitions between two phonemes - as the context-aware modeling target. We integrate diphones into existing phoneme decoding frameworks through a novel divide-and-conquer strategy in which we model the phoneme distribution by marginalizing over the diphone distribution. Our approach effectively leverages the enhanced context-aware representation of diphones while preserving the manageable class size of phonemes, a key factor in simplifying the subsequent phoneme-to-text conversion task. We demonstrate the effectiveness of our approach on the Brain-to-Text 2024 benchmark, where it achieves state-of-the-art Phoneme Error Rate (PER) of 15.34% compared to 16.62% PER of monophone-based decoding. When coupled with finetuned Large Language Models (LLMs), our method yields a Word Error Rate (WER) of 5.77%, significantly outperforming the 8.93% WER of the leading method in the benchmark.

eess.SP↗
arXiv2024

Transferable polychromatic optical encoder for neural networks

Artificial neural networks (ANNs) have fundamentally transformed the field of computer vision, providing unprecedented performance. However, these ANNs for image processing demand substantial computational resources, often hindering real-time operation. In this paper, we demonstrate an optical encoder that can perform convolution simultaneously in three color channels during the image capture, effectively implementing several initial convolutional layers of a ANN. Such an optical encoding results in ~24,000 times reduction in computational operations, with a state-of-the art classification accuracy (~73.2%) in free-space optical system. In addition, our analog optical encoder, trained for CIFAR-10 data, can be transferred to the ImageNet subset, High-10, without any modifications, and still exhibits moderate accuracy. Our results evidence the potential of hybrid optical/digital computer vision system in which the optical frontend can pre-process an ambient scene to reduce the energy and latency of the whole computer vision system.

cs.CV↗
arXiv2024

From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation

Video encompasses both visual and auditory data, creating a perceptually rich experience where these two modalities complement each other. As such, videos are a valuable type of media for the investigation of the interplay between audio and visual elements. Previous studies of audio-visual modalities primarily focused on either audio-visual representation learning or generative modeling of a modality conditioned on the other, creating a disconnect between these two branches. A unified framework that learns representation and generates modalities has not been developed yet. In this work, we introduce a novel framework called Vision to Audio and Beyond (VAB) to bridge the gap between audio-visual representation learning and vision-to-audio generation. The key approach of VAB is that rather than working with raw video frames and audio data, VAB performs representation learning and generative modeling within latent spaces. In particular, VAB uses a pre-trained audio tokenizer and an image encoder to obtain audio tokens and visual features, respectively. It then performs the pre-training task of visual-conditioned masked audio token prediction. This training strategy enables the model to engage in contextual learning and simultaneous video-to-audio generation. After the pre-training phase, VAB employs the iterative-decoding approach to rapidly generate audio tokens conditioned on visual features. Since VAB is a unified model, its backbone can be fine-tuned for various audio-visual downstream tasks. Our experiments showcase the efficiency of VAB in producing high-quality audio from video, and its capability to acquire semantic audio-visual features, leading to competitive results in audio-visual retrieval and classification.

cs.MM↗
arXiv2024

The time is ripe to reverse engineer an entire nervous system: simulating behavior from neural interactions

Just like electrical engineers understand how microprocessors execute programs in terms of how transistor currents are affected by their inputs, neuroscientists want to understand behavior production in terms of how neuronal outputs are affected by their inputs and internal states. This dependency of neuronal outputs on inputs can be described by a state-dependent input-output (IO)-function. However, to reliably identify these IO-functions, we need to perturb each input and combinations of inputs while observing all the outputs. Here, we argue that such completeness is possible in C. elegans; a complete description that goes all the way from the activity of every neuron to predict behavior. The established and growing toolkit of optophysiology can non-invasively capture and control every neuron's activity and scale to countless experiments. The information from many such experiments can be pooled while capturing the inter-individual variability because neuronal identity and function are largely conserved across individuals. Just like electrical engineers use transistor IO-functions to simulate program execution, we argue that neuronal IO-functions could be used to simulate the impressive breadth of brain states and behaviors of C. elegans.

q-bio.NC↗
arXiv2024

Calo-VQ: Vector-Quantized Two-Stage Generative Model in Calorimeter Simulation

We introduce a novel machine learning method developed for the fast simulation of calorimeter detector response, adapting vector-quantized variational autoencoder (VQ-VAE). Our model adopts a two-stage generation strategy: initially compressing geometry-aware calorimeter data into a discrete latent space, followed by the application of a sequence model to learn and generate the latent tokens. Extensive experimentation on the Calo-challenge dataset underscores the efficiency of our approach, showcasing a remarkable improvement in the generation speed compared with conventional method by a factor of 2000. Remarkably, our model achieves the generation of calorimeter showers within milliseconds. Furthermore, comprehensive quantitative evaluations across various metrics are performed to validate physics performance of generation.

physics.ins-det↗
arXiv2024

Compressed Meta-Optical Encoder for Image Classification

Optical and hybrid convolutional neural networks (CNNs) recently have become of increasing interest to achieve low-latency, low-power image classification and computer vision tasks. However, implementing optical nonlinearity is challenging, and omitting the nonlinear layers in a standard CNN comes at a significant reduction in accuracy. In this work, we use knowledge distillation to compress modified AlexNet to a single linear convolutional layer and an electronic backend (two fully connected layers). We obtain comparable performance to a purely electronic CNN with five convolutional layers and three fully connected layers. We implement the convolution optically via engineering the point spread function of an inverse-designed meta-optic. Using this hybrid approach, we estimate a reduction in multiply-accumulate operations from 17M in a conventional electronic modified AlexNet to only 86K in the hybrid compressed network enabled by the optical frontend. This constitutes over two orders of magnitude reduction in latency and power consumption. Furthermore, we experimentally demonstrate that the classification accuracy of the system exceeds 93% on the MNIST dataset.

cs.CV↗
arXiv2023

Lyapunov-Guided Representation of Recurrent Neural Network Performance

Recurrent Neural Networks (RNN) are ubiquitous computing systems for sequences and multivariate time series data. While several robust architectures of RNN are known, it is unclear how to relate RNN initialization, architecture, and other hyperparameters with accuracy for a given task. In this work, we propose to treat RNN as dynamical systems and to correlate hyperparameters with accuracy through Lyapunov spectral analysis, a methodology specifically designed for nonlinear dynamical systems. To address the fact that RNN features go beyond the existing Lyapunov spectral analysis, we propose to infer relevant features from the Lyapunov spectrum with an Autoencoder and an embedding of its latent representation (AeLLE). Our studies of various RNN architectures show that AeLLE successfully correlates RNN Lyapunov spectrum with accuracy. Furthermore, the latent representation learned by AeLLE is generalizable to novel inputs from the same task and is formed early in the process of RNN training. The latter property allows for the prediction of the accuracy to which RNN would converge when training is complete. We conclude that representation of RNN through Lyapunov spectrum along with AeLLE provides a novel method for organization and interpretation of variants of RNN architectures.

cs.LG↗
arXiv2023

Evolutionary algorithms as an alternative to backpropagation for supervised training of Biophysical Neural Networks and Neural ODEs

Training networks consisting of biophysically accurate neuron models could allow for new insights into how brain circuits can organize and solve tasks. We begin by analyzing the extent to which the central algorithm for neural network learning -- stochastic gradient descent through backpropagation (BP) -- can be used to train such networks. We find that properties of biophysically based neural network models needed for accurate modelling such as stiffness, high nonlinearity and long evaluation timeframes relative to spike times makes BP unstable and divergent in a variety of cases. To address these instabilities and inspired by recent work, we investigate the use of "gradient-estimating" evolutionary algorithms (EAs) for training biophysically based neural networks. We find that EAs have several advantages making them desirable over direct BP, including being forward-pass only, robust to noisy and rigid losses, allowing for discrete loss formulations, and potentially facilitating a more global exploration of parameters. We apply our method to train a recurrent network of Morris-Lecar neuron models on a stimulus integration and working memory task, and show how it can succeed in cases where direct BP is inapplicable. To expand on the viability of EAs in general, we apply them to a general neural ODE problem and a stiff neural ODE benchmark and find again that EAs can out-perform direct BP here, especially for the over-parameterized regime. Our findings suggest that biophysical neurons could provide useful benchmarks for testing the limits of BP-adjacent methods, and demonstrate the viability of EAs for training networks with complex components.

q-bio.NC↗
arXiv2023

Learning Time-Invariant Representations for Individual Neurons from Population Dynamics

Neurons can display highly variable dynamics. While such variability presumably supports the wide range of behaviors generated by the organism, their gene expressions are relatively stable in the adult brain. This suggests that neuronal activity is a combination of its time-invariant identity and the inputs the neuron receives from the rest of the circuit. Here, we propose a self-supervised learning based method to assign time-invariant representations to individual neurons based on permutation-, and population size-invariant summary of population recordings. We fit dynamical models to neuronal activity to learn a representation by considering the activity of both the individual and the neighboring population. Our self-supervised approach and use of implicit representations enable robust inference against imperfections such as partial overlap of neurons across sessions, trial-to-trial variability, and limited availability of molecular (transcriptomic) labels for downstream supervised tasks. We demonstrate our method on a public multimodal dataset of mouse cortical neuronal activity and transcriptomic labels. We report > 35% improvement in predicting the transcriptomic subclass identity and > 20% improvement in predicting class identity with respect to the state-of-the-art.

q-bio.NC↗
arXiv2023

Physics-Driven Diffusion Models for Impact Sound Synthesis from Videos

Modeling sounds emitted from physical object interactions is critical for immersive perceptual experiences in real and virtual worlds. Traditional methods of impact sound synthesis use physics simulation to obtain a set of physics parameters that could represent and synthesize the sound. However, they require fine details of both the object geometries and impact locations, which are rarely available in the real world and can not be applied to synthesize impact sounds from common videos. On the other hand, existing video-driven deep learning-based approaches could only capture the weak correspondence between visual content and impact sounds since they lack of physics knowledge. In this work, we propose a physics-driven diffusion model that can synthesize high-fidelity impact sound for a silent video clip. In addition to the video content, we propose to use additional physics priors to guide the impact sound synthesis procedure. The physics priors include both physics parameters that are directly estimated from noisy real-world impact sound examples without sophisticated setup and learned residual parameters that interpret the sound environment via neural networks. We further implement a novel diffusion model with specific training and inference strategies to combine physics priors and visual information for impact sound synthesis. Experimental results show that our model outperforms several existing systems in generating realistic impact sounds. More importantly, the physics-based representations are fully interpretable and transparent, thus enabling us to perform sound editing flexibly.

cs.CV↗
arXiv2022

TKIL: Tangent Kernel Approach for Class Balanced Incremental Learning

When learning new tasks in a sequential manner, deep neural networks tend to forget tasks that they previously learned, a phenomenon called catastrophic forgetting. Class incremental learning methods aim to address this problem by keeping a memory of a few exemplars from previously learned tasks, and distilling knowledge from them. However, existing methods struggle to balance the performance across classes since they typically overfit the model to the latest task. In our work, we propose to address these challenges with the introduction of a novel methodology of Tangent Kernel for Incremental Learning (TKIL) that achieves class-balanced performance. The approach preserves the representations across classes and balances the accuracy for each class, and as such achieves better overall accuracy and variance. TKIL approach is based on Neural Tangent Kernel (NTK), which describes the convergence behavior of neural networks as a kernel function in the limit of infinite width. In TKIL, the gradients between feature layers are treated as the distance between the representations of these layers and can be defined as Gradients Tangent Kernel loss (GTK loss) such that it is minimized along with averaging weights. This allows TKIL to automatically identify the task and to quickly adapt to it during inference. Experiments on CIFAR-100 and ImageNet datasets with various incremental learning settings show that these strategies allow TKIL to outperform existing state-of-the-art methods.

cs.LG↗
arXiv2022

STNDT: Modeling Neural Population Activity with a Spatiotemporal Transformer

Modeling neural population dynamics underlying noisy single-trial spiking activities is essential for relating neural observation and behavior. A recent non-recurrent method - Neural Data Transformers (NDT) - has shown great success in capturing neural dynamics with low inference latency without an explicit dynamical model. However, NDT focuses on modeling the temporal evolution of the population activity while neglecting the rich covariation between individual neurons. In this paper we introduce SpatioTemporal Neural Data Transformer (STNDT), an NDT-based architecture that explicitly models responses of individual neurons in the population across time and space to uncover their underlying firing rates. In addition, we propose a contrastive learning loss that works in accordance with mask modeling objective to further improve the predictive performance. We show that our model achieves state-of-the-art performance on ensemble level in estimating neural activities across four neural datasets, demonstrating its capability to capture autonomous and non-autonomous dynamics spanning different cortical regions while being completely agnostic to the specific behaviors at hand. Furthermore, STNDT spatial attention mechanism reveals consistently important subsets of neurons that play a vital role in driving the response of the entire population, providing interpretability and key insights into how the population of neurons performs computation.

q-bio.NC↗
arXiv2022

Statistical Perspective on Functional and Causal Neural Connectomics: The Time-Aware PC Algorithm

The representation of the flow of information between neurons in the brain based on their activity is termed the causal functional connectome. Such representation incorporates the dynamic nature of neuronal activity and causal interactions between them. In contrast to connectome, the causal functional connectome is not directly observed and needs to be inferred from neural time series. A popular statistical framework for inferring causal connectivity from observations is the directed probabilistic graphical modeling. Its common formulation is not suitable for neural time series since was developed for variables with independent and identically distributed static samples. In this work, we propose to model and estimate the causal functional connectivity from neural time series using a novel approach that adapts directed probabilistic graphical modeling to the time series scenario. In particular, we develop the Time-Aware PC (TPC) algorithm for estimating the causal functional connectivity, which adapts the PC algorithm a state-of-the-art method for statistical causal inference. We show that the model outcome of TPC has the properties of reflecting causality of neural interactions such as being non-parametric, exhibits the directed Markov property in a time-series setting, and is predictive of the consequence of counterfactual interventions on the time series. We demonstrate the utility of the methodology to obtain the causal functional connectome for several datasets including simulations, benchmark datasets, and recent multi-array electro-physiological recordings from the mouse visual cortex.

q-bio.NC↗
arXiv2021

Statistical Perspective on Functional and Causal Neural Connectomics: A Comparative Study

Representation of brain network interactions is fundamental to the translation of neural structure to brain function. As such, methodologies for mapping neural interactions into structural models, i.e., inference of functional connectome from neural recordings, are key for the study of brain networks. While multiple approaches have been proposed for functional connectomics based on statistical associations between neural activity, association does not necessarily incorporate causation. Additional approaches have been proposed to incorporate aspects of causality to turn functional connectomes into causal functional connectomes, however, these methodologies typically focus on specific aspects of causality. This warrants a systematic statistical framework for causal functional connectomics that defines the foundations of common aspects of causality. Such a framework can assist in contrasting existing approaches and to guide development of further causal methodologies. In this work, we develop such a statistical guide. In particular, we consolidate the notions of associations and representations of neural interaction, i.e., types of neural connectomics, and then describe causal modeling in the statistics literature. We particularly focus on the introduction of directed Markov graphical models as a framework through which we define the Directed Markov Property -- an essential criterion for examining the causality of proposed functional connectomes. We demonstrate how based on these notions, a comparative study of several existing approaches for finding causal functional connectivity from neural activity can be conducted. We proceed by providing an outlook ahead regarding the additional properties that future approaches could include to thoroughly address causality.

q-bio.NC↗
arXiv2021

Knowledge Distillation Circumvents Nonlinearity for Optical Convolutional Neural Networks

In recent years, Convolutional Neural Networks (CNNs) have enabled ubiquitous image processing applications. As such, CNNs require fast runtime (forward propagation) to process high-resolution visual streams in real time. This is still a challenging task even with state-of-the-art graphics and tensor processing units. The bottleneck in computational efficiency primarily occurs in the convolutional layers. Performing operations in the Fourier domain is a promising way to accelerate forward propagation since it transforms convolutions into elementwise multiplications, which are considerably faster to compute for large kernels. Furthermore, such computation could be implemented using an optical 4f system with orders of magnitude faster operation. However, a major challenge in using this spectral approach, as well as in an optical implementation of CNNs, is the inclusion of a nonlinearity between each convolutional layer, without which CNN performance drops dramatically. Here, we propose a Spectral CNN Linear Counterpart (SCLC) network architecture and develop a Knowledge Distillation (KD) approach to circumvent the need for a nonlinearity and successfully train such networks. While the KD approach is known in machine learning as an effective process for network pruning, we adapt the approach to transfer the knowledge from a nonlinear network (teacher) to a linear counterpart (student). We show that the KD approach can achieve performance that easily surpasses the standard linear version of a CNN and could approach the performance of the nonlinear network. Our simulations show that the possibility of increasing the resolution of the input image allows our proposed 4f optical linear network to perform more efficiently than a nonlinear network with the same accuracy on two fundamental image processing tasks: (i) object classification and (ii) semantic segmentation.

cs.CV↗
arXiv2020

Sparse Semi-Supervised Action Recognition with Active Learning

Current state-of-the-art methods for skeleton-based action recognition are supervised and rely on labels. The reliance is limiting the performance due to the challenges involved in annotation and mislabeled data. Unsupervised methods have been introduced, however, they organize sequences into clusters and still require labels to associate clusters with actions. In this paper, we propose a novel approach for skeleton-based action recognition, called SESAR, that connects these approaches. SESAR leverages the information from both unlabeled data and a handful of sequences actively selected for labeling, combining unsupervised training with sparsely supervised guidance. SESAR is composed of two main components, where the first component learns a latent representation for unlabeled action sequences through an Encoder-Decoder RNN which reconstructs the sequences, and the second component performs active learning to select sequences to be labeled based on cluster and classification uncertainty. When the two components are simultaneously trained on skeleton-based action sequences, they correspond to a robust system for action recognition with only a handful of labeled samples. We evaluate our system on common datasets with multiple sequences and actions, such as NW UCLA, NTU RGB+D 60, and UWA3D. Our results outperform standalone skeleton-based supervised, unsupervised with cluster identification, and active-learning methods for action recognition when applied to sparse labeled samples, as low as 1% of the data.

cs.CV↗