The concept of sharpness has been successfully applied to traditional architectures like MLPs and CNNs to predict their generalization. For transformers, however, recent work reported weak correlation between flatness and generalization. We argue that existing sharpness measures fail for transformers, because they have much richer symmetries in their attention mechanism that induce directions in parameter space along which the network or its loss remain identical. We posit that sharpness must account fully for these symmetries, and thus we redefine it on a quotient manifold that results from quotienting out the transformer symmetries, thereby removing their ambiguities. Leveraging tools from Riemannian geometry, we propose a fully general notion of sharpness, in terms of a geodesic ball on the symmetry-corrected quotient manifold. In practice, we need to resort to approximating the geodesics. Doing so up to first order yields existing adaptive sharpness measures, and we demonstrate that including higher-order terms is crucial to recover correlation with generalization. We present results on diagonal networks with synthetic data, and show that our geodesic sharpness reveals strong correlation for real-world transformers on both text and image classification tasks.

We study the problem of symbolic music generation (e.g., generating piano rolls), with a technical focus on non-differentiable rule guidance. Musical rules are often expressed in symbolic form on note characteristics, such as note density or chord progression, many of which are non-differentiable which pose a challenge when using them for guided diffusion. We propose Stochastic Control Guidance (SCG), a novel guidance method that only requires forward evaluation of rule functions that can work with pre-trained diffusion models in a plug-and-play way, thus achieving training-free guidance for non-differentiable rules for the first time. Additionally, we introduce a latent diffusion architecture for symbolic music generation with high time resolution, which can be composed with SCG in a plug-and-play fashion. Compared to standard strong baselines in symbolic music generation, this framework demonstrates marked advancements in music quality and rule-based controllability, outperforming current state-of-the-art generators in a variety of settings. For detailed demonstrations, code and model checkpoints, please visit our [project website](https://scg-rule-guided-music.github.io/).

Synthesizers are powerful tools that allow musicians to create dynamic and original sounds. Existing commercial interfaces for synthesizers typically require musicians to interact with complex low-level parameters or to manage large libraries of premade sounds. To address these challenges, we implement SynthScribe — a fullstack system that uses multimodal deep learning to let users express their intentions at a much higher level. We implement features which address a number of difficulties, namely 1) searching through existing sounds, 2) creating completely new sounds, and 3) making meaningful modifications to a given sound. This is achieved with three main features: a multimodal search engine for a large library of synthesizer sounds; a user centered genetic algorithm by which completely new sounds can be created and selected given the users preferences; a sound editing support feature which highlights and gives examples for key control parameters with respect to a text or audio based query. The results of our user studies show SynthScribe is capable of reliably retrieving and modifying sounds while also affording the ability to create completely new sounds that expand a musicians creative horizon.

Despite their remarkable successes, state-of-the-art large language models (LLMs), including vision-and-language models (VLMs) and unimodal language models (ULMs), fail to understand precise semantics. For example, semantically equivalent sentences expressed using different lexical compositions elicit diverging representations. The degree of this divergence and its impact on encoded semantics is not very well understood. In this paper, we introduce the SUGARCREPE++ dataset to analyze the sensitivity of VLMs and ULMs to lexical and semantic alterations. Each sample in SUGARCREPE++ dataset consists of an image and a corresponding triplet of captions: a pair of semantically equivalent but lexically different positive captions and one hard negative caption. This poses a 3-way semantic (in)equivalence problem to the language models. We comprehensively evaluate VLMs and ULMs that differ in architecture, pre-training objectives and datasets to benchmark the performance of SUGARCREPE++ dataset. Experimental results highlight the difficulties of VLMs in distinguishing between lexical and semantic variations, particularly to object attributes and spatial relations. Although VLMs with larger pre-training datasets, model sizes, and multiple pre-training objectives achieve better performance on SUGARCREPE++, there is a significant opportunity for improvement. We demonstrate that models excelling on compositionality datasets may not perform equally well on SUGARCREPE++. This indicates that compositionality alone might not be sufficient to fully understand semantic and lexical alterations. Given the importance of the property that the SUGARCREPE++ dataset targets, it serves as a new challenge to the vision-and-language community. Data and code is available at https://github.com/Sri-Harsha/scpp.

We introduce DiffAug, a simple and efficient diffusion-based augmentation technique to train image classifiers for the crucial yet challenging goal of improved classifier robustness. Applying DiffAug to a given example consists of one forward-diffusion step followed by one reverse-diffusion step. Using both ResNet-50 and Vision Transformer architectures, we comprehensively evaluate classifiers trained with DiffAug and demonstrate the surprising effectiveness of single-step reverse diffusion in improving robustness to covariate shifts, certified adversarial accuracy and out of distribution detection. When we combine DiffAug with other augmentations such as AugMix and DeepAugment we demonstrate further improved robustness. Finally, building on this approach, we also improve classifier-guided diffusion wherein we observe improvements in: (i) classifier-generalization, (ii) gradient quality (i.e., improved perceptual alignment) and (iii) image generation performance. We thus introduce a computationally efficient technique for training with improved robustness that does not require any additional data, and effectively complements existing augmentation approaches.

Text-to-image generative models have demonstrated remarkable capabilities in generating high-quality images based on textual prompts. However, crafting prompts that accurately capture the user’s creative intent remains challenging. It often involves laborious trial-and-error procedures to ensure that the model interprets the prompts in alignment with the user’s intention. To address these challenges, we present Promptify, an interactive system that supports prompt exploration and refinement for text-to-image generative models. Promptify utilizes a suggestion engine powered by large language models to help users quickly explore and craft diverse prompts. Our interface allows users to organize the generated images flexibly, and based on their preferences, Promptify suggests potential changes to the original prompt. This feedback loop enables users to iteratively refine their prompts and enhance desired features while avoiding unwanted ones. Our user study shows that Promptify effectively facilitates the text-to-image workflow, allowing users to create visually appealing images on their first attempt while requiring significantly less cognitive load than a widely-used baseline tool.

The choice of activation functions and their motivation is a long-standing issue within the neural network community. Neuronal representations within artificial neural networks are commonly understood as logits, representing the log-odds score of presence of features within the stimulus. We derive logit-space operators equivalent to probabilistic Boolean logic-gates AND, OR, and XNOR for independent probabilities. Such theories are important to formalize more complex dendritic operations in real neurons, and these operations can be used as activation functions within a neural network, introducing probabilistic Boolean-logic as the core operation of the neural network. Since these functions involve taking multiple exponents and logarithms, they are computationally expensive and not well suited to be directly used within neural networks. Consequently, we construct efficient approximations named $\text{AND}_\text{AIL}$ (the AND operator Approximate for Independent Logits), $\text{OR}_\text{AIL}$, and $\text{XNOR}_\text{AIL}$, which utilize only comparison and addition operations, have well-behaved gradients, and can be deployed as activation functions in neural networks. Like MaxOut, $\text{AND}_\text{AIL}$ and $\text{OR}_\text{AIL}$ are generalizations of ReLU to two-dimensions. While our primary aim is to formalize dendritic computations within a logit-space probabilistic-Boolean framework, we deploy these new activation functions, both in isolation and in conjunction to demonstrate their effectiveness on a variety of tasks including tabular classification, image classification, transfer learning, abstract reasoning, and compositional zero-shot learning.

Major depressive disorder, referred to as depression, is a leading cause of disability, absence from work, and premature death. Automatic assessment of depression from speech is a critical step towards improving diagnosis and treatment of depression. Previous works on depression assessment from speech considered various acoustic features extracted from speech to estimate depression severity. But performance of these approaches is not at clinical standards, and thus requires further improvement. In this work, we examine two novel approaches for improving depression severity estimation from short audio recordings of speech. Specifically, in audio recordings of a narrative by individuals diagnosed with major depressive disorder, we analyze spectral-based and excitation source-based features extracted from speech, and significance of sentiment and emotion classification in estimation of depression severity. Initial results indicate synchrony between depression scores and the sentiment and emotion labels. We propose the use of sentiment and emotion based embeddings obtained using machine learning techniques in estimation of depression severity. We also propose use of multi-task training to better estimate depression severity. We show that the proposed approaches provide additive improvements in the estimation of depression severity.

When presented with Out-of-Distribution (OOD) examples, deep neural networks yield confident, incorrect predictions; detecting OOD examples is challenging, and the potential risks are high. In this paper, we propose to detect OOD examples by identifying inconsistencies between activity patterns and predicted class. We find that characterizing activity patterns by Gram matrices and identifying anomalies in Gram matrix values can yield high OOD detection rates. We identify anomalies in the Gram matrices by simply comparing each value with its respective range observed over the training data. Unlike many approaches, this can be used with any pre-trained softmax classifier and neither requires access to OOD data for fine-tuning hyperparameters, nor does it require OOD access for inferring parameters. We empirically demonstrate applicability across a variety of architectures and vision datasets and, for the important and surprisingly hard task of detecting far out-of-distribution examples, it generally performs better than or equal to state-of-the-art OOD detection methods (including those that do assume access to OOD examples).

Music generation has generally been focused on either creating scores or interpreting them. We discuss differences between these two problems and propose that, in fact, it may be valuable to work in the space of direct performance generation: jointly predicting the notes and also their expressive timing and dynamics. We consider the significance and qualities of the dataset needed for this. Having identified both a problem domain and characteristics of an appropriate dataset, we show an LSTM-based recurrent network model that subjectively performs quite well on this task. Critically, we provide generated examples. We also include feedback from professional composers and musicians about some of these examples.

Adding small, well crafted perturbations to the pixel values of input images leads to adversarial examples, so called because these perturbed images can drastically affect the accuracy of machine learning classifiers. Defenses against such attacks are being studied, often with varying results. In this study, we introduce a model called the Stochastic-Gated Partially Binarized Network (SGBN ), that incorporates binarization and input-dependent stochasticity. In particular, a gate module learns the probability that individual weights in corresponding convolutional filters should be masked (turned on or off). The gate module itself consists of a shallow convolutional neural network, and its sigmoid outputs are stochastically binarized and pointwise multiplied with corresponding filters in the convolutional layer of the main network. We test and compare our model with several related approaches, and to try to gain an understanding of our model, we visualize activations of some of the gating network outputs and their corresponding filters.

Computer dialogue systems are designed with the intention of supporting meaningful interactions with humans. Common modes of communication include speech, text, and physical gestures. In this work we explore a communication paradigm in which the input and output channels consist of music. Specifically, we examine the musical interaction scenario of call and response. We present a system that utilizes a deep autoencoder to learn semantic embeddings of musical input. The system learns to transform these embeddings in a manner such that reconstructing from these transformation vectors produces appropriate musical responses. In order to generate a response the system employs a combination of generation and unit selection. Selection is based on a nearest neighbor search within the embedding space and for real-time application the search space is pruned using vector quantization. The live demo consists of a person playing a midi keyboard and the computer generating a response that is played through a loudspeaker.

We present a novel interface for young children to interact with digital music. PlaceAndPlay provides an intuitive environment for children with no music creation experience. Multimodal interaction techniques and a unique approach to music layout accommodate physical and cognitive abilities of young children. The system was evaluated in user study settings at the different designing stages and the results were positive.

Our goal is to design and build a tool for the creation of expressive character animation. Virtual puppetry, also known as performance animation, is a technique in which the user interactively controls a character's motion. In this paper we introduce local physical models for performance animation and describe how they can augment an existing kinematic method to achieve very effective animation control. These models approximate specific physically-generated aspects of a character's motion. They automate certain behaviours, while still letting the user override such motion via a PD-controller if he so desires. Furthermore, they can be tuned to ignore certain undesirable effects, such as the risk of having a character fall over, by ignoring corresponding components of the force. Although local physical models are a quite simple approximation to real physical behaviour, we show that they are extremely useful for interactive character control, and contribute positively to the expressiveness of the character's motion. In this paper, we develop such models at the knees and ankles of an interactively-animated 3D anthropomorphic character, and demonstrate a resulting animation. This approach can be applied in a straight-forward way to other joints. Categories and Subject Descriptors (according to ACM CCS): I.3.7 [Computer Graphics]: Three-Dimensional Graphics and Realism, Interaction Techniques

We show how a neural network can be used to allow a mobile robot to derive an accurate estimate of its location from noisy sonar sensors and noisy motion information. The robot's model of its location is in the form of a probability distribution across a grid of possible locations. This distribution is updated using both the motion information and the predictions of a neural network that maps locations into likelihood distributions across possible sonar readings. By predicting sonar readings from locations, rather than vice versa, the robot can handle the very nongaussian noise in the sonar sensors. By using the constraint provided by the noisy motion information, the robot can use previous readings to improve its estimate of its current location. By treating the resulting estimates as if they were correct, the robot can learn the relationship between location and sonar readings without requiring an external supervision signal that specifies the actual location of the robot. It can learn to locate itself in a new environment with almost no supervision, and it can maintain its location ability even when the environment is nonstationary.