This paper addresses the issue of stiffness in the upper body and lack of coordination between the upper and lower body during humanoid robot walking. An improved humanoid robot reinforcement learning algorithm incorporating an LSTM framework is proposed to optimize full-body coordinated movement. Based on the Humanoid-Gym framework, a novel reward mechanism is designed, taking into account the detailed evaluation of arm movement and the collaborative control between the arms and thighs. The reinforcement learning model adopts an Actor-Critic architecture, integrating the LSTM framework into the network to enhance the feature extraction and dynamic modeling capabilities. Finally, experiments were conducted using the Hi ROBOT humanoid platform to validate the proposed model. The proposed LSTM network algorithm is compared with the original network, GRU, CNN, and other networks, demonstrating the superiority of the model. Compared with other networks, the performance improves by approximately $3.4 \%$ in terms of reward metric, and the model reaches the performance level of the original network after 40k training steps, as opposed to 60 k steps. It also maintains a fast convergence rate. Additionally, the optimized algorithm results in better gait arm swing and leg coordination, with smoother and more coordinated movement, closest to the human walking pattern.

We present Synthio, a novel approach for augmenting small-scale audio classification datasets with synthetic data. Our goal is to improve audio classification accuracy with limited labeled data. Traditional data augmentation techniques, which apply artificial transformations (e.g., adding random noise or masking segments), struggle to create data that captures the true diversity present in real-world audios. To address this shortcoming, we propose to augment the dataset with synthetic audio generated from text-to-audio (T2A) diffusion models. However, synthesizing effective augmentations is challenging because not only should the generated data be acoustically consistent with the underlying small-scale dataset, but they should also have sufficient compositional diversity. To overcome the first challenge, we align the generations of the T2A model with the small-scale dataset using preference optimization. This ensures that the acoustic characteristics of the generated data remain consistent with the small-scale dataset. To address the second challenge, we propose a novel caption generation technique that leverages the reasoning capabilities of Large Language Models to (1) generate diverse and meaningful audio captions and (2) iteratively refine their quality. The generated captions are then used to prompt the aligned T2A model. We extensively evaluate Synthio on ten datasets and four simulated limited-data settings. Results indicate our method consistently outperforms all baselines by 0.1%-39% using a T2A model trained only on weakly-captioned AudioSet.

Fugatto is a versatile audio synthesis and transformation model capable of following free-form text instructions with optional audio inputs. While large language models (LLMs) trained with text on a simple next-token prediction objective can learn to infer instructions directly from the data, models trained solely on audio data lack this capacity. This is because audio data does not inherently contain the instructions that were used to generate it. To overcome this challenge, we introduce a specialized dataset generation approach optimized for producing a wide range of audio generation and transformation tasks, ensuring the data reveals meaningful relationships between audio and language. Another challenge lies in achieving compositional abilities -- such as combining, interpolating between, or negating instructions -- using data alone. To address it, we propose ComposableART, an inference-time technique that extends classifier-free guidance to compositional guidance. It enables the seamless and flexible composition of instructions, leading to highly customizable audio outputs outside the training distribution. Our evaluations across a diverse set of tasks demonstrate that Fugatto performs competitively with specialized models, while ComposableART enhances its sonic palette and control over synthesis. Most notably, we highlight our framework's ability to execute emergent sounds and tasks -- sonic phenomena that transcend conventional audio generation -- unlocking new creative possibilities. \href{https://fugatto.github.io/}{Demo Website.}

Understanding and reasoning over non-speech sounds and music are crucial for both humans and AI agents to interact effectively with their environments. In this paper, we introduce Audio Flamingo 2 (AF2), an Audio-Language Model (ALM) with advanced audio understanding and reasoning capabilities. AF2 leverages (i) a custom CLAP model, (ii) synthetic Audio QA data for fine-grained audio reasoning, and (iii) a multi-stage curriculum learning strategy. AF2 achieves state-of-the-art performance with only a 3B parameter small language model, surpassing large open-source and proprietary models across over 20 benchmarks. Next, for the first time, we extend audio understanding to long audio segments (30 secs to 5 mins) and propose LongAudio, a large and novel dataset for training ALMs on long audio captioning and question-answering tasks. Fine-tuning AF2 on LongAudio leads to exceptional performance on our proposed LongAudioBench, an expert-annotated benchmark for evaluating ALMs on long audio understanding capabilities. We conduct extensive ablation studies to confirm the efficacy of our approach.

Recent years have seen significant progress in Text-To-Audio (TTA) synthesis, enabling users to enrich their creative workflows with synthetic audio generated from natural language prompts. Despite this progress, the effects of data, model architecture, training objective functions, and sampling strategies on target benchmarks are not well understood. With the purpose of providing a holistic understanding of the design space of TTA models, we set up a large-scale empirical experiment focused on diffusion and flow matching models. Our contributions include: 1) AF-Synthetic, a large dataset of high quality synthetic captions obtained from an audio understanding model; 2) a systematic comparison of different architectural, training, and inference design choices for TTA models; 3) an analysis of sampling methods and their Pareto curves with respect to generation quality and inference speed. We leverage the knowledge obtained from this extensive analysis to propose our best model dubbed Elucidated Text-To-Audio (ETTA). When evaluated on AudioCaps and MusicCaps, ETTA provides improvements over the baselines trained on publicly available data, while being competitive with models trained on proprietary data. Finally, we show ETTA’s improved ability to generate creative audio following complex and imaginative captions – a task that is more challenging than current benchmarks.

We present Audio Flamingo 3 (AF3), a fully open state-of-the-art (SOTA) large audio-language model that advances reasoning and understanding across speech, sound, and music. AF3 introduces: (i) AF-Whisper, a unified audio encoder trained using a novel strategy for joint representation learning across all 3 modalities of speech, sound, and music; (ii) flexible, on-demand thinking, allowing the model to do chain-of-thought-type reasoning before answering; (iii) multi-turn, multi-audio chat; (iv) long audio understanding and reasoning (including speech) up to 10 minutes; and (v) voice-to-voice interaction. To enable these capabilities, we propose several large-scale training datasets curated using novel strategies, including AudioSkills-XL, LongAudio-XL, AF-Think, and AF-Chat, and train AF3 with a novel five-stage curriculum-based training strategy. Trained on only open-source audio data, AF3 achieves new SOTA results on over 20+ (long) audio understanding and reasoning benchmarks, surpassing both open-weight and closed-source models trained on much larger datasets.

Augmenting large language models (LLMs) to understand audio – including non-speech sounds and non-verbal speech – is critically important for diverse real-world applications of LLMs. In this paper, we propose Audio Flamingo, a novel audio language model with 1) strong audio understanding abilities, 2) the ability to quickly adapt to unseen tasks via in-context learning and retrieval, and 3) strong multi-turn dialogue abilities. We introduce a series of training techniques, architecture design, and data strategies to enhance our model with these abilities. Extensive evaluations across various audio understanding tasks confirm the efficacy of our method, setting new state-of-the-art benchmarks. Our demo website is https://audioflamingo.github.io/ and the code is open-sourced at https://github.com/NVIDIA/audio-flamingo.

Users have the right to have their data deleted by third-party learned systems, as codified by recent legislation such as the General Data Protection Regulation (GDPR) and the California Consumer Privacy Act (CCPA). Such data deletion can be achieved by full re-training, but this incurs a high computational cost for modern machine learning methods. To avoid this cost, many approximate deletion methods have been developed for supervised learning. Unsupervised learning, in contrast, remains largely an open problem when it comes to efficient approximate data deletion. In this paper, we introduce (1) an efficient method for approximate deletion in generative models, and (2) statistical tests for estimating whether training points have been deleted. We provide theoretical guarantees under various learner assumptions. We then empirically demonstrate our methods across a variety of generative methods.

In this work, we present CleanUNet 2, a speech denoising model that combines the advantages of waveform denoiser and spectrogram denoiser and achieves the best of both worlds. CleanUNet 2 uses a two-stage framework inspired by popular speech synthesis methods that consist of a waveform model and a spectrogram model. Specifically, CleanUNet 2 builds upon CleanUNet, the state-of-the-art waveform denoiser, and further boosts its performance by taking predicted spectrograms from a spectrogram denoiser as the input. We demonstrate that CleanUNet 2 outperforms previous methods in terms of various objective and subjective evaluations.

In this work, we present CleanUNet, a causal speech denoising model on the raw waveform. The proposed model is based on an encoder-decoder architecture combined with several self-attention blocks to refine its bottleneck representations, which is crucial to obtain good results. The model is optimized through a set of losses defined over both waveform and multi-resolution spectrograms. The proposed method outperforms the state-of-the-art models in terms of denoised speech quality from various objective and subjective evaluation metrics.1

Instance-based interpretation methods have been widely studied for supervised learning methods as they help explain how black box neural networks predict. However, instance-based interpretations remain ill-understood in the context of unsupervised learning. In this paper, we investigate influence functions [Koh and Liang, 2017], a popular instance-based interpretation method, for a class of deep generative models called variational auto-encoders (VAE). We formally frame the counter-factual question answered by influence functions in this setting, and through theoretical analysis, examine what they reveal about the impact of training samples on classical unsupervised learning methods. We then introduce VAE- TracIn, a computationally efficient and theoretically sound solution based on Pruthi et al. [2020], for VAEs. Finally, we evaluate VAE-TracIn on several real world datasets with extensive quantitative and qualitative analysis.

The rapid growth of deep learning applications in real life is accompanied by severe safety concerns. To mitigate this uneasy phenomenon, much research has been done providing reliable evaluations of the fragility level in different deep neural networks. Apart from devising adversarial attacks, quantifiers that certify safeguarded regions have also been designed in the past five years. The summarizing work in (Salman et al. 2019) unifies a family of existing verifiers under a convex relaxation framework. We draw inspiration from such work and further demonstrate the optimality of deterministic CROWN (Zhang et al. 2018) solutions in a given linear programming problem under mild constraints. Given this theoretical result, the computationally expensive linear programming based method is shown to be unnecessary. We then propose an optimization-based approach FROWN (Fastened CROWN): a general algorithm to tighten robustness certificates for neural networks. Extensive experiments on various networks trained individually verify the effectiveness of FROWN in safeguarding larger robust regions.

Normalizing flows have received a great deal of recent attention as they allow flexible generative modeling as well as easy likelihood computation. While a wide variety of flow models have been proposed, there is little formal understanding of the representation power of these models. In this work, we study some basic normalizing flows and rigorously establish bounds on their expressive power. Our results indicate that while these flows are highly expressive in one dimension, in higher dimensions their representation power may be limited, especially when the flows have moderate depth.

The capacity to model temporal dependency by Recurrent Neural Networks (RNNs) makes it a plausible selection for the multi-object tracking (MOT) problem. Due to the nonlinear transformations and the unique memory mechanism, Long Short-Term Memory (LSTM) can consider a window of history when learning discriminative features, which suggests that the LSTM is suitable for state estimation of target objects as they move around. This paper focuses on association based MOT, and we propose a novel Siamese LSTM Network to interpret both temporal and spatial components nonlinearly by learning the feature of trajectories, and outputs the similarity score of two trajectories for data association. In addition, we also introduce an online metric learning scheme to update the state estimation of each trajectory dynamically. Experimental evaluation on MOT16 benchmark shows that the proposed method achieves competitive performance compared with other state-of-the-art works.