Zhengdong Zhang

Qingqing Huang, Daniel S. Park, Tao Wang et al.

We introduce Noise2Music, where a series of diffusion models is trained to generate high-quality 30-second music clips from text prompts. Two types of diffusion models, a generator model, which generates an intermediate representation conditioned on text, and a cascader model, which generates high-fidelity audio conditioned on the intermediate representation and possibly the text, are trained and utilized in succession to generate high-fidelity music. We explore two options for the intermediate representation, one using a spectrogram and the other using audio with lower fidelity. We find that the generated audio is not only able to faithfully reflect key elements of the text prompt such as genre, tempo, instruments, mood, and era, but goes beyond to ground fine-grained semantics of the prompt. Pretrained large language models play a key role in this story -- they are used to generate paired text for the audio of the training set and to extract embeddings of the text prompts ingested by the diffusion models. Generated examples: https://google-research.github.io/noise2music

Zihan Dong, ZhengDong Zhang

Bloodstain pattern analysis plays a crucial role in crime scene investigations by providing valuable information through the study of unique blood patterns. Conventional image analysis methods, like Thresholding and Contrast, impose stringent requirements on the image background and is labor-intensive in the context of droplet image segmentation. The Segment Anything Model (SAM), a recently proposed method for extensive image recognition, is yet to be adequately assessed for its accuracy and efficiency on bloodstain image segmentation. This paper explores the application of pre-trained SAM and fine-tuned SAM on bloodstain image segmentation with diverse image backgrounds. Experiment results indicate that both pre-trained and fine-tuned SAM perform the bloodstain image segmentation task with satisfactory accuracy and efficiency, while fine-tuned SAM achieves an overall 2.2\% accuracy improvement than pre-trained SAM and 4.70\% acceleration in terms of speed for image recognition. Analysis of factors that influence bloodstain recognition is carried out. This research demonstrates the potential application of SAM on bloodstain image segmentation, showcasing the effectiveness of Artificial Intelligence application in criminology research. We release all code and demos at \url{https://github.com/Zdong104/Bloodstain_Analysis_Ai_Tool}

Yanghao Li, Rui Qian, Bowen Pan et al.

Unified multimodal Large Language Models (LLMs) that can both understand and generate visual content hold immense potential. However, existing open-source models often suffer from a performance trade-off between these capabilities. We present Manzano, a simple and scalable unified framework that substantially reduces this tension by coupling a hybrid image tokenizer with a well-curated training recipe. A single shared vision encoder feeds two lightweight adapters that produce continuous embeddings for image-to-text understanding and discrete tokens for text-to-image generation within a common semantic space. A unified autoregressive LLM predicts high-level semantics in the form of text and image tokens, with an auxiliary diffusion decoder subsequently translating the image tokens into pixels. The architecture, together with a unified training recipe over understanding and generation data, enables scalable joint learning of both capabilities. Manzano achieves state-of-the-art results among unified models, and is competitive with specialist models, particularly on text-rich evaluation. Our studies show minimal task conflicts and consistent gains from scaling model size, validating our design choice of a hybrid tokenizer.

Zhengdong Zhang, Zihan Dong, Yang Shi et al.

The rapid evolution of artificial intelligence (AI), specifically large language models (LLMs), has opened opportunities for various educational applications. This paper explored the feasibility of utilizing ChatGPT, one of the most popular LLMs, for automating feedback for Java programming assignments in an introductory computer science (CS1) class. Specifically, this study focused on three questions: 1) To what extent do students view LLM-generated feedback as formative? 2) How do students see the comparative affordances of feedback prompts that include their code, vs. those that exclude it? 3) What enhancements do students suggest for improving AI-generated feedback? To address these questions, we generated automated feedback using the ChatGPT API for four lab assignments in the CS1 class. The survey results revealed that students perceived the feedback as aligning well with formative feedback guidelines established by Shute. Additionally, students showed a clear preference for feedback generated by including the students' code as part of the LLM prompt, and our thematic study indicated that the preference was mainly attributed to the specificity, clarity, and corrective nature of the feedback. Moreover, this study found that students generally expected specific and corrective feedback with sufficient code examples, but had diverged opinions on the tone of the feedback. This study demonstrated that ChatGPT could generate Java programming assignment feedback that students perceived as formative. It also offered insights into the specific improvements that would make the ChatGPT-generated feedback useful for students.

Ethan Li, Anders Boesen Lindbo Larsen, Chen Zhang et al. · apple-ml, cmu

We introduce two multilingual, multimodal foundation language models that power Apple Intelligence features across Apple devices and services: i a 3B-parameter on-device model optimized for Apple silicon through architectural innovations such as KV-cache sharing and 2-bit quantization-aware training; and ii a scalable server model built on a novel Parallel-Track Mixture-of-Experts PT-MoE transformer that combines track parallelism, mixture-of-experts sparse computation, and interleaved global-local attention to deliver high quality with competitive cost on Apple's Private Cloud Compute platform. Both models are trained on large-scale multilingual and multimodal datasets sourced via responsible web crawling, licensed corpora, and high-quality synthetic data, then further refined with supervised fine-tuning and reinforcement learning on a new asynchronous platform. The resulting models support several additional languages while understanding images and executing tool calls. In public benchmarks and human evaluations, both the server model and the on-device model match or surpass comparably sized open baselines. A new Swift-centric Foundation Models framework exposes guided generation, constrained tool calling, and LoRA adapter fine-tuning, allowing developers to integrate these capabilities with a few lines of code. The latest advancements in Apple Intelligence models are grounded in our Responsible AI approach with safeguards like content filtering and locale-specific evaluation, as well as our commitment to protecting our users' privacy with innovations like Private Cloud Compute.

Jiquan Ngiam, Benjamin Caine, Vijay Vasudevan et al.

Predicting the motion of multiple agents is necessary for planning in dynamic environments. This task is challenging for autonomous driving since agents (e.g. vehicles and pedestrians) and their associated behaviors may be diverse and influence one another. Most prior work have focused on predicting independent futures for each agent based on all past motion, and planning against these independent predictions. However, planning against independent predictions can make it challenging to represent the future interaction possibilities between different agents, leading to sub-optimal planning. In this work, we formulate a model for predicting the behavior of all agents jointly, producing consistent futures that account for interactions between agents. Inspired by recent language modeling approaches, we use a masking strategy as the query to our model, enabling one to invoke a single model to predict agent behavior in many ways, such as potentially conditioned on the goal or full future trajectory of the autonomous vehicle or the behavior of other agents in the environment. Our model architecture employs attention to combine features across road elements, agent interactions, and time steps. We evaluate our approach on autonomous driving datasets for both marginal and joint motion prediction, and achieve state of the art performance across two popular datasets. Through combining a scene-centric approach, agent permutation equivariant model, and a sequence masking strategy, we show that our model can unify a variety of motion prediction tasks from joint motion predictions to conditioned prediction.

Ziyang Wang, Zhengdong Zhang, Irina Voiculescu

Segmentation algorithms for medical images are widely studied for various clinical and research purposes. In this paper, we propose a new and efficient method for medical image segmentation under noisy labels. The method operates under a deep learning paradigm, incorporating four novel contributions. Firstly, a residual interconnection is explored in different scale encoders to transfer gradient information efficiently. Secondly, four copy-and-crop connections are replaced by residual-block-based concatenation to alleviate the disparity between encoders and decoders. Thirdly, convolutional attention modules for feature refinement are studied on all scale decoders. Finally, an adaptive denoising learning strategy (ADL) is introduced into the training process to avoid too much influence from the noisy labels. Experimental results are illustrated on a publicly available benchmark database of spine CTs. Our proposed method achieves competitive performance against other state-of-the-art methods over a variety of different evaluation measures.

Anmol Gulati, James Qin, Chung-Cheng Chiu et al.

Recently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (RNNs). Transformer models are good at capturing content-based global interactions, while CNNs exploit local features effectively. In this work, we achieve the best of both worlds by studying how to combine convolution neural networks and transformers to model both local and global dependencies of an audio sequence in a parameter-efficient way. To this regard, we propose the convolution-augmented transformer for speech recognition, named Conformer. Conformer significantly outperforms the previous Transformer and CNN based models achieving state-of-the-art accuracies. On the widely used LibriSpeech benchmark, our model achieves WER of 2.1%/4.3% without using a language model and 1.9%/3.9% with an external language model on test/testother. We also observe competitive performance of 2.7%/6.3% with a small model of only 10M parameters.

Wei Han, Zhengdong Zhang, Yu Zhang et al.

Convolutional neural networks (CNN) have shown promising results for end-to-end speech recognition, albeit still behind other state-of-the-art methods in performance. In this paper, we study how to bridge this gap and go beyond with a novel CNN-RNN-transducer architecture, which we call ContextNet. ContextNet features a fully convolutional encoder that incorporates global context information into convolution layers by adding squeeze-and-excitation modules. In addition, we propose a simple scaling method that scales the widths of ContextNet that achieves good trade-off between computation and accuracy. We demonstrate that on the widely used LibriSpeech benchmark, ContextNet achieves a word error rate (WER) of 2.1%/4.6% without external language model (LM), 1.9%/4.1% with LM and 2.9%/7.0% with only 10M parameters on the clean/noisy LibriSpeech test sets. This compares to the previous best published system of 2.0%/4.6% with LM and 3.9%/11.3% with 20M parameters. The superiority of the proposed ContextNet model is also verified on a much larger internal dataset.

Wei Han, Zhengdong Zhang, Benjamin Caine et al.

Autonomous vehicles operate in a dynamic environment, where the speed with which a vehicle can perceive and react impacts the safety and efficacy of the system. LiDAR provides a prominent sensory modality that informs many existing perceptual systems including object detection, segmentation, motion estimation, and action recognition. The latency for perceptual systems based on point cloud data can be dominated by the amount of time for a complete rotational scan (e.g. 100 ms). This built-in data capture latency is artificial, and based on treating the point cloud as a camera image in order to leverage camera-inspired architectures. However, unlike camera sensors, most LiDAR point cloud data is natively a streaming data source in which laser reflections are sequentially recorded based on the precession of the laser beam. In this work, we explore how to build an object detector that removes this artificial latency constraint, and instead operates on native streaming data in order to significantly reduce latency. This approach has the added benefit of reducing the peak computational burden on inference hardware by spreading the computation over the acquisition time for a scan. We demonstrate a family of streaming detection systems based on sequential modeling through a series of modifications to the traditional detection meta-architecture. We highlight how this model may achieve competitive if not superior predictive performance with state-of-the-art, traditional non-streaming detection systems while achieving significant latency gains (e.g. 1/15'th - 1/3'rd of peak latency). Our results show that operating on LiDAR data in its native streaming formulation offers several advantages for self driving object detection -- advantages that we hope will be useful for any LiDAR perception system where minimizing latency is critical for safe and efficient operation.

Zhengdong Zhang, Shuai Li, Ziyang Wang et al.

As Deep Convolutional Neural Networks (DCNNs) have shown robust performance and results in medical image analysis, a number of deep-learning-based tumor detection methods were developed in recent years. Nowadays, the automatic detection of pancreatic tumors using contrast-enhanced Computed Tomography (CT) is widely applied for the diagnosis and staging of pancreatic cancer. Traditional hand-crafted methods only extract low-level features. Normal convolutional neural networks, however, fail to make full use of effective context information, which causes inferior detection results. In this paper, a novel and efficient pancreatic tumor detection framework aiming at fully exploiting the context information at multiple scales is designed. More specifically, the contribution of the proposed method mainly consists of three components: Augmented Feature Pyramid networks, Self-adaptive Feature Fusion and a Dependencies Computation (DC) Module. A bottom-up path augmentation to fully extract and propagate low-level accurate localization information is established firstly. Then, the Self-adaptive Feature Fusion can encode much richer context information at multiple scales based on the proposed regions. Finally, the DC Module is specifically designed to capture the interaction information between proposals and surrounding tissues. Experimental results achieve competitive performance in detection with the AUC of 0.9455, which outperforms other state-of-the-art methods to our best of knowledge, demonstrating the proposed framework can detect the tumor of pancreatic cancer efficiently and accurately.

Zhengdong Zhang, Trevor Henderson, Sertac Karaman et al.

Exploration tasks are embedded in many robotics applications, such as search and rescue and space exploration. Information-based exploration algorithms aim to find the most informative trajectories by maximizing an information-theoretic metric, such as the mutual information between the map and potential future measurements. Unfortunately, most existing information-based exploration algorithms are plagued by the computational difficulty of evaluating the Shannon mutual information metric. In this paper, we consider the fundamental problem of evaluating Shannon mutual information between the map and a range measurement. First, we consider 2D environments. We propose a novel algorithm, called the Fast Shannon Mutual Information (FSMI). The key insight behind the algorithm is that a certain integral can be computed analytically, leading to substantial computational savings. Second, we consider 3D environments, represented by efficient data structures, e.g., an OctoMap, such that the measurements are compressed by Run-Length Encoding (RLE). We propose a novel algorithm, called FSMI-RLE, that efficiently evaluates the Shannon mutual information when the measurements are compressed using RLE. For both the FSMI and the FSMI-RLE, we also propose variants that make different assumptions on the sensor noise distribution for the purpose of further computational savings. We evaluate the proposed algorithms in extensive experiments. In particular, we show that the proposed algorithms outperform existing algorithms that compute Shannon mutual information as well as other algorithms that compute the Cauchy-Schwarz Quadratic mutual information (CSQMI). In addition, we demonstrate the computation of Shannon mutual information on a 3D map for the first time.

Amr Suleiman, Zhengdong Zhang, Luca Carlone et al.

This paper presents Navion, an energy-efficient accelerator for visual-inertial odometry (VIO) that enables autonomous navigation of miniaturized robots (e.g., nano drones), and virtual/augmented reality on portable devices. The chip uses inertial measurements and mono/stereo images to estimate the drone's trajectory and a 3D map of the environment. This estimate is obtained by running a state-of-the-art VIO algorithm based on non-linear factor graph optimization, which requires large irregularly structured memories and heterogeneous computation flow. To reduce the energy consumption and footprint, the entire VIO system is fully integrated on chip to eliminate costly off-chip processing and storage. This work uses compression and exploits both structured and unstructured sparsity to reduce on-chip memory size by 4.1$\times$. Parallelism is used under tight area constraints to increase throughput by 43%. The chip is fabricated in 65nm CMOS, and can process 752$\times$480 stereo images from EuRoC dataset in real-time at 20 frames per second (fps) consuming only an average power of 2mW. At its peak performance, Navion can process stereo images at up to 171 fps and inertial measurements at up to 52 kHz, while consuming an average of 24mW. The chip is configurable to maximize accuracy, throughput and energy-efficiency trade-offs and to adapt to different environments. To the best of our knowledge, this is the first fully integrated VIO system in an ASIC.

Vivienne Sze, Yu-Hsin Chen, Joel Emer et al.

Machine learning plays a critical role in extracting meaningful information out of the zetabytes of sensor data collected every day. For some applications, the goal is to analyze and understand the data to identify trends (e.g., surveillance, portable/wearable electronics); in other applications, the goal is to take immediate action based the data (e.g., robotics/drones, self-driving cars, smart Internet of Things). For many of these applications, local embedded processing near the sensor is preferred over the cloud due to privacy or latency concerns, or limitations in the communication bandwidth. However, at the sensor there are often stringent constraints on energy consumption and cost in addition to throughput and accuracy requirements. Furthermore, flexibility is often required such that the processing can be adapted for different applications or environments (e.g., update the weights and model in the classifier). In many applications, machine learning often involves transforming the input data into a higher dimensional space, which, along with programmable weights, increases data movement and consequently energy consumption. In this paper, we will discuss how these challenges can be addressed at various levels of hardware design ranging from architecture, hardware-friendly algorithms, mixed-signal circuits, and advanced technologies (including memories and sensors).

Amr Suleiman, Zhengdong Zhang, Vivienne Sze

This paper presents a programmable, energy-efficient and real-time object detection accelerator using deformable parts models (DPM), with 2x higher accuracy than traditional rigid body models. With 8 deformable parts detection, three methods are used to address the high computational complexity: classification pruning for 33x fewer parts classification, vector quantization for 15x memory size reduction, and feature basis projection for 2x reduction of the cost of each classification. The chip is implemented in 65nm CMOS technology, and can process HD (1920x1080) images at 30fps without any off-chip storage while consuming only 58.6mW (0.94nJ/pixel, 1168 GOPS/W). The chip has two classification engines to simultaneously detect two different classes of objects. With a tested high throughput of 60fps, the classification engines can be time multiplexed to detect even more than two object classes. It is energy scalable by changing the pruning factor or disabling the parts classification.

Zhengdong Zhang, Vivienne Sze

State-of-the-art super-resolution (SR) algorithms require significant computational resources to achieve real-time throughput (e.g., 60Mpixels/s for HD video). This paper introduces FAST (Free Adaptive Super-resolution via Transfer), a framework to accelerate any SR algorithm applied to compressed videos. FAST exploits the temporal correlation between adjacent frames such that SR is only applied to a subset of frames; SR pixels are then transferred to the other frames. The transferring process has negligible computation cost as it uses information already embedded in the compressed video (e.g., motion vectors and residual). Adaptive processing is used to retain accuracy when the temporal correlation is not present (e.g., occlusions). FAST accelerates state-of-the-art SR algorithms by up to 15x with a visual quality loss of 0.2dB. FAST is an important step towards real-time SR algorithms for ultra-HD displays and energy constrained devices (e.g., phones and tablets).

Zhengdong Zhang, Phillip Isola, Edward H. Adelson

In this paper, we study the problem of reproducing the world lighting from a single image of an object covered with random specular microfacets on the surface. We show that such reflectors can be interpreted as a randomized mapping from the lighting to the image. Such specular objects have very different optical properties from both diffuse surfaces and smooth specular objects like metals, so we design special imaging system to robustly and effectively photograph them. We present simple yet reliable algorithms to calibrate the proposed system and do the inference. We conduct experiments to verify the correctness of our model assumptions and prove the effectiveness of our pipeline.