OpenAI o1 System Card

The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. These advanced reasoning capabilities provide new avenues for improving the safety and robustness of our models. In particular, our models can reason about our safety policies in context when responding to potentially unsafe prompts, through deliberative alignment. This leads to state-of-the-art performance on certain benchmarks for risks such as generating illicit advice, choosing stereotyped responses, and succumbing to known jailbreaks. Training models to incorporate a chain of thought before answering has the potential to unlock substantial benefits, while also increasing potential risks that stem from heightened intelligence. Our results underscore the need for building robust alignment methods, extensively stress-testing their efficacy, and maintaining meticulous risk management protocols. This report outlines the safety work carried out for the OpenAI o1 and OpenAI o1-mini models, including safety evaluations, external red teaming, and Preparedness Framework evaluations.

Towards Automated Model Design on Recommender Systems

The increasing popularity of deep learning models has created new opportunities for developing AI-based recommender systems. Designing recommender systems using deep neural networks requires careful architecture design, and further optimization demands extensive co-design efforts on jointly optimizing model architecture and hardware. Design automation, such as Automated Machine Learning (AutoML), is necessary to fully exploit the potential of recommender model design, including model choices and model-hardware co-design strategies. We introduce a novel paradigm that utilizes weight sharing to explore abundant solution spaces. Our paradigm creates a large supernet to search for optimal architectures and co-design strategies to address the challenges of data multi-modality and heterogeneity in the recommendation domain. From a model perspective, the supernet includes a variety of operators, dense connectivity, and dimension search options. From a co-design perspective, it encompasses versatile Processing-In-Memory (PIM) configurations to produce hardware-efficient models. Our solution space's scale, heterogeneity, and complexity pose several challenges, which we address by proposing various techniques for training and evaluating the supernet. Our crafted models show promising results on three Click-Through Rates (CTR) prediction benchmarks, outperforming both manually designed and AutoML-crafted models with state-of-the-art performance when focusing solely on architecture search. From a co-design perspective, we achieve 2x FLOPs efficiency, 1.8x energy efficiency, and 1.5x performance improvements in recommender models.

Masked Autoencoders are Parameter-Efficient Federated Continual Learners

Federated learning is a specific distributed learning paradigm in which a central server aggregates updates from multiple clients' local models, thereby enabling the server to learn without requiring clients to upload their private data, maintaining data privacy. While existing federated learning methods are primarily designed for static data, real-world applications often require clients to learn new categories over time. This challenge necessitates the integration of continual learning techniques, resulting in federated continual learning (FCL). Although advanced prompt-based continual learning methods leverage pre-trained transformers to mitigate catastrophic forgetting, they do not adequately address the non-IID challenges in federated learning. To address both catastrophic forgetting and non-IID issues, we propose to use masked autoencoders (MAEs) as parameter-efficient federated continual learners, called pMAE. pMAE learns reconstructive prompt on the client side through image reconstruction using MAEs. On the server side, it reconstructs the uploaded restore information to capture the data distribution across previous tasks and different clients, using these reconstructed images to finetune discriminative prompt and classifier parameters designed for classification, thereby alleviating catastrophic forgetting and non-IID challenges on a global scale. Experimental results demonstrate that pMAE achieves performance comparable to existing prompt-based methods and can enhance their effectiveness, particularly when using self-supervised pre-trained transformers as the backbone. Code is available at: https://github.com/ycheoo/pMAE.

FPPL: An Efficient and Non-IID Robust Federated Continual Learning Framework

Federated continual learning (FCL) aims to learn from sequential data stream in the decentralized federated learning setting, while simultaneously mitigating the catastrophic forgetting issue in classical continual learning. Existing FCL methods usually employ typical rehearsal mechanisms, which could result in privacy violations or additional onerous storage and computational burdens. In this work, an efficient and non-IID robust federated continual learning framework, called Federated Prototype-Augmented Prompt Learning (FPPL), is proposed. The FPPL can collaboratively learn lightweight prompts augmented by prototypes without rehearsal. On the client side, a fusion function is employed to fully leverage the knowledge contained in task-specific prompts for alleviating catastrophic forgetting. Additionally, global prototypes aggregated from the server are used to obtain unified representation through contrastive learning, mitigating the impact of non-IID-derived data heterogeneity. On the server side, locally uploaded prototypes are utilized to perform debiasing on the classifier, further alleviating the performance degradation caused by both non-IID and catastrophic forgetting. Empirical evaluations demonstrate the effectiveness of FPPL, achieving notable performance with an efficient design while remaining robust to diverse non-IID degrees. Code is available at: https://github.com/ycheoo/FPPL.

GPT-4o System Card

GPT-4o is an autoregressive omni model that accepts as input any combination of text, audio, image, and video, and generates any combination of text, audio, and image outputs. It's trained end-to-end across text, vision, and audio, meaning all inputs and outputs are processed by the same neural network. GPT-4o can respond to audio inputs in as little as 232 milliseconds, with an average of 320 milliseconds, which is similar to human response time in conversation. It matches GPT-4 Turbo performance on text in English and code, with significant improvement on text in non-English languages, while also being much faster and 50\% cheaper in the API. GPT-4o is especially better at vision and audio understanding compared to existing models. In line with our commitment to building AI safely and consistent with our voluntary commitments to the White House, we are sharing the GPT-4o System Card, which includes our Preparedness Framework evaluations. In this System Card, we provide a detailed look at GPT-4o's capabilities, limitations, and safety evaluations across multiple categories, focusing on speech-to-speech while also evaluating text and image capabilities, and measures we've implemented to ensure the model is safe and aligned. We also include third-party assessments on dangerous capabilities, as well as discussion of potential societal impacts of GPT-4o's text and vision capabilities.

Ghost imaging-based Non-contact Heart Rate Detection

Remote heart rate measurement is an increasingly concerned research field, usually using remote photoplethysmography (rPPG) to collect heart rate information through video data collection. However, in certain specific scenarios (such as low light conditions, intense lighting, and non-line-of-sight situations), traditional imaging methods fail to capture image information effectively, that may lead to difficulty or inability in measuring heart rate. To address these limitations, this study proposes using ghost imaging as a substitute for traditional imaging in the aforementioned scenarios. The mean absolute error between experimental measurements and reference true values is 4.24 bpm.Additionally, the bucket signals obtained by the ghost imaging system can be directly processed using digital signal processing techniques, thereby enhancing personal privacy protection.

Understanding Memory-Regret Trade-Off for Streaming Stochastic Multi-Armed Bandits

We study the stochastic multi-armed bandit problem in the $P$-pass streaming model. In this problem, the $n$ arms are present in a stream and at most $m<n$ arms and their statistics can be stored in the memory. We give a complete characterization of the optimal regret in terms of $m, n$ and $P$. Specifically, we design an algorithm with $\tilde O\left((n-m)^{1+\frac{2^{P}-2}{2^{P+1}-1}} n^{\frac{2-2^{P+1}}{2^{P+1}-1}} T^{\frac{2^P}{2^{P+1}-1}}\right)$ regret and complement it with an $\tilde \Omega\left((n-m)^{1+\frac{2^{P}-2}{2^{P+1}-1}} n^{\frac{2-2^{P+1}}{2^{P+1}-1}} T^{\frac{2^P}{2^{P+1}-1}}\right)$ lower bound when the number of rounds $T$ is sufficiently large. Our results are tight up to a logarithmic factor in $n$ and $P$.

ViSTec: Video Modeling for Sports Technique Recognition and Tactical Analysis

The immense popularity of racket sports has fueled substantial demand in tactical analysis with broadcast videos. However, existing manual methods require laborious annotation, and recent attempts leveraging video perception models are limited to low-level annotations like ball trajectories, overlooking tactics that necessitate an understanding of stroke techniques. State-of-the-art action segmentation models also struggle with technique recognition due to frequent occlusions and motion-induced blurring in racket sports videos. To address these challenges, We propose ViSTec, a Video-based Sports Technique recognition model inspired by human cognition that synergizes sparse visual data with rich contextual insights. Our approach integrates a graph to explicitly model strategic knowledge in stroke sequences and enhance technique recognition with contextual inductive bias. A two-stage action perception model is jointly trained to align with the contextual knowledge in the graph. Experiments demonstrate that our method outperforms existing models by a significant margin. Case studies with experts from the Chinese national table tennis team validate our model's capacity to automate analysis for technical actions and tactical strategies. More details are available at: https://ViSTec2024.github.io/.

On Interpolating Experts and Multi-Armed Bandits

Learning with expert advice and multi-armed bandit are two classic online decision problems which differ on how the information is observed in each round of the game. We study a family of problems interpolating the two. For a vector $\mathbf{m}=(m_1,\dots,m_K)\in \mathbb{N}^K$, an instance of $\mathbf{m}$-MAB indicates that the arms are partitioned into $K$ groups and the $i$-th group contains $m_i$ arms. Once an arm is pulled, the losses of all arms in the same group are observed. We prove tight minimax regret bounds for $\mathbf{m}$-MAB and design an optimal PAC algorithm for its pure exploration version, $\mathbf{m}$-BAI, where the goal is to identify the arm with minimum loss with as few rounds as possible. We show that the minimax regret of $\mathbf{m}$-MAB is $\Theta\left(\sqrt{T\sum_{k=1}^K\log (m_k+1)}\right)$ and the minimum number of pulls for an $(\epsilon,0.05)$-PAC algorithm of $\mathbf{m}$-BAI is $\Theta\left(\frac{1}{\epsilon^2}\cdot \sum_{k=1}^K\log (m_k+1)\right)$. Both our upper bounds and lower bounds for $\mathbf{m}$-MAB can be extended to a more general setting, namely the bandit with graph feedback, in terms of the clique cover and related graph parameters. As consequences, we obtained tight minimax regret bounds for several families of feedback graphs.

Optimizing Long-term Value for Auction-Based Recommender Systems via On-Policy Reinforcement Learning

Auction-based recommender systems are prevalent in online advertising platforms, but they are typically optimized to allocate recommendation slots based on immediate expected return metrics, neglecting the downstream effects of recommendations on user behavior. In this study, we employ reinforcement learning to optimize for long-term return metrics in an auction-based recommender system. Utilizing temporal difference learning, a fundamental reinforcement learning algorithm, we implement an one-step policy improvement approach that biases the system towards recommendations with higher long-term user engagement metrics. This optimizes value over long horizons while maintaining compatibility with the auction framework. Our approach is grounded in dynamic programming ideas which show that our method provably improves upon the existing auction-based base policy. Through an online A/B test conducted on an auction-based recommender system which handles billions of impressions and users daily, we empirically establish that our proposed method outperforms the current production system in terms of long-term user engagement metrics.