We address the problem of personalized, interactive text-to-image (T2I) generation, designing a reinforcement learning (RL) agent which iteratively improves a set of generated images for a user through a sequence of prompt expansions. Using human raters, we create a novel dataset of sequential preferences, which we leverage, together with large-scale open-source (non-sequential) datasets. We construct user-preference and user-choice models using an EM strategy and identify varying user preference types. We then leverage a large multimodal language model (LMM) and a value-based RL approach to suggest a personalized and diverse slate of prompt expansions to the user. Our Personalized And Sequential Text-to-image Agent (PASTA) extends T2I models with personalized multi-turn capabilities, fostering collaborative co-creation and addressing uncertainty or underspecification in a user's intent. We evaluate PASTA using human raters, showing significant improvement compared to baseline methods. We also release our sequential rater dataset and simulated user-rater interactions to support future research in personalized, multi-turn T2I generation.

The performance of modern reinforcement learning algorithms critically relies on tuning ever-increasing numbers of hyperparameters. Often, small changes in a hyperparameter can lead to drastic changes in performance, and different environments require very different hyperparameter settings to achieve state-of-the-art performance reported in the literature. We currently lack a scalable and widely accepted approach to characterizing these complex interactions. This work proposes a new empirical methodology for studying, comparing, and quantifying the sensitivity of an algorithm's performance to hyperparameter tuning for a given set of environments. We then demonstrate the utility of this methodology by assessing the hyperparameter sensitivity of several commonly used normalization variants of PPO. The results suggest that several algorithmic performance improvements may, in fact, be a result of an increased reliance on hyperparameter tuning.

In differential privacy, $\textit{continual observation}$ refers to problems in which we wish to continuously release a function of a dataset that is revealed one element at a time. The challenge is to maintain a good approximation while keeping the combined output over all time steps differentially private. In the special case of $\textit{continual counting}$ we seek to approximate a sum of binary input elements. This problem has received considerable attention lately, in part due to its relevance in implementations of differentially private stochastic gradient descent. $\textit{Factorization mechanisms}$ are the leading approach to continual counting, but the best such mechanisms do not work well in $\textit{streaming}$ settings since they require space proportional to the size of the input. In this paper, we present a simple approach to approximating factorization mechanisms in low space via $\textit{binning}$, where adjacent matrix entries with similar values are changed to be identical in such a way that a matrix-vector product can be maintained in sublinear space. Our approach has provable sublinear space guarantees for a class of lower triangular matrices whose entries are monotonically decreasing away from the diagonal. We show empirically that even with very low space usage we are able to closely match, and sometimes surpass, the performance of asymptotically optimal factorization mechanisms. Recently, and independently of our work, Dvijotham et al. have also suggested an approach to implementing factorization mechanisms in a streaming setting. Their work differs from ours in several respects: It only addresses factorization into $\textit{Toeplitz}$ matrices, only considers $\textit{maximum}$ error, and uses a different technique based on rational function approximation that seems less versatile than our binning approach.

To develop autonomous agents capable of executing complex, multi-step decision-making tasks as specified by humans in natural language, existing reinforcement learning approaches typically require expensive labeled datasets or access to real-time experimentation. Moreover, conventional methods often face difficulties in generalizing to unseen goals and states, thereby limiting their practical applicability. This paper presents TEDUO, a novel training pipeline for offline language-conditioned policy learning. TEDUO operates on easy-to-obtain, unlabeled datasets and is suited for the so-called in-the-wild evaluation, wherein the agent encounters previously unseen goals and states. To address the challenges posed by such data and evaluation settings, our method leverages the prior knowledge and instruction-following capabilities of large language models (LLMs) to enhance the fidelity of pre-collected offline data and enable flexible generalization to new goals and states. Empirical results demonstrate that the dual role of LLMs in our framework-as data enhancers and generalizers-facilitates both effective and data-efficient learning of generalizable language-conditioned policies.

Importance and Endangerment of Low-Resource Languages in the Global Linguistic Ecology The linguistic landscape of the world constitutes a complex tapestry interwoven with a rich diversity of languages, each strand epitomizing a distinctive cultural, historical, and social identity. This global linguistic diversity forms a foundational pillar of human civilization, cultivating an array of perspectives and worldviews that enhance our collective intellectual legacy. Among these, low-resource languages occupy a particularly crucial position, not merely as modes of communication but as repositories of distinctive cultural knowledge, historical narratives, and worldviews. These languages, frequently spoken by smaller communities, are essential to the preservation of cultural heritage and the transmission of indigenous knowledge systems. However, the global linguistic landscape is presently undergoing an extraordinary crisis, with lowresource languages among the most threatened. The swift vanishing of these languages is of serious concern, highlighted by concerning data and studies. It is estimated, for example, that around 40% of the world's 7,000 languages face extinction, with numerous low-resource languages having fewer than 1,000 speakers [94].

Motivation: Codon optimization of Open Reading Frame (ORF) sequences is essential for enhancing mRNA stability and expression in applications like mRNA vaccines, where codon choice can significantly impact protein yield which directly impacts immune strength. In this work, we investigate the use of a pre-trained protein language model (PPLM) for getting a rich representation of amino acids which could be utilized for codon optimization. This leaves us with a simpler fine-tuning task over PPLM in optimizing ORF sequences. Results: The ORFs generated by our proposed models outperformed their natural counterparts encoding the same proteins on computational metrics for stability and expression. They also demonstrated enhanced performance against the benchmark ORFs used in mRNA vaccines for the SARS-CoV-2 viral spike protein and the varicella-zoster virus (VZV). These results highlight the potential of adapting PPLM for designing ORFs tailored to encode target antigens in mRNA vaccines.

Natural intelligence processes experience as a continuous stream, sensing, acting, and learning moment-by-moment in real time. Streaming learning, the modus operandi of classic reinforcement learning (RL) algorithms like Q-learning and TD, mimics natural learning by using the most recent sample without storing it. This approach is also ideal for resource-constrained, communication-limited, and privacy-sensitive applications. However, in deep RL, learners almost always use batch updates and replay buffers, making them computationally expensive and incompatible with streaming learning. Although the prevalence of batch deep RL is often attributed to its sample efficiency, a more critical reason for the absence of streaming deep RL is its frequent instability and failure to learn, which we refer to as stream barrier. This paper introduces the stream-x algorithms, the first class of deep RL algorithms to overcome stream barrier for both prediction and control and match sample efficiency of batch RL. Through experiments in Mujoco Gym, DM Control Suite, and Atari Games, we demonstrate stream barrier in existing algorithms and successful stable learning with our stream-x algorithms: stream Q, stream AC, and stream TD, achieving the best model-free performance in DM Control Dog environments. A set of common techniques underlies the stream-x algorithms, enabling their success with a single set of hyperparameters and allowing for easy extension to other algorithms, thereby reviving streaming RL.

This paper explores the transformative role of Agent AI and LangGraph in advancing the automation and effectiveness of machine translation (MT). Agents are modular components designed to perform specific tasks, such as translating between particular languages, with specializations like TranslateEnAgent, TranslateFrenchAgent, and TranslateJpAgent for English, French, and Japanese translations, respectively. These agents leverage the powerful semantic capabilities of large language models (LLMs), such as GPT-4o, to ensure accurate, contextually relevant translations while maintaining modularity, scalability, and context retention. LangGraph, a graph-based framework built on LangChain, simplifies the creation and management of these agents and their workflows. It supports dynamic state management, enabling agents to maintain dialogue context and automates complex workflows by linking agents and facilitating their collaboration. With flexibility, open-source community support, and seamless integration with LLMs, LangGraph empowers agents to deliver high-quality translations. Together, Agent AI and LangGraph create a cohesive system where LangGraph orchestrates agent interactions, ensuring that user inputs are analyzed, routed, and processed efficiently. Experimental results demonstrate the potential of this system to enhance multilingual translation accuracy and scalability. By highlighting modular design and automated workflows, this paper sets the stage for further innovations in intelligent machine translation services.

We consider the problem of hypothesis testing for discrete distributions. In the standard model, where we have sample access to an underlying distribution $p$, extensive research has established optimal bounds for uniformity testing, identity testing (goodness of fit), and closeness testing (equivalence or two-sample testing). We explore these problems in a setting where a predicted data distribution, possibly derived from historical data or predictive machine learning models, is available. We demonstrate that such a predictor can indeed reduce the number of samples required for all three property testing tasks. The reduction in sample complexity depends directly on the predictor's quality, measured by its total variation distance from $p$. A key advantage of our algorithms is their adaptability to the precision of the prediction. Specifically, our algorithms can self-adjust their sample complexity based on the accuracy of the available prediction, operating without any prior knowledge of the estimation's accuracy (i.e. they are consistent). Additionally, we never use more samples than the standard approaches require, even if the predictions provide no meaningful information (i.e. they are also robust). We provide lower bounds to indicate that the improvements in sample complexity achieved by our algorithms are information-theoretically optimal. Furthermore, experimental results show that the performance of our algorithms on real data significantly exceeds our worst-case guarantees for sample complexity, demonstrating the practicality of our approach.

Robotic search of people in human-centered environments, including healthcare settings, is challenging as autonomous robots need to locate people without complete or any prior knowledge of their schedules, plans or locations. Furthermore, robots need to be able to adapt to real-time events that can influence a person's plan in an environment. In this paper, we present MLLM-Search, a novel zero-shot person search architecture that leverages multimodal large language models (MLLM) to address the mobile robot problem of searching for a person under event-driven scenarios with varying user schedules. Our approach introduces a novel visual prompting method to provide robots with spatial understanding of the environment by generating a spatially grounded waypoint map, representing navigable waypoints by a topological graph and regions by semantic labels. This is incorporated into a MLLM with a region planner that selects the next search region based on the semantic relevance to the search scenario, and a waypoint planner which generates a search path by considering the semantically relevant objects and the local spatial context through our unique spatial chain-of-thought prompting approach. Extensive 3D photorealistic experiments were conducted to validate the performance of MLLM-Search in searching for a person with a changing schedule in different environments. An ablation study was also conducted to validate the main design choices of MLLM-Search. Furthermore, a comparison study with state-of-the art search methods demonstrated that MLLM-Search outperforms existing methods with respect to search efficiency. Real-world experiments with a mobile robot in a multi-room floor of a building showed that MLLM-Search was able to generalize to finding a person in a new unseen environment.