Generative AI (AI) has become ubiquitous in both daily and professional life, with emerging research demonstrating its potential as a tool for accessibility. Neurodivergent people, often left out by existing accessibility technologies, develop their own ways of navigating normative expectations. GAI offers new opportunities for access, but it is important to understand how neurodivergent "power users"-successful early adopters-engage with it and the challenges they face. Further, we must understand how marginalization and intersectional identities influence their interactions with GAI. Our autoethnography, enhanced by privacy-preserving GAI-based diaries and interviews, reveals the intricacies of using GAI to navigate normative environments and expectations. Our findings demonstrate how GAI can both support and complicate tasks like code-switching, emotional regulation, and accessing information. We show that GAI can help neurodivergent users to reclaim their agency in systems that diminish their autonomy and self-determination. However, challenges such as balancing authentic self-expression with societal conformity, alongside other risks, create barriers to realizing GAI's full potential for accessibility.

Simulating a single trajectory of a dynamical system under some state-dependent policy is a core bottleneck in policy optimization (PO) algorithms. The many inherently serial policy evaluations that must be performed in a single simulation constitute the bulk of this bottleneck. In applying PO to supply chain optimization (SCO) problems, simulating a single sample path corresponding to one month of a supply chain can take several hours. We present an iterative algorithm to accelerate policy simulation, dubbed Picard Iteration. This scheme carefully assigns policy evaluation tasks to independent processes. Within an iteration, any given process evaluates the policy only on its assigned tasks while assuming a certain cached’ evaluation for other tasks; the cache is updated at the end of the iteration. Implemented on GPUs, this scheme admits batched evaluation of the policy across a single trajectory. We prove that the structure afforded by many SCO problems allows convergence in a small number of iterations independent of the horizon. We demonstrate practical speedups of 400x on large-scale SCO problems even with a single GPU, and also demonstrate practical efficacy in other RL environments.

Experiments in online platforms frequently suffer from network interference, where treatments applied to one unit affect outcomes of connected ones, violating the Stable Unit Treatment Value Assumption (SUTVA) and substantially biasing treatment effect estimations. A common solution is to cluster connected units and randomize treatments at the cluster level, typically followed by estimation using either a simple difference-in-means (DM) estimator, which ignores remaining interference and suffers from O(δ) bias where δ measures interference strength; or the unbiased Horvitz-Thompson (HT) estimator, which eliminates bias through importance sampling but incurs exponentially high variance scaling with d, the maximum network degree. This fundamental limitation persists even with sophisticated clustering designs, creating narrow bias-variance tradeoffs often inadequate for practical applications.

MOTIVATION: Large Language Models (LLMs) have the potential to revolutionize the field of Natural Language Processing, excelling not only in text generation and reasoning tasks but also in their ability for zero/few-shot learning, swiftly adapting to new tasks with minimal fine-tuning. LLMs have also demonstrated great promise in biomedical and healthcare applications. However, when it comes to Named Entity Recognition (NER), particularly within the biomedical domain, LLMs fall short of the effectiveness exhibited by fine-tuned domain-specific models. One key reason is that NER is typically conceptualized as a sequence labeling task, whereas LLMs are optimized for text generation and reasoning tasks. RESULTS: We developed an instruction-based learning paradigm that transforms biomedical NER from a sequence labeling task into a generation task. This paradigm is end-to-end and streamlines the training and evaluation process by automatically repurposing pre-existing biomedical NER datasets. We further developed BioNER-LLaMA using the proposed paradigm with LLaMA-7B as the foundational LLM. We conducted extensive testing on BioNER-LLaMA across three widely recognized biomedical NER datasets, consisting of entities related to diseases, chemicals, and genes. The results revealed that BioNER-LLaMA consistently achieved higher F1-scores ranging from 5% to 30% compared to the few-shot learning capabilities of GPT-4 on datasets with different biomedical entities. We show that a general-domain LLM can match the performance of rigorously fine-tuned PubMedBERT models and PMC-LLaMA, biomedical-specific language model. Our findings underscore the potential of our proposed paradigm in developing general-domain LLMs that can rival SOTA performances in multi-task, multi-domain scenarios in biomedical and health applications. AVAILABILITY AND IMPLEMENTATION: Datasets and other resources are available at https://github.com/BIDS-Xu-Lab/BioNER-LLaMA.

BACKGROUND: Taxonomic classification of reads obtained by metagenomic sequencing is often a first step for understanding a microbial community, but correctly assigning sequencing reads to the strain or sub-species level has remained a challenging computational problem. RESULTS: We introduce Mora, a MetagenOmic read Re-Assignment algorithm capable of assigning short and long metagenomic reads with high precision, even at the strain level. Mora is able to accurately re-assign reads by first estimating abundances through an expectation-maximization algorithm and then utilizing abundance information to re-assign query reads. The key idea behind Mora is to maximize read re-assignment qualities while simultaneously minimizing the difference from estimated abundance levels, allowing Mora to avoid over assigning reads to the same genomes. On simulated diverse reads, this allows Mora to achieve F1 scores comparable to other algorithms while having less runtime. However, Mora significantly outshines other algorithms on very similar reads. We show that the high penalty of over assigning reads to a common reference genome allows Mora to accurately infer correct strains for real data in the form of E. coli reads. CONCLUSIONS: Mora is a fast and accurate read re-assignment algorithm that is modularized, allowing it to be incorporated into general metagenomics and genomics workflows. It is freely available at https://github.com/AfZheng126/MORA .

Interference is a ubiquitous problem in experiments conducted on two-sided content marketplaces, such as Douyin (China’s analog of TikTok). In many cases, creators are the natural unit of experimentation, but creators interfere with each other through competition for viewers’ limited time and attention. “Naive” estimators currently used in practice simply ignore the interference, but in doing so incur bias on the order of the treatment effect. We formalize the problem of inference in such experiments as one of policy evaluation. Off-policy estimators, while unbiased, are impractically high variance. We introduce a novel Monte-Carlo estimator, based on “Differences-in-Qs” (DQ) techniques, which achieves bias that is second-order in the treatment effect, while remaining sample-efficient to estimate. On the theoretical side, our contribution is to develop a generalized theory of Taylor expansions for policy evaluation, which extends DQ theory to all major MDP formulations. On the practical side, we implement our estimator on Douyin’s experimentation platform, and in the process develop DQ into a truly “plug-and-play” estimator for interference in real-world settings: one which provides robust, low-bias, low-variance treatment effect estimates; admits computationally cheap, asymptotically exact uncertainty quantification; and reduces MSE by 99% compared to the best existing alternatives in our applications.

We consider experiments in dynamical systems where interventions on some experimental units impact other units through a limiting constraint (such as a limited supply of products). Despite outsize practical importance, the best estimators for this `Markovian' interference problem are largely heuristic in nature, and their bias is not well understood. We formalize the problem of inference in such experiments as one of policy evaluation. Off-policy estimators, while unbiased, apparently incur a large penalty in variance relative to state-of-the-art heuristics. We introduce an on-policy estimator: the Differences-In-Q's (DQ) estimator. We show that the DQ estimator can in general have exponentially smaller variance than off-policy evaluation. At the same time, its bias is second order in the impact of the intervention. This yields a striking bias-variance tradeoff so that the DQ estimator effectively dominates state-of-the-art alternatives. From a theoretical perspective, we introduce three separate novel techniques that are of independent interest in the theory of Reinforcement Learning (RL). Our empirical evaluation includes a set of experiments on a city-scale ride-hailing simulator.

This paper provides the first sample complexity lower bounds for the estimation of simple diffusion models which seek to explain the diffusion of an epidemic in a network. The Susceptible-Infected-Recovered (SIR) model is a classic example, proposed nearly a century ago [2]. The SIR model remains a cornerstone for the forecasting of epidemics. The so-called Bass model [1] remains a basic building block in forecasting consumer adoption of new products and services. The durability of these models arises from the fact that they have shown an excellent fit to data, in numerous studies spanning both the epidemiology and marketing literatures. Somewhat paradoxically, using these same models as reliable forecasting tools presents a challenge.