Predicting the outcomes of species invasions is a central goal of ecology, a task made especially challenging due to ecological feedbacks. To address this, we develop a general theory of ecological invasions applicable to a wide variety of ecological models: including Lotka-Volterra models, consumer resource models, and models with cross feeding. Importantly, our framework remains valid even when invading evolved (non-random) communities and accounts for invasion-driven species extinctions. We derive analytical expressions relating invasion fitness to invader abundance, shifts in the community, and extinction probabilities. These results can be understood through a new quantity we term ``dressed invasion fitness'', which augments the traditional notion of invasion fitness by incorporating ecological feedbacks. We apply our theory to analyze short-term evolutionary dynamics through a series of invasions by mutants whose traits are correlated with an existing parent. We demonstrate that, generically, mutants and parents can coexist, often by driving the extinction of low-abundance species. We validate theoretical predictions against experimental datasets spanning ecosystems from plants to microbial protists. Our work highlights the central role of ecological feedbacks in shaping community responses to invasions and mutations, suggesting that parent-mutant coexistence is widespread in eco-evolutionary dynamics.
We consider the problem of generating valid and small prediction sets by sampling outputs (e.g., software code and natural language text) from a black-box deep generative model for a given input (e.g., textual prompt). The validity of a prediction set is determined by a user-defined binary admissibility function depending on the target application. For example, requiring at least one program in the set to pass all test cases in code generation application. To address this problem, we develop a simple and effective conformal inference algorithm referred to as Generative Prediction Sets (GPS). Given a set of calibration examples and black-box access to a deep generative model, GPS can generate prediction sets with provable guarantees. The key insight behind GPS is to exploit the inherent structure within the distribution over the minimum number of samples needed to obtain an admissible output to develop a simple conformal regression approach over the minimum number of samples. Experiments on multiple datasets for code and math word problems using different large language models demonstrate the efficacy of GPS over state-of-the-art methods.
Regression discontinuity designs have become one of the most popular research designs in empirical economics. We argue, however, that widely used approaches to building confidence intervals in regression discontinuity designs exhibit suboptimal behavior in practice: In a simulation study calibrated to high-profile applications of regression discontinuity designs, existing methods either have systematic under-coverage or have wider-than-necessary intervals. We propose a new approach, partially linear regression discontinuity inference (PLRD), and find it to address shortcomings of existing methods: Throughout our experiments, confidence intervals built using PLRD are both valid and short. We also provide large-sample guarantees for PLRD under smoothness assumptions.
Forecasting surgical instrument trajectories and predicting the next surgical action recently started to attract attention from the research community. Both these tasks are crucial for automation and assistance in endoscopy surgery. Given the safety-critical nature of these tasks, reliable uncertainty quantification is essential. Conformal prediction is a fast-growing and widely recognized framework for uncertainty estimation in machine learning and computer vision, offering distribution-free, theoretically valid prediction intervals. In this work, we explore the application of standard conformal prediction and conformalized quantile regression to estimate uncertainty in forecasting surgical instrument motion, i.e., predicting direction and magnitude of surgical instruments' future motion. We analyze and compare their coverage and interval sizes, assessing the impact of multiple hypothesis testing and correction methods. Additionally, we show how these techniques can be employed to produce useful uncertainty heatmaps. To the best of our knowledge, this is the first study applying conformal prediction to surgical guidance, marking an initial step toward constructing principled prediction intervals with formal coverage guarantees in this domain.
Unbiased data synthesis is crucial for evaluating causal discovery algorithms in the presence of unobserved confounding, given the scarcity of real-world datasets. A common approach, implicit parameterization, encodes unobserved confounding by modifying the off-diagonal entries of the idiosyncratic covariance matrix while preserving positive definiteness. Within this approach, we identify that state-of-the-art protocols have two distinct issues that hinder unbiased sampling from the complete space of causal models: first, we give a detailed analysis of use of diagonally dominant constructions restricts the spectrum of partial correlation matrices; and second, the restriction of possible graphical structures when sampling bidirected edges, unnecessarily ruling out valid causal models. To address these limitations, we propose an improved explicit modeling approach for unobserved confounding, leveraging block-hierarchical ancestral generation of ground truth causal graphs. Algorithms for converting the ground truth DAG into ancestral graph is provided so that the output of causal discovery algorithms could be compared with. We draw connections between implicit and explicit parameterization, prove that our approach fully covers the space of causal models, including those generated by the implicit parameterization, thus enabling more robust evaluation of methods for causal discovery and inference.
Scenario-based testing with driving simulators is extensively used to identify failing conditions of automated driving assistance systems (ADAS) and reduce the amount of in-field road testing. However, existing studies have shown that repeated test execution in the same as well as in distinct simulators can yield different outcomes, which can be attributed to sources of flakiness or different implementations of the physics, among other factors. In this paper, we present MultiSim, a novel approach to multi-simulation ADAS testing based on a search-based testing approach that leverages an ensemble of simulators to identify failure-inducing, simulator-agnostic test scenarios. During the search, each scenario is evaluated jointly on multiple simulators. Scenarios that produce consistent results across simulators are prioritized for further exploration, while those that fail on only a subset of simulators are given less priority, as they may reflect simulator-specific issues rather than generalizable failures. Our case study, which involves testing a deep neural network-based ADAS on different pairs of three widely used simulators, demonstrates that MultiSim outperforms single-simulator testing by achieving on average a higher rate of simulator-agnostic failures by 51%. Compared to a state-of-the-art multi-simulator approach that combines the outcome of independent test generation campaigns obtained in different simulators, MultiSim identifies 54% more simulator-agnostic failing tests while showing a comparable validity rate. An enhancement of MultiSim that leverages surrogate models to predict simulator disagreements and bypass executions does not only increase the average number of valid failures but also improves efficiency in finding the first valid failure.
Counterfactual explanations indicate the smallest change in input that can translate to a different outcome for a machine learning model. Counterfactuals have generated immense interest in high-stakes applications such as finance, education, hiring, etc. In several use-cases, the decision-making process often relies on an ensemble of models rather than just one. Despite significant research on counterfactuals for one model, the problem of generating a single counterfactual explanation for an ensemble of models has received limited interest. Each individual model might lead to a different counterfactual, whereas trying to find a counterfactual accepted by all models might significantly increase cost (effort). We propose a novel strategy to find the counterfactual for an ensemble of models using the perspective of entropic risk measure. Entropic risk is a convex risk measure that satisfies several desirable properties. We incorporate our proposed risk measure into a novel constrained optimization to generate counterfactuals for ensembles that stay valid for several models. The main significance of our measure is that it provides a knob that allows for the generation of counterfactuals that stay valid under an adjustable fraction of the models. We also show that a limiting case of our entropic-risk-based strategy yields a counterfactual valid for all models in the ensemble (worst-case min-max approach). We study the trade-off between the cost (effort) for the counterfactual and its validity for an ensemble by varying degrees of risk aversion, as determined by our risk parameter knob. We validate our performance on real-world datasets.
The design of novel molecules with desired properties is a key challenge in drug discovery and materials science. Traditional methods rely on trial-and-error, while recent deep learning approaches have accelerated molecular generation. However, existing models struggle with generating molecules based on specific textual descriptions. We introduce Mol-CADiff, a novel diffusion-based framework that uses causal attention mechanisms for text-conditional molecular generation. Our approach explicitly models the causal relationship between textual prompts and molecular structures, overcoming key limitations in existing methods. We enhance dependency modeling both within and across modalities, enabling precise control over the generation process. Our extensive experiments demonstrate that Mol-CADiff outperforms state-of-the-art methods in generating diverse, novel, and chemically valid molecules, with better alignment to specified properties, enabling more intuitive language-driven molecular design.
The accurate prediction of chemical reaction outcomes is a major challenge in computational chemistry. Current models rely heavily on either highly specific reaction templates or template-free methods, both of which present limitations. To address these limitations, this work proposes the Broad Reaction Set (BRS), a dataset featuring 20 generic reaction templates that allow for the efficient exploration of the chemical space. Additionally, ProPreT5 is introduced, a T5 model tailored to chemistry that achieves a balance between rigid templates and template-free methods. ProPreT5 demonstrates its capability to generate accurate, valid, and realistic reaction products, making it a promising solution that goes beyond the current state-of-the-art on the complex reaction product prediction task.
Modern assembly processes require flexibility and adaptability to handle increasing product variety and customization. Traditional assembly planning methods often prioritize finding an optimal assembly sequence, overlooking the requirements of contemporary manufacturing. This work uses Supervisory Control Theory to systematically generate all feasible assembly sequences while ensuring compliance with precedence and process constraints. By synthesizing a controllable, non-blocking, and minimally restrictive supervisor, the proposed method guarantees that only valid sequences are allowed, balancing flexibility and constraint enforcement. The obtained sequences can serve as a basis for further optimization or exception management, improving responsiveness to disruptions.
Multi-Agent Path Finding (MAPF) involves finding collision-free paths for multiple agents while minimizing a cost function--an NP-hard problem. Bounded suboptimal methods like Enhanced Conflict-Based Search (ECBS) and Explicit Estimation CBS (EECBS) balance solution quality with computational efficiency using focal search mechanisms. While effective, traditional focal search faces a limitation: the lower bound (LB) value determining which nodes enter the FOCAL list often increases slowly in early search stages, resulting in a constrained search space that delays finding valid solutions. In this paper, we propose a novel bounded suboptimal algorithm, double-ECBS (DECBS), to address this issue by first determining the maximum LB value and then employing a best-first search guided by this LB to find a collision-free path. Experimental results demonstrate that DECBS outperforms ECBS in most test cases and is compatible with existing optimization techniques. DECBS can reduce nearly 30% high-level CT nodes and 50% low-level focal search nodes. When agent density is moderate to high, DECBS achieves a 23.5% average runtime improvement over ECBS with identical suboptimality bounds and optimizations.
Current LLM pipelines account for only one possible tokenization for a given string, ignoring exponentially many alternative tokenizations during training and inference. For example, the standard Llama3 tokenization of penguin is [p,enguin], yet [peng,uin] is another perfectly valid alternative. In this paper, we show that despite LLMs being trained solely on one tokenization, they still retain semantic understanding of other tokenizations, raising questions about their implications in LLM safety. Put succinctly, we answer the following question: can we adversarially tokenize an obviously malicious string to evade safety and alignment restrictions? We show that not only is adversarial tokenization an effective yet previously neglected axis of attack, but it is also competitive against existing state-of-the-art adversarial approaches without changing the text of the harmful request. We empirically validate this exploit across three state-of-the-art LLMs and adversarial datasets, revealing a previously unknown vulnerability in subword models.
Given the remarkable performance of Large Language Models (LLMs), an important question arises: Can LLMs conduct human-like scientific research and discover new knowledge, and act as an AI scientist? Scientific discovery is an iterative process that demands efficient knowledge updating and encoding. It involves understanding the environment, identifying new hypotheses, and reasoning about actions; however, no standardized benchmark specifically designed for scientific discovery exists for LLM agents. In response to these limitations, we introduce a novel benchmark, \textit{Auto-Bench}, that encompasses necessary aspects to evaluate LLMs for scientific discovery in both natural and social sciences. Our benchmark is based on the principles of causal graph discovery. It challenges models to uncover hidden structures and make optimal decisions, which includes generating valid justifications. By engaging interactively with an oracle, the models iteratively refine their understanding of underlying interactions, the chemistry and social interactions, through strategic interventions. We evaluate state-of-the-art LLMs, including GPT-4, Gemini, Qwen, Claude, and Llama, and observe a significant performance drop as the problem complexity increases, which suggests an important gap between machine and human intelligence that future development of LLMs need to take into consideration.
In the current insurance literature, prediction of insurance claims in the regression problem is often performed with a statistical model. This model-based approach may potentially suffer from several drawbacks: (i) model misspecification, (ii) selection effect, and (iii) lack of finite-sample validity. This article addresses these three issues simultaneously by employing conformal prediction -- a general machine learning strategy for valid predictions. The proposed method is both model-free and tuning-parameter-free. It also guarantees finite-sample validity at a pre-assigned coverage probability level. Examples, based on both simulated and real data, are provided to demonstrate the excellent performance of the proposed method and its applications in insurance, especially regarding meeting the solvency capital requirement of European insurance regulation, Solvency II.
Diffusion-based models have shown great promise in molecular generation but often require a large number of sampling steps to generate valid samples. In this paper, we introduce a novel Straight-Line Diffusion Model (SLDM) to tackle this problem, by formulating the diffusion process to follow a linear trajectory. The proposed process aligns well with the noise sensitivity characteristic of molecular structures and uniformly distributes reconstruction effort across the generative process, thus enhancing learning efficiency and efficacy. Consequently, SLDM achieves state-of-the-art performance on 3D molecule generation benchmarks, delivering a 100-fold improvement in sampling efficiency. Furthermore, experiments on toy data and image generation tasks validate the generality and robustness of SLDM, showcasing its potential across diverse generative modeling domains.
Stochastic models for biochemical reaction networks are widely used to explore their complex dynamics but face significant challenges, including difficulties in determining rate constants and high computational costs. To address these issues, model reduction approaches based on deterministic quasi-steady-state approximations (QSSA) have been employed, resulting in propensity functions in the form of deterministic non-elementary reaction functions, such as the Michaelis-Menten equation. In particular, the total QSSA (tQSSA), known for its accuracy in deterministic frameworks, has been perceived as universally valid for stochastic model reduction. However, recent studies have challenged this perception. In this review, we demonstrate that applying tQSSA in stochastic model reduction can distort dynamics, even in cases where the deterministic tQSSA is rigorously valid. This highlights the need for caution when using deterministic QSSA in stochastic model reduction to avoid erroneous conclusions from model simulations.
Crystal symmetry plays a fundamental role in determining its physical, chemical, and electronic properties such as electrical and thermal conductivity, optical and polarization behavior, and mechanical strength. Almost all known crystalline materials have internal symmetry. However, this is often inadequately addressed by existing generative models, making the consistent generation of stable and symmetrically valid crystal structures a significant challenge. We introduce WyFormer, a generative model that directly tackles this by formally conditioning on space group symmetry. It achieves this by using Wyckoff positions as the basis for an elegant, compressed, and discrete structure representation. To model the distribution, we develop a permutation-invariant autoregressive model based on the Transformer encoder and an absence of positional encoding. Extensive experimentation demonstrates WyFormer's compelling combination of attributes: it achieves best-in-class symmetry-conditioned generation, incorporates a physics-motivated inductive bias, produces structures with competitive stability, predicts material properties with competitive accuracy even without atomic coordinates, and exhibits unparalleled inference speed.
Reliance on stereotypes is a persistent feature of human decision-making and has been extensively documented in educational settings, where it can shape students' confidence, performance, and long-term human capital accumulation. While effective techniques exist to mitigate these negative effects, a crucial first step is to establish whether teachers can recognize stereotypes in their professional environment. We introduce the Stereotype Identification Test (SIT), a novel survey tool that asks teachers to evaluate and comment on the presence of stereotypes in images randomly drawn from school textbooks. Their responses are systematically linked to established measures of implicit bias (Implicit Association Test, IAT) and explicit bias (survey scales on teaching stereotypes and social values). Our findings demonstrate that the SIT is a valid and reliable measure of stereotype recognition. Teachers' ability to recognize stereotypes is linked to trainable traits such as implicit bias awareness and inclusive teaching practices. Moreover, providing personalized feedback on implicit bias improves SIT scores by 0.25 standard deviations, reinforcing the idea that stereotype recognition is malleable and can be enhanced through targeted interventions.
Online misinformation remains a critical challenge, and fact-checkers increasingly rely on embedding-based methods to retrieve relevant fact-checks. Yet, when debunked claims reappear in edited forms, the performance of these methods is unclear. In this work, we introduce a taxonomy of six common real-world misinformation edits and propose a perturbation framework that generates valid, natural claim variations. Our multi-stage retrieval evaluation reveals that standard embedding models struggle with user-introduced edits, while LLM-distilled embeddings offer improved robustness at a higher computational cost. Although a strong reranker helps mitigate some issues, it cannot fully compensate for first-stage retrieval gaps. Addressing these retrieval gaps, our train- and inference-time mitigation approaches enhance in-domain robustness by up to 17 percentage points and boost out-of-domain generalization by 10 percentage points over baseline models. Overall, our findings provide practical improvements to claim-matching systems, enabling more reliable fact-checking of evolving misinformation.
Engineering disciplines often rely on extensive simulations to ensure that structures are designed to withstand harsh conditions while avoiding over-engineering for unlikely scenarios. Assessments such as Serviceability Limit State (SLS) involve evaluating weather events, including estimating loads not expected to be exceeded more than a specified number of times (e.g., 100) throughout the structure's design lifetime. Although physics-based simulations provide robust and detailed insights, they are computationally expensive, making it challenging to generate statistically valid representations of a wide range of weather conditions. To address these challenges, we propose an approach using Gaussian Process (GP) surrogate models trained on a limited set of simulation outputs to directly generate the structural response distribution. We apply this method to an SLS assessment for estimating the order statistics \(Y_{100}\), representing the 100th highest response, of a structure exposed to 25 years of historical weather observations. Our results indicate that the GP surrogate models provide comparable results to full simulations but at a fraction of the computational cost.