paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

Credo: Declarative Control of LLM Pipelines via Beliefs and Policies

Duo Lu, Andrew Crotty, Uğur Çetintemel

Agentic AI systems are becoming commonplace in domains that require long-lived, stateful decision-making in continuously evolving conditions. As such, correctness depends not only on the output of individual model calls, but also on how to best adapt when incorporating new evidence or revising prior conclusions. However, existing frameworks rely on imperative control loops, ephemeral memory, and prompt-embedded logic, making agent behavior opaque, brittle, and difficult to verify. This paper introduces Credo, which represents semantic state as beliefs and regulates behavior using declarative policies defined over these beliefs. This design supports adaptive, auditable, and composable execution through a database-backed semantic control plane. We showcase these concepts in a decision-control scenario, where beliefs and policies declaratively guide critical execution choices (e.g., model selection, retrieval, corrective re-execution), enabling dynamic behavior without requiring any changes to the underlying pipeline code.

arXiv

Evaluation and Hardening of LLM System Instructions Against Extraction via Encoding Attacks

Anubhab Sahu, Diptisha Samanta, Reza Soosahabi

System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications. These instructions may contain sensitive information such as API credentials, internal policies, and privileged workflow definitions, making system instruction leakage a critical security risk highlighted in the OWASP Top 10 for LLM Applications. Without incurring the overhead costs of reasoning models, many LLM applications rely on refusal-based instructions that block direct requests for system instructions, implicitly assuming that prohibited information can only be extracted through explicit queries. We introduce an automated evaluation framework that tests whether system instructions remain confidential when extraction requests are re-framed as encoding or structured output tasks. Across seven common models and 46 verified system instructions, we observe high attack success rates (>0.7) for structured serialization where models refuse direct extraction requests but disclose protected content in the requested serialization formats. We further demonstrate a mitigation strategy based on one-shot instruction reshaping using a Chain-of-Thought reasoning model, indicating that even subtle changes in wording and structure of system instructions can significantly reduce attack success rate without requiring model retraining.

arXiv

REVERE: Reflective Evolving Research Engineer

Balaji Dinesh Gangireddi, Aniketh Garikaparthi, Manasi Patwardhan, Arman Cohan

Existing prompt-optimization techniques rely on local signals, causing poor generalization across tasks. In addition, they also rely on weak update mechanisms, such as full-prompt rewrites or unstructured merges, which cause knowledge loss and unstable adaptation. These limitations are magnified in research-coding workflows, which involve heterogeneous repositories and weak feedback, limiting abstraction and learning across tasks. We introduce Reflective Evolving Research Engineer (REVERE), a lightweight, self-adapting agent framework that learns from a Global Training Context, distills recurring cross-repository failure modes into reusable heuristics, and applies targeted, code-based edits to agent prompts. REVERE is evaluated across settings ranging from long-horizon to single-shot benchmarks, and improves over prior expert-crafted instructions by 4.50% on SUPER, 1.3% on ResearchCodeBench, and 4.89% on ScienceAgentBench. It does so at nearly 10x lower cost and 2.7x faster adaptation than existing prompt-optimization baselines, demonstrating that self-adapting agents with continual learning and global memory consolidation can meaningfully evolve their capabilities over time.

arXiv

VLM2Rec: Resolving Modality Collapse in Vision-Language Model Embedders for Multimodal Sequential Recommendation

Junyoung Kim, Woojoo Kim, Wonbin Kweon, Jaehyung Lim, Dongha Kim, Hwanjo Yu

Sequential Recommendation (SR) in multimodal settings typically relies on small frozen pretrained encoders, which limits semantic capacity and prevents Collaborative Filtering (CF) signals from being fully integrated into item representations. Inspired by the recent success of Large Language Models (LLMs) as high-capacity embedders, we investigate the use of Vision-Language Models (VLMs) as CF-aware multimodal embedders for SR. However, we find that standard contrastive Supervised Fine-Tuning (SFT), used to adapt VLMs for embedding generation and inject CF signals, can amplify inherent modality imbalance: optimization becomes dominated by one modality while the other degrades, ultimately undermining recommendation accuracy. To address this, we propose VLM2Rec, a VLM embedder-based framework for multimodal sequential recommendation designed to promote balanced modality utilization. Specifically, we introduce Weak-modality Penalized Contrastive Learning to mitigate gradient imbalance during optimization and cross-modal Relational Topology Regularization to preserve geometric consistency between modalities. Experiments show that VLM2Rec consistently improves over strong baselines in both accuracy and robustness across diverse scenarios.

arXiv

Behavior and Representation in Open-Weight Large Language Models for Combinatorial Optimization: From Feature Extraction to Algorithm Selection

Francesca Da Ros, Luca Di Gaspero, Kevin Roitero

Recent advances in Large Language Models (LLMs) open new perspectives for automation in optimization, yet little is known about whether their internal representations capture problem structure or algorithmic behavior. We investigate whether representations learned by frozen, open-weight LLMs for combinatorial optimization instances can support downstream decision tasks. The goal is not to replace exact feature extractors or to propose a new algorithm, but to assess whether such representations are reusable for feature recovery and algorithm selection. Our methodology combines direct querying, which tests explicit feature extraction, with probing analyses of whether this information is implicitly encoded in the hidden layers. The probing framework is further extended to a per-instance algorithm selection task. Experiments span four benchmark problems, three instance representations, and five open-weight models from 3B to 120B parameters across the Llama instruct and GPT reasoning families, including a chain-of-thought study on Llama models. Results show a limited ability to recover features explicitly, particularly those requiring structured computation, while part of this information remains implicitly encoded in the hidden states. A consistent gap separates implicit encoding from explicit retrieval. Model scale attenuates this gap, whereas the effect of chain-of-thought prompting depends strongly on model size, and in all cases the gap remains open. Reasoning-oriented models also tend to abstain more when reliable computation is not possible. Notably, the predictive power of LLM hidden-layer representations is comparable to traditional feature extraction across all five models, indicating they can act as effective surrogate descriptors for downstream optimization tasks.

arXiv

A Prior-Aware Metric for Efficiently Distinguishing Memorization from Generalization in Large Language Models

Trishita Tiwari, Ari Trachtenberg, G. Edward Suh

Training data leakage from Large Language Models (LLMs) raises serious concerns related to privacy, security, and copyright compliance. A central challenge in assessing this risk is distinguishing prefix-specific memorization of training data from the generation of statistically common sequences. Existing approaches to measuring memorization often conflate these phenomena, labeling outputs as memorized even when they arise from generalization over common patterns. Counterfactual memorization and other related metrics \citep{zhang2023counterfactual, wang2025generalization, lesci2024causal} provide principled solutions, however, their reliance on retraining multiple baseline models or parsing through the training data makes them computationally impractical at scale. This work introduces \emph{Prior-Aware memorization}, a theoretically grounded, lightweight and training-free criterion for identifying prefix-specific memorization in LLMs. The key idea is to evaluate whether a candidate suffix is strongly associated with its specific training prefix or whether it appears with high probability across many IID sampled sequences from the training data distribution due to statistical commonality. We correlate our metric with counterfactual memorization, and also evaluate it on the training corpora of two pre-trained models, LLaMA and OPT. Our results show that between 55\% and 90\% of sequences previously labeled as memorized fail our criterion and are consistent with statistical commonality

arXiv

Ethics Practices in AI Development: An Empirical Study Across Roles and Regions

Wilder Baldwin, Sepideh Ghanavati, Manuel Woersdoerfer

Recent advances in AI applications have raised growing concerns about the need for ethical guidelines and regulations to mitigate the risks posed by these technologies. In this paper, we present a mixed-methods survey study - combining statistical and qualitative analyses - to examine the ethical perceptions, practices, and knowledge of individuals involved in various AI development roles. Our survey comprises 414 participants from 43 countries, representing various roles such as AI managers, analysts, developers, quality assurance professionals, and information security and privacy experts. The results reveal varying degrees of familiarity and experience with AI ethics principles, government initiatives, and risk mitigation strategies across roles, regions, and other demographic factors. Our findings underscore the importance of a collaborative, role-sensitive approach that involves diverse stakeholders in ethical decision-making throughout the AI development lifecycle. We advocate for developing tailored, inclusive solutions to address ethical challenges in AI development, and we propose future research directions and educational strategies to promote ethics-aware AI practices.

arXiv

Empowering Children to Create AI-Enabled Augmented Reality Experiences

Lei Zhang, Shuyao Zhou, Amna Liaqat, Tinney Mak, Brian Berengard, Emily Qian, Andrés Monroy-Hernández

Despite their potential to enhance children's learning experiences, AI-enabled AR technologies are predominantly used in ways that position children as consumers rather than creators. We introduce Capybara, an AR-based and AI-powered visual programming environment that empowers children to create, customize, and program 3D characters overlaid onto the physical world. Capybara enables children to create virtual characters and accessories using text-to-3D generative AI models, and to animate these characters through auto-rigging and body tracking. In addition, our system employs vision-based AI models to recognize physical objects, allowing children to program interactive behaviors between virtual characters and their physical surroundings. We demonstrate the expressiveness of Capybara through a set of novel AR experiences. We conducted user studies with 20 children in the United States and Argentina. Our findings suggest that Capybara can empower children to harness AI in authoring personalized and engaging AR experiences that seamlessly bridge the virtual and physical worlds.

arXiv

On the Definition of Intelligence

Kei-Sing Ng

To engineer AGI, we should first capture the essence of intelligence in a species-agnostic form that can be evaluated, while being sufficiently general to encompass diverse paradigms of intelligent behavior, including reinforcement learning, generative models, classification, analogical reasoning, and goal-directed decision-making. We propose a general criterion based on \textit{entity fidelity}: Intelligence is the ability, given entities exemplifying a concept, to generate entities exemplifying the same concept. We formalise this intuition as \(\varepsilon\)-concept intelligence: it is \(\varepsilon\)-intelligent with respect to a concept if no chosen admissible distinguisher can separate generated entities from original entities beyond tolerance \(\varepsilon\). We present the formal framework, outline empirical protocols, and discuss implications for evaluation, safety, and generalization.

arXiv

OpenAg: Democratizing Agricultural Intelligence

Srikanth Thudumu, Jason Fisher

Agriculture is undergoing a major transformation driven by artificial intelligence (AI), machine learning, and knowledge representation technologies. However, current agricultural intelligence systems often lack contextual understanding, explainability, and adaptability, especially for smallholder farmers with limited resources. General-purpose large language models (LLMs), while powerful, typically lack the domain-specific knowledge and contextual reasoning needed for practical decision support in farming. They tend to produce recommendations that are too generic or unrealistic for real-world applications. To address these challenges, we present OpenAg, a comprehensive framework designed to advance agricultural artificial general intelligence (AGI). OpenAg combines domain-specific foundation models, neural knowledge graphs, multi-agent reasoning, causal explainability, and adaptive transfer learning to deliver context-aware, explainable, and actionable insights. The system includes: (i) a unified agricultural knowledge base that integrates scientific literature, sensor data, and farmer-generated knowledge; (ii) a neural agricultural knowledge graph for structured reasoning and inference; (iii) an adaptive multi-agent reasoning system where AI agents specialize and collaborate across agricultural domains; and (iv) a causal transparency mechanism that ensures AI recommendations are interpretable, scientifically grounded, and aligned with real-world constraints. OpenAg aims to bridge the gap between scientific knowledge and the tacit expertise of experienced farmers to support scalable and locally relevant agricultural decision-making.

arXiv

Proportional Committee Elections with Positive and Negative Votes

Sonja Kraiczy, Georgios Papasotiropoulos, Grzegorz Pierczyński, Piotr Skowron

In the classic committee election setting each voter approves a subset of candidates and the goal is to select $k$ winners based on these preferences. A central focus of recent research in the area has been to achieve proportional representation. In this work, we explore notions of proportionality in a more expressive setting that allows voters to vote against candidates---a common feature on online polling platforms and beyond. We propose two conceptually distinct interpretations of negative votes, resulting in different perspectives of proportionality. In the first, preventing the election of disapproved candidates is as important to voters as electing approved ones. In the second, approvals and disapprovals are treated separately, with each receiving its own fairness guarantees. For each approach, we introduce suitable axioms capturing proportionality and examine their satisfiability by appropriate variants of Phragmén's rule, Proportional Approval Voting rule (PAV), and the Method of Equal Shares (MES).

arXiv

Reduced Order Modeling for Tsunami Forecasting with Bayesian Hierarchical Pooling

Shane X. Coffing, John Tipton, Arvind T. Mohan, Darren Engwirda

Reduced-order models (ROMs) can represent spatiotemporal processes in significantly fewer dimensions and can often be solved many orders of magnitude faster than their governing partial differential equations (PDEs). For example, proper orthogonal decomposition yields a ROM in which the state is represented as a low-dimensional linear combination of fixed spatial modes and time-dependent coefficients, but this representation remains constrained by the process used to construct the basis. In this work, we explore a new type of ROM that is not restricted to a single fixed coefficient trajectory. Specifically, we consider a corrected Galerkin-projection ROM, formulated as an initial value problem that encodes the physics of the governing PDEs and is calibrated through operator corrections to more accurately reproduce the coefficient dynamics. By combining this corrected reduced model with a Bayesian hierarchical pooling framework over the initial reduced coefficients, we obtain new, statistically interpretable and physically grounded coefficient trajectories that generalize across related scenarios. When recombined with the spatial modes, these trajectories define a complete probabilistic physics surrogate, called a randPROM, for generating simulations that are distributionally consistent with a neighborhood of initial conditions near those used to construct the ROM. We apply the randPROM framework to tsunami modeling, a setting involving unpredictable, catastrophic, and strongly nonlinear dynamics, using both a synthetic case study near Fiji and the real-world 2011 Tohoku tsunami. We demonstrate that randPROMs can substantially reduce the number of full simulations required while providing statistically calibrated and physically defensible predictions of tsunami wave arrival times and heights.

arXiv

On Benchmarking Human-Like Intelligence in Machines

Lance Ying, Katherine M. Collins, Lionel Wong, Ilia Sucholutsky, Ryan Liu, Adrian Weller, Tianmin Shu, Thomas L. Griffiths, Joshua B. Tenenbaum

Recent advances in Artificial Intelligence (AI) have yielded powerful computational models that, by learning from vast amounts of human-generated data, are increasingly posited as approximate models of human cognition. However, we argue that many current evaluation paradigms for AI are insufficient for assessing human-like cognitive capabilities in these models. We identify a set of key shortcomings: a lack of human-validated labels, inadequate representation of human response variability and uncertainty, and reliance on simplified and ecologically invalid tasks. We support our claims by conducting a human evaluation study on nine existing AI benchmarks, suggesting major limitations in task and label designs. To address these limitations, we propose five concrete recommendations for future AI evaluation efforts that will enable more rigorous and meaningful understanding of human-like cognitive capacities in AI models.

arXiv

Automated Design Optimization via Strategic Search with Large Language Models

Anthony Carreon, Vansh Sharma, Venkat Raman

Optimization methods have long advanced many fields, yet they struggle when faced with design problems where the search space and design parameters are difficult to define. Large language models (LLMs) offer a promising alternative by dynamically interpreting design spaces and leveraging encoded domain knowledge. To this end, we present AUTO: an iterative optimization framework that treats design optimization as a strategic search guided by LLM reasoning. The framework separates high-level planning by a Strategist agent from low-level implementation by concurrent Implementor agents, iteratively refining designs through explore-exploit strategies. We demonstrate AUTO on three GPU code optimization problems. For chemical kinetics, AUTO outperforms in-lab-optimized code by up to 1.74$\times$ for problem sizes up to $10^5$ cells. For matrix multiplication, AUTO achieves up to 94\% of cuBLAS double-precision performance. For KernelBench, we achieve speedups of up to 118$\times$ over PyTorch baselines across 29 problems spanning individual operators and full neural network architectures; however, cheating was frequently observed. A posteriori analysis reveals 50~--~70\% alignment with Bayesian optimization sampling strategies. All AUTO simulations ran within 100 iterations (about 10 hours), with estimated costs of \$15~--~159 per run for proprietary models. Furthermore, AUTO is built entirely on open-source LLMs and libraries, demonstrating affordability and data privacy. Given AUTO's generizability and flexibility, future work will explore domains beyond GPUs and supercomputing.

arXiv

Online Correlation Clustering: Simultaneously Optimizing All $\ell_p$-norms

Sami Davies, Benjamin Moseley, Heather Newman

The $\ell_p$-norm objectives for correlation clustering present a fundamental trade-off between minimizing total disagreements (the $\ell_1$-norm) and ensuring fairness to individual nodes (the $\ell_\infty$-norm). Surprisingly, in the offline setting it is possible to simultaneously approximate all $\ell_p$-norms with a single clustering. Can this powerful guarantee be achieved in an online setting? This paper provides the first affirmative answer. We present a single algorithm for the online-with-a-sample (AOS) model that, given a small constant fraction of the input as a sample, produces one clustering that is simultaneously $O(\log^4 n)$-competitive for all $\ell_p$-norms with high probability, $O(\log n)$-competitive for the $\ell_\infty$-norm with high probability, and $O(1)$-competitive for the $\ell_1$-norm in expectation. This work successfully translates the offline "all-norms" guarantee to the online world. Our setting is motivated by a new hardness result that demonstrates a fundamental separation between these objectives in the standard random-order (RO) online model. Namely, while the $\ell_1$-norm is trivially $O(1)$-approximable in the RO model, we prove that any algorithm in the RO model for the fairness-promoting $\ell_\infty$-norm must have a competitive ratio of at least $Ω(n^{1/3})$. This highlights the necessity of a different beyond-worst-case model. We complement our algorithm with lower bounds, showing our competitive ratios for the $\ell_1$- and $\ell_\infty$- norms are nearly tight in the AOS model.

arXiv

Unlearning at Scale: State-Exact Trace-Preserving Deletion in Billion-Parameter Language Models

Abdullah X

Can a prospectively instrumented training continuation reproduce a deletion counterfactual exactly after selected examples leave its replay dataset? We study a trace-preserving counterfactual that fixes recorded execution controls while assigning requested identifiers zero contribution. The guarantee is prospective: the original run must record this execution provenance and retain an eligible uncontaminated checkpoint. Under pinned single-GPU environments, replay from a token store materialized without the requested rows reconstructs a separately executed trace oracle bit-for-bit in model and optimizer state. Pythia 160M is exact across four deletion geometries; Pythia 2.8B matches all 2,775,208,960 model-state elements for a random 5% request; and Llama 3.2 1B is exact after omitting 400 of 4,000 TOFU examples from replay storage. These results establish billion-parameter state exactness. They do not establish cheap deletion, because dispersed requests can force nearly full replay. We release standardized TOFU/OpenUnlearning measurements as descriptive diagnostics only because the frozen campaign lacks the matched controls required for a causal behavioral claim.

arXiv

Efficient Image Restoration with State-Dependent Forward Diffusion

Ziwei Luo, Fredrik K. Gustafsson, Jens Sjölund, Thomas B. Schön

This paper proposes to perform image restoration through a state-dependent mean-reverting forward diffusion (FoD) process. In contrast to traditional diffusion-based approaches that rely on a coupled forward-backward diffusion scheme, FoD directly learns image restoration through a single forward diffusion process, yielding a simple yet efficient framework. The core of FoD is a state-dependent stochastic differential equation (SDE) that involves a mean-reverting term in both the drift and diffusion functions. This mean-reverting structure drives the low-quality data toward the clean endpoint with controlled stochastic variation, therefore simulating a stochastic interpolation between source and target distributions. More importantly, FoD is analytically tractable and is trained using a simple stochastic flow matching objective, enabling few-step sampling during inference. The proposed FoD model, despite its simplicity, achieves strong overall performance on various image restoration tasks compared to representative diffusion, diffusion bridge, and flow matching approaches. The code is available at https://github.com/Algolzw/FoD.

arXiv

Accelerated Markov Chain Monte Carlo Algorithms on Discrete States

Bohan Zhou, Shu Liu, Xinzhe Zuo, Wuchen Li

We propose a class of discrete state sampling algorithms based on Nesterov's accelerated gradient method, which extends the classical Metropolis-Hastings (MH) algorithm. The evolution of the discrete states probability distribution governed by MH can be interpreted as a gradient descent direction of the Kullback--Leibler (KL) divergence, via a mobility function and a score function. Specifically, this gradient is defined on a probability simplex equipped with a discrete Wasserstein-2 metric with a mobility function. This motivates us to study a momentum-based acceleration framework using damped Hamiltonian flows on the simplex set, whose stationary distribution matches the discrete target distribution. Furthermore, we design an interacting particle system to approximate the proposed accelerated sampling dynamics. The extension of the algorithm with a general choice of potentials and mobilities is also discussed. In particular, we choose the accelerated gradient flow of the relative Fisher information, demonstrating the advantages of the algorithm in estimating discrete score functions without requiring the normalizing constant and keeping positive probabilities. Numerical examples, including sampling on a Gaussian mixture supported on lattices or a distribution on a hypercube, demonstrate the effectiveness of the proposed discrete-state sampling algorithm.

arXiv

"Cause" is Mechanistic Narrative within Scientific Domains: An Ordinary Language Philosophical Critique of "Causal Machine Learning"

Vyacheslav Kungurtsev, Leonardo Christov Moore, Gustav Sir, Martin Krutsky

Causal Learning has emerged as a major theme of research in statistics and machine learning in recent years, promising computational techniques to reveal ``true'' causality. In this paper, we critique the premise of causal learning by considering the epistemology of causality across disciplines, applying the Ordinary Language method of an anthropological investigation of customary word use in reasoning about cause and effect in the real world. We observe that although cause-and-effect semantics vary between scientific domains, they maintain a consistent central function of describing the mechanisms underlying forces most salient to the systems under research. A critical distinction is the degree to which the mathematical representations of the models used for statistical analysis exhibit a faithful correspondence to expert knowledge in mechanism. We demarcate 1) physics and engineering as domains wherein mathematical models are sufficient to comprehensively describe causality, in contrast to 2) biology, which studies open and irreducible systems with mechanisms crossing scales through emergence, and 3) the social sciences as suffering from compounding difficulties for precision but providing, through Hermeneutics, the potential for subjective phenomenology yielding findings instrumentally useful to individuals. We posit the greater the discrepancy between expert-defined models and complete characterization of mechanism, the more that epistemic virtue requires that definitive causal claims regarding phenomena can only come through an agglomeration of consistent evidence across multiple domains. Exercising greater caution in communicating the degree of certainty evidence provides, especially demanding restraint in the face of incentives to overstate research conclusions, is the only durable solution to modern science's collective action problems.

arXiv

MatchMiner-AI: Open-source, Privacy-preserving Cancer Clinical Trial Matching using Artificial Intelligence

Jennifer Altreuter, Pavel Trukhanov, Morgan A. Paul, Michael J. Hassett, Irbaz B. Riaz, Muhammad Umar Afzal, Arshad A. Mohammed, Ayub Umair, Huan He, Chueh Husan Hsu, Sarah Sammons, James Lindsay, Emily Mallaber, Harry R. Klein, Gufran Gungor, Matthew Galvin, Michael Deletto, Sabrina Y. Camp, Stephen C. Van Nostrand, James Provencher, Joyce Yu, Naeem Tahir, Jonathan Wischhusen, Olga Kozyreva, Taylor Ortiz, Hande Tuncer, Jad El Masri, Alys Malcolm, Tali Mazor, Ethan Cerami, Kenneth L. Kehl

Background: Clinical trials are essential to advancing cancer treatments, but fewer than 10% of adults with cancer enroll in therapeutic trials. Open-source AI trial matching tools could democratize access to trial options. Methods: We created MatchMiner-AI, co-developed with practicing clinical oncologists and trained on synthetic electronic health record (EHR) data. It uses open-weight LLMs to summarize patient histories from unstructured EHR text and extract target populations from trial eligibility documents. Embedding and re-ranking models were distilled to retrieve and rank trial and patient suggestions. Multifaceted evaluation was performed, including retrospective quantification of distillation fidelity; applying a closed-source LLM as judge of patient summarization and matching; and evaluation of candidate matches by oncologists. Results: Across retrospective evaluations of distillation fidelity, the pipeline outperformed a baseline text-embedding model, improving mean average precision (MAP) at 20 from 0.44 (95% CI 0.44-0.45) to 0.95 (95% CI 0.95-0.96) for trial-enrolled patients and from 0.38 (95% CI 0.37-0.38) to 0.94 (95% CI 0.93-0.94) for patients who received standard of care therapies. In a 50-patient sample selected for comparison between MatchMiner-AI and a rules-based tumor genomic trial matching algorithm, MatchMiner-AI retrieved trials for all patients, as opposed to 19 patients (38%) who had tumor genomic data available. Among those 19 patients, 80% of 256 trial suggestions retrieved by MatchMiner-AI were deemed reasonable considerations by a frontier LLM, vs 53% of 113 suggestions retrieved by the rules-based approach. Conclusion: MatchMiner-AI is an open-source, open-weights, clinical trial matching AI pipeline for oncology. Synthetic training data, model weights, inference tools, and demonstration frontends are publicly available.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.