Machine Learning seminars

Liver toxicity can emerge late in drug development when early assays fail to capture human biology, exposure or injury mechanisms. This webinar introduces Axiom’s hepatic profiling approach, combining multicellular liver systems, high-content imaging, transcriptomics, proteomics and ADME measurements. Its reasoning agent integrates those results with partner assays, chemical-series context, exposure estimates and clinical evidence to assess mechanistic liver-safety risks. Rather than using a single cell-toxicity score, the approach develops interpretable, series-specific structure–toxicity hypotheses, compares analogues, ranks compounds and suggests follow-up experiments or structural changes. Performance on established liver-injury reference compounds and newer molecules is examined through case studies, showing how multimodal evidence can inform medicinal-chemistry decisions and predicted therapeutic index.

Jin Zhu examines statistical approaches to identifying text produced by large language models. The increasing availability of fluent generated writing raises questions about misinformation, academic integrity and the authenticity of digital content. Although detection has attracted substantial machine-learning research, the talk argues that its statistical foundations remain underdeveloped. Zhu presents recent work on principled, computationally efficient detection methods, including approaches reported at NeurIPS and ICLR. An interactive demonstration accompanies the research, illustrating one of the proposed methods.

Arno Onken examines transformer models for predicting responses in the retina and visual cortex. These models learn complex neural-response patterns from large datasets and can transfer learned representations between settings, but fitting and interpreting them differs from linear–nonlinear and convolutional approaches. The talk discusses the opportunities and difficulties this creates for understanding sensory processing. It includes ViV1T, a transformer trained on natural movies that revealed previously uncharacterised response properties in mouse primary visual cortex. The work illustrates how predictive models can generate hypotheses and guide animal experiments. Onken also considers the substantial data and computing requirements and the difficulty of interpreting what the models have learned.

Pulsating ancient stars preserve information about distance, chemical composition and age that can constrain the early history of galaxies. Earl Patrick Bellinger describes advances in stellar-evolution and pulsation simulations, together with machine-learning acceleration, that allow these stellar records to test models of galaxy formation. The talk develops two applications. RR Lyrae stars trace the Galactic halo and Milky Way dwarf galaxies; a new physics-informed approach to their observations enables distance precision of about one percent almost to the Milky Way’s virial radius, supporting galactic archaeology and nearby-universe cosmology. For the distant universe, the presentation examines JWST’s Little Red Dots and evidence for an interpretation as pulsating quasi-stars: black holes surrounded by supermassive, Cepheid-like stellar envelopes. If confirmed, this interpretation could explain both the Little Red Dots and the early formation of supermassive black holes.

AI systems increasingly influence both which images people encounter and predictions of how those images attract attention. This session examines the relationship between automated image selection, predicted visual attention and measured human responses. Peter Steidl presents Visual GEO and a two-stage account of visual communication: an image must first be recognized and selected by a machine before human attention can be measured. Hedda Martina Šola compares machine predictions with human measurements in two published studies using the same material, including a case where an AI-created design was evaluated unfavorably by another AI assessment. Together, the presentations trace the processes determining image visibility and subsequent memory, with implications for benchmarking, transparency, robustness, ethics and the generalizability of predictive models across populations and contexts. The programme includes introductions, discussion and questions.

Raymundo Arróyave discusses alloy discovery guided by both metallurgical knowledge and Bayesian optimization. The approach combines physical models, high-throughput CALPHAD calculations, microstructural information and experimental feedback to search chemical and processing spaces that are difficult to explore through data alone. Examples involving high-entropy and refractory alloys address multiple objectives and constraints, including feasibility, correlated properties, uncertainty and microstructural sensitivity. The seminar then connects these decision methods to the Autonomous Robotic Metallurgist under development at his university. This platform links modular synthesis, characterization and testing with digital twins, human–robot collaboration and AI agents. The aim is a closed experimental loop in which scientific judgment and physical understanding guide automated execution.

Representation learning underlies visual search, retrieval and recognition by encoding gallery images and matching them with queries. Most early work assumes a fixed model, but new training data or more expressive architectures can change the feature representation. Recomputing every gallery vector after an update is expensive for collections containing billions of images and may be impossible when the original images are unavailable because of privacy or storage restrictions. Compatible representation learning aims to update the model while retaining usable existing gallery features. The talk examines the foundational compatibility problem, the role of representation stationarity, and new training techniques that use stationarity to learn compatible feature representations.

Dan Meyer considers the questions generative AI raises for mathematics learning after four years of rapid technological development. He argues that its novelty has been accompanied by educational adoption and institutional change falling short of early expectations, including lower-than-anticipated teacher use. The session explores what the technology can do, what students need and what teaching entails, using these questions to examine AI’s contribution to education.

Oden Institute Seminar by Rex Ying (Yale University) on how non-Euclidean geometries, particularly hyperbolic geometry, can enhance foundation models by better capturing hierarchies and symmetries in real-world data, with applications across Transformers, language model training, multimodal systems, and recommender systems.

Visual information is central to healthcare, agriculture, autonomous systems and communication, but remains expensive to encode, difficult to interpret in detail and vulnerable to manipulation. Manoranjan Paul presents research that combines domain knowledge, structural constraints and careful treatment of noisy observations to make visual AI dependable in practical settings. Four connected directions organize the talk. Compact representations of video and three-dimensional data can support several downstream tasks without separate encodings. Vision-language methods connect image components with semantic descriptions under limited supervision. Efficient task-specific video representations support reasoning across space and time and video question answering. Structural evidence in generated images helps distinguish synthetic content from authentic images. The presentation draws on digital health, environmental sensing and intelligent systems, and closes with research challenges in integrated multimodal pipelines and emerging approaches to computing for imaging.

David Persson presents Polar Express, a method for polar decomposition and the matrix sign function motivated by the Muon neural-network optimizer. It uses matrix multiplications suited to GPUs and adapts each polynomial update through a minimax problem to reduce worst-case error. The talk covers convergence, finite-precision implementation in bfloat16 and validation-loss improvements when training GPT-2 on FineWeb data. This is an in-person PACM IDeAS seminar at Princeton.

José Molina Mora presents an integrative study of the core stress-response mechanisms, or perturbome, of Escherichia coli, Pseudomonas aeruginosa and Staphylococcus aureus. Transcriptomic data are analysed using machine learning, systems biology, functional enrichment and ortholog comparisons to prioritise stress-associated genes. Experimentally determined protein structures are combined with AlphaFold predictions where structural data are missing. Molecular docking and further computational analyses then identify preliminary compounds and conditions that might inhibit selected targets. These results are a proof of concept awaiting experimental validation. The talk connects gene-expression analysis with structural modelling for antimicrobial research and is aimed at researchers, graduate students and professionals in microbiology, bioinformatics and related biomedical fields.

Olivia Di Matteo introduces quantum computing and compilation, examining how the translation from high-level quantum programs to efficient hardware instructions becomes a bottleneck as applications scale. The seminar identifies parts of the quantum software stack where machine learning and artificial intelligence can improve this process. It presents the group’s work using graph-based reinforcement learning to optimize quantum circuits, then considers outstanding challenges and research questions for scalable quantum software.

Stephanie Gil studies reliable coordination in robot networks facing malicious information and ordinary environmental uncertainty. Communication signals provide physical evidence of trustworthiness that is difficult to forge; the cy-trust framework turns that evidence into probabilistic trust estimates and weights neighboring agents accordingly. For consensus and distributed optimization, the analysis establishes almost-sure convergence with bounded departures from nominal performance even when malicious agents form a majority of a node’s neighbors, exceeding the classical Byzantine threshold. Theory and hardware experiments support these guarantees. For natural uncertainty, real-time sensing is incorporated into rollout-based reinforcement learning, reweighting possible futures. Applications include fleet routing under random demand and Project CETI’s autonomous robotic rendezvous with sperm whales at sea. The talk closes with directions for combining trust and long-horizon sequential decisions to retain resilience when planning data may be corrupted.

This webinar introduces supervised, unsupervised and reinforcement learning, then connects those methods to applications beyond conversational language models. Simple examples explain how machine learning and deep learning work and where they can support practical decisions in manufacturing, smart farming, healthcare, gastronomy and tourism. The session includes an introduction to AI Factory Austria, a presentation of the methods and application scenarios, and a concluding discussion. It is delivered in English for beginners; previous technical or AI knowledge is not required. The webinar is free for participants from academia, industry and public administration in EU or EuroHPC JU member countries; registration requires an institutional email address.

The growth of machine-learning conference submissions and rapid uptake of large language models have accelerated research, while leaving open the question of whether findings have become more reliable. A favourable random seed or contamination of a test set can be mistaken for a scientific advance. This lecture examines the resulting gap in trust, analyses common research practices that produce fragile conclusions, and discusses safeguards needed for machine-learning studies to make a durable scientific contribution.