Machine Learning

Ming-Yu Liu, NVIDIA vice president of research and head of the Cosmos Lab, joins Practical AI hosts Daniel Whitenack and Chris Benson to discuss AI systems that interact with the physical world. The conversation examines open models, world models and simulation as foundations for robotics and autonomous vehicles, and how research and deployment can advance physical AI. Published 1 October 2026; publisher runtime 47 minutes 19 seconds.

Sam Charrington speaks with Greg Burnham, who leads AI capabilities research at Epoch AI, about the progression from elementary mathematical tasks to difficult research problems, including Navier–Stokes. They examine how advanced systems solve mathematical problems, the roles of persistence and existing human work, and the evidence for new ideas. The conversation also considers how to measure progress when traditional benchmarks become less informative, why improvements appear steady across successive model generations, and the remaining weaknesses in open-ended research, learning from experience and choosing productive scientific questions.

Stanford linguist and computer scientist Chris Manning discusses what linguistics contributed to machine learning and why pragmatics and dialogue remain open problems for language models. The conversation examines early abstraction of verb categories in small transformers, how distributed representations shape learning, and whether language alone can support meaningful representations. It also considers language in world models, diffusion language models, and representation finetuning (ReFT), which steers frozen models through their hidden states. The final discussion asks where knowledge resides and whether concepts occupy linear subspaces.

Nick Kuhn joins Daniel Whitenack and Chris Benson to discuss deploying AI agents alongside conventional enterprise applications. Topics include agent build packs, MCP gateways, shared memory, identity, sandboxing and lessons from platform engineering.

Develop machine-learning methods for early prediction of primary sclerosing cholangitis using clinical and national registry data. The project in the Nouairi research environment explores prediction in people with inflammatory bowel disease, with attention to calibration, validation and interpretable models. It is a research-training scholarship for eligible university students at Karolinska Institutet or a collaborating university. The source does not advertise an amount. Apply by 7 October 2026.

Fund collaborative research on electron transfer between biological and synthetic components, including enzyme–electrode interfaces and electroactive microbes. The programme encourages rigorous mechanistic work and integration of data science or AI, rather than development of a specific end product. Consortia of two to four groups may request DKK 30–75 million over six years. A qualifying European lead institution and Danish participation are required. First-stage applications close on 7 October 2026.

Help Danish research institutions recruit faculty and establish independent research groups in life sciences, medicine and other fields relevant to health or sustainability, including data science and AI. Four-year support is capped at DKK 5 million for assistant professors, DKK 8 million for associate professors and DKK 10 million for full or eligible clinical professors. The institution’s appointment authority must apply for an identified candidate. The deadline is 8 October 2026 at 2 p.m. Copenhagen time.

NSF support for interdisciplinary collaborations developing mathematical and theoretical foundations for explainable, reliable, sustainable and trustworthy artificial intelligence.

Rafael Rosengarten and BioPharmaTrend co-founder Andrii Buvailo discuss how to assess progress in AI-assisted drug discovery. They trace the move from individual computational tasks to connected research workflows and question whether counting AI-associated drug candidates captures the technology’s value. Topics include research productivity, trial design, biomarkers, human expertise and the use of patient-derived data, organoids and other representative biological systems to improve translation. The conversation also considers why AI has become polarising and how specialised models may fit into pharmaceutical research.

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.

Jan Kosinski explains how AlphaFold-style methods predict protein complexes and why their reliance on evolutionary information makes interactions between host and pathogen proteins especially difficult. The talk reviews large-scale studies, interpreting both successful predictions and failures rather than treating reported success rates as universal performance. It then examines ways to improve predictions through broader sampling, altered sequence alignments and experimental restraints, including crosslinking mass spectrometry, with influenza A virus as a worked research example. The session is suitable for students and researchers interested in host-pathogen interactions and structural bioinformatics; basic knowledge of protein structures and sequence alignments is useful, but prior AlphaFold experience is unnecessary.