Professor Thomas G. Dietterich, School of EECS, Oregon State University
Exogenous state variables and rewards can slow reinforcement learning by injecting uncontrolled variation into the reward signal. In this talk, I’ll describe our work on formalizing exogenous state variables and rewards. Then I’ll discuss our main result: if the reward function decomposes additively into endogenous and exogenous components, the MDP can be decomposed into an exogenous Markov Reward Process (based on the exogenous reward) and an endogenous Markov Decision Process (optimizing the endogenous reward).
Gerado Duran-Martin, Oxford-Man Institute, University of Oxford
We propose a unifying framework for methods that perform probabilistic online learning in non-stationary environments. We call the framework BONE, which stands for generalised (B)ayesian (O)nline learning in (N)on-stationary (E)nvironments. BONE provides a common structure to tackle a variety of problems, including online continual learning, prequential forecasting, and contextual bandits.
Ang Yu, Hong Kong University of Science and Technology
We introduce a new nonparametric causal decomposition approach that identifies the mechanisms by which a treatment variable contributes to a group-based outcome disparity. Our approach distinguishes three mechanisms: group differences in: (1) treatment prevalence, (2) average treatment effects, and (3) selection into treatment based on individual-level treatment effects.
Samiran Dey, Indian Association for the Cultivation of Science, Kolkota
Transcriptomic profiling provides rich molecular insights for cancer diagnosis and prognosis, but its high cost limits routine clinical use, where histopathology remains the primary diagnostic modality. Recent advances in artificial intelligence suggest that molecular information can be inferred directly from digital pathology images. This talk discusses a generative multimodal framework that synthesizes transcriptomic features from whole-slide histopathology images and incorporates them to improve cancer
grading and survival risk prediction across multiple cancer cohorts.
In this talk, I will present CodeScaler, a novel framework designed to overcome the scalability bottlenecks of Reinforcement Learning from Verifiable Rewards (RLVR) in code generation. While traditional RLVR relies heavily on the availability of high-quality unit tests—which are often scarce or unreliable—CodeScaler introduces an execution-free reward model that scales both training and test-time inference.
Kevin Monteiro, Department of Computer Science and Technology
Sleep disorders, particularly insomnia, and mental health
conditions affect a significant fraction of adults worldwide, posing seriousmmental and physical health risk. Music therapy offers promising, low-cost, and non-invasive treatment, but current approaches rely heavily on expert-curated playlists, limiting scalability and personalisation. We propose a low-cost generative system leveraging recent advances in diffusion models to synthesize music for therapy. We focus on insomnia and curate a dataset of waveform sleep music to generate audio tailored to sleep.
What’s a numerically verified proof? In pure maths we want to prove theorems, usually using pen and paper. On the other side there exist hundreds of very elaborate ways to approximately solve equations, for example physics-informed neural networks. Due to the advent of greater computational power it has recently become possible to use such approximate solutions in a theorem proofs. In the talk, I’ll explain how that works in a toy example and then briefly mention some applications of this in pure maths.
Mike Lee PhD, Associate Professor Department of Systems Biology, UMass Chan Medical School
*Talk Title:* Life, death, and the discovery of PDAR: the Pol II Degradation-dependent Apoptotic Response
*Abstract:* Many cellular functions are considered “life essential”, but why are they actually essential? Why does a cell die, for instance, when transcription or translation are inhibited, and can we improve cancer therapies by developing a more complete understanding of how cellular life/death decisions are made? To answer these questions, we developed a suite of new tools for studying all forms of cell death.
Training generative AI is not a one-step process. In the case of large language models (LLMs), self-supervision is often followed by supervised and reinforcement learning stages to improve instruction following, safety, and other desirable qualities. This multi-stage process that has emerged in the last 3 years has led to huge leaps in model capabilities. It has also led to new challenges and risks. In this talk, I will overview some of our group's work to identify and address such challenges by focusing on the training data used at different stages.
Prof Isabelle Augenstein (University of Copenhagen)
Language Models (LMs) acquire parametric knowledge from their training process, embedding it within their weights. The increasing scalability of LMs, however, poses significant challenges for understanding a model's inner workings and further for updating or correcting this embedded knowledge without the significant cost of retraining. Moreover, when using these language models for knowledge-intensive language understanding tasks, LMs have to integrate relevant context, mitigating their inherent weaknesses, such as incomplete or outdated knowledge.
We warmly invite you to the C2D3 Computational Biology Annual Symposium 2026. This event is open to everyone in the Computational Biology Community.
https://www.c2d3.cam.ac.uk/events/comp-bio-2026
Early Career Researcher: Abstract Submission
We are inviting Early Career Researchers to present their research during the symposium. Talks should be 17 minutes each, and a short Q&A will follow. Abstract submission - Deadline 9am 1st April 2026.
Registrations
Registration is essential. A waitlist will open if capacity is reached. Registrations - Deadline 9am Monday 4th May 2026.
Scientific discovery emerges not from isolated reasoning, but from the intersection of diverse epistemic traditions. This talk proposes that the modern AI ecosystem, a structured network of heterogeneous reasoning agents spanning approximate and rigorous inference, constitutes a new form of collaborative intelligence for scientific inquiry. Drawing on Simon's conception of reasoning as adaptive search, we argue that such ecosystems do not merely accelerate known reasoning pathways, but create conditions under which genuinely novel representations may emerge.
Scientific discovery emerges not from isolated reasoning, but from the intersection of diverse epistemic traditions. This talk proposes that the modern AI ecosystem, a structured network of heterogeneous reasoning agents spanning approximate and rigorous inference, constitutes a new form of collaborative intelligence for scientific inquiry. Drawing on Simon's conception of reasoning as adaptive search, we argue that such ecosystems do not merely accelerate known reasoning pathways, but create conditions under which genuinely novel representations may emerge.
Scientific discovery emerges not from isolated reasoning, but from the intersection of diverse epistemic traditions. This talk proposes that the modern AI ecosystem, a structured network of heterogeneous reasoning agents spanning approximate and rigorous inference, constitutes a new form of collaborative intelligence for scientific inquiry. Drawing on Simon's conception of reasoning as adaptive search, we argue that such ecosystems do not merely accelerate known reasoning pathways, but create conditions under which genuinely novel representations may emerge.
